Publications

@conference{Thawakar2025,

title = {Beyond Simple Edits: Composed Video Retrieval with Dense Modifications},

author = {Omkar Thawakar and Dmitry Demidov and Ritesh Thawkar and Rao Anwer and Mubarak Shah and Fahad Khan and Salman Khan},

url = {https://iccv.thecvf.com/virtual/2025/poster/1966},

year  = {2025},

date = {2025-10-19},

urldate = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Composed video retrieval is a challenging task that strives to retrieve a target video based on a query video and a textual description detailing specific modifications. Standard retrieval frameworks typically struggle to handle the complexity of fine-grained compositional queries and variations in temporal understanding limiting their retrieval ability in the fine-grained setting. To address this issue, we introduce a novel dataset that captures both fine-grained and composed actions across diverse video segments, enabling more detailed compositional changes in retrieved video content.The proposed dataset, named Dense-WebVid-CoVR, consists of 1.6 million samples with dense modification text that is around seven times more than its existing counterpart. We further develop a new model that integrates visual and textual information through Cross-Attention (CA) fusion using grounded text encoder, enabling precise alignment between dense query modifications and target videos. The proposed model achieves state-of-the-art results surpassing existing methods on all metrics. Notably, it achieves 71.3% Recall@1 in visual+text setting and outperforms the state-of-the-art by 3.4%, highlighting its efficacy in terms of leveraging detailed video descriptions and dense modification texts. Our proposed dataset, code, and model will be publicly released.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Wang2025b,

title = {CaO$_2$ : Rectifying Inconsistencies in Diffusion-Based Dataset Distillation},

author = {Haoxuan Wang and Zhenghao Zhao and Junyi Wu and Yuzhang Shang and Gaowen Liu and Yan Yan},

url = {https://arxiv.org/abs/2506.22637},

year  = {2025},

date = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {The recent introduction of diffusion models in dataset distillation has shown promising potential in creating compact surrogate datasets for large, high-resolution target datasets, offering improved efficiency and performance over traditional bi-level/uni-level optimization methods. However, current diffusion-based dataset distillation approaches overlook the evaluation process and exhibit two critical inconsistencies in the distillation process: (1) Objective Inconsistency, where the distillation process diverges from the evaluation objective, and (2) Condition Inconsistency, leading to mismatches between generated images and their corresponding conditions. To resolve these issues, we introduce Condition-aware Optimization with Objective-guided Sampling (CaO_2), a two-stage diffusion-based framework that aligns the distillation process with the evaluation objective. The first stage employs a probability-informed sample selection pipeline, while the second stage refines the corresponding latent representations to improve conditional likelihood. CaO_2 achieves state-of-the-art performance on ImageNet and its subsets, surpassing the best-performing baselines by an average of 2.3% accuracy.

},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {Colors See Colors Ignore: Clothes Changing ReID with Color Disentanglement},

author = {Priyank Pathak and Yogesh Singh Rawat},

url = {https://arxiv.org/abs/2507.07230},

year  = {2025},

date = {2025-10-19},

urldate = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Clothes-Changing Re-Identification (CC-ReID) aims to recognize individuals across different locations and times, irrespective of clothing. Existing methods often rely on additional models or annotations to learn robust, clothing-invariant features, making them resource-intensive. In contrast, we explore the use of color - specifically foreground and background colors - as a lightweight, annotation-free proxy for mitigating appearance bias in ReID models. We propose Colors See, Colors Ignore (CSCI), an RGB-only method that leverages color information directly from raw images or video frames. CSCI efficiently captures color-related appearance bias ('Color See') while disentangling it from identity-relevant ReID features ('Color Ignore'). To achieve this, we introduce S2A self-attention, a novel self-attention to prevent information leak between color and identity cues within the feature space. Our analysis shows a strong correspondence between learned color embeddings and clothing attributes, validating color as an effective proxy when explicit clothing labels are unavailable. We demonstrate the effectiveness of CSCI on both image and video ReID with extensive experiments on four CC-ReID datasets. We improve the baseline by Top-1 2.9% on LTCC and 5.0% on PRCC for image-based ReID, and 1.0% on CCVID and 2.5% on MeVID for video-based ReID without relying on additional supervision. Our results highlight the potential of color as a cost-effective solution for addressing appearance bias in CC-ReID. Github: this https URL.

},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Yuan2025,

title = {DLFR-Gen: Diffusion-based Video Generation with Dynamic Latent Frame Rate},

author = {Zhihang Yuan and Rui Xie and Yuzhang Shang and Hanling Zhang and Siyuan Wang and Shengen Yan and Guohao Dai and Yu Wang},

year  = {2025},

date = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {DreamDance: Animating Human Images by Enriching 3D Geometry Cues from 2D Poses},

author = {Yatian Pang and Bin Zhu and Bin Lin and Mingzhe Zheng and Francis Tay and Ser-Nam Lim and Harry Yang and Li Yuan},

url = {https://pang-yatian.github.io/Dreamdance-webpage/

https://arxiv.org/abs/2412.00397

https://github.com/PKU-YuanGroup/DreamDance

https://pang-yatian.github.io/Dreamdance-webpage/resources/full_video_ids.txt},

year  = {2025},

date = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {In this work, we present DreamDance, a novel method for animating human images using only skeleton pose sequences as conditional inputs. Existing approaches struggle with generating coherent, high-quality content in an efficient and user-friendly manner. Concretely, baseline methods relying on only 2D pose guidance lack the cues of 3D information, leading to suboptimal results, while methods using 3D representation as guidance achieve higher quality but involve a cumbersome and time-intensive process. To address these limitations, DreamDance enriches 3D geometry cues from 2D poses by introducing an efficient diffusion model, enabling high-quality human image animation with various guidance. Our key insight is that human images naturally exhibit multiple levels of correlation, progressing from coarse skeleton poses to fine-grained geometry cues, and further from these geometry cues to explicit appearance details. Capturing such correlations could enrich the guidance signals, facilitating intra-frame coherency and inter-frame consistency. Specifically, we construct the TikTok-Dance5K dataset, comprising 5K high-quality dance videos with detailed frame annotations, including human pose, depth, and normal maps. Next, we introduce a Mutually Aligned Geometry Diffusion Model to generate fine-grained depth and normal maps for enriched guidance. Finally, a Cross-domain Controller incorporates multi-level guidance to animate human images effectively with a video diffusion model. Extensive experiments demonstrate that our method achieves state-of-the-art performance in animating human images.



},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Zhu2025,

title = {EA-Vit: Efficient Adaptation for Elastic Vision Transformer},

author = {Chen Zhu and Wangbo Zhao and Huiwen Zhang and Yuhao Zhou and Weidong Tang and Shuo Wang and Zhihang Yuan and Yuzhang Shang and Xiaojiang Peng and Kai Wang and Dawei Yang},

url = {https://iccv.thecvf.com/virtual/2025/poster/1084

https://arxiv.org/abs/2507.19360},

year  = {2025},

date = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Vision Transformer (ViT) has emerged as a foundational model in computer vision, excelling in generalization and adaptation to downstream tasks. However, supporting diverse resource constraints typically requires retraining multiple, size-specific ViTs, which is both time-consuming and expensive. In this paper, we propose emph{Efficient Elastic ViT Adaptation}, a single ViT framework that encapsulates multiple submodels of varying sizes, eliminating the need for repeated adaptation.We introduce elastic configurations along four key dimensions—embedding dimension, attention heads, MLP expansion ratio, and layer depth—and a lightweight router that selects the optimal submodel under different computational budgets. Training proceeds in two stages: emph{Staged Elastic Adaptation} progressively introduces complexity for efficient joint training of submodels while preserving as much pre-trained knowledge as possible; Subsequently, we integrate the router to refine the model by balancing accuracy and MACs, guiding it to initially focus on a small set of promising submodels for faster convergence within the large design space.Our approach captures an exponentially large family of submodels in a single adaptation process. Extensive experiments demonstrate that, for any resource constraint, the router identifies the best submodel, delivering high performance and reduced overhead compared to previous methods.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Wu2025,

title = {Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognition},

author = {Wenhan Wu and Zhishuai Guo and Chen Chen and Hongfei Xue and Aidong Lu},

url = {https://arxiv.org/abs/2506.22179},

year  = {2025},

date = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Zero-shot skeleton-based action recognition aims to develop models capable of identifying actions beyond the categories encountered during training. Previous approaches have primarily focused on aligning visual and semantic representations but often overlooked the importance of fine-grained action patterns in the semantic space (e.g., the hand movements in drinking water and brushing teeth). To address these limitations, we propose a Frequency-Semantic Enhanced Variational Autoencoder (FS-VAE) to explore the skeleton semantic representation learning with frequency decomposition. FS-VAE consists of three key components: 1) a frequency-based enhancement module with high- and low-frequency adjustments to enrich the skeletal semantics learning and improve the robustness of zero-shot action recognition; 2) a semantic-based action description with multilevel alignment to capture both local details and global correspondence, effectively bridging the semantic gap and compensating for the inherent loss of information in skeleton sequences; 3) a calibrated cross-alignment loss that enables valid skeleton-text pairs to counterbalance ambiguous ones, mitigating discrepancies and ambiguities in skeleton and text features, thereby ensuring robust alignment. Evaluations on the benchmarks demonstrate the effectiveness of our approach, validating that frequency-enhanced semantic features enable robust differentiation of visually and semantically similar action clusters, improving zero-shot action recognition.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Shatwell2025,

title = { GT-Loc: Unifying When and Where in Images through a Joint Embedding Space},

author = {David Shatwell and Ishan Dave and Swetha Sirnam and Mubarak Shah},

url = {https://chatpaper.com/fr/chatpaper/paper/163729

https://arxiv.org/abs/2507.10473#:~:text=14%20Jul%202025%5D-,GT%2DLoc%3A%20Unifying%20When%20and%20Where%20in%20Images,Through%20a%20Joint%20Embedding%20Space&text=Abstract%3ATimestamp%20prediction%20aims%20to,%2C%20retrieval%2C%20and%20digital%20forensics.},

year  = {2025},

date = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Timestamp prediction aims to determine when an image was captured using only visual information, supporting applications such as metadata correction, retrieval, and digital forensics. In outdoor scenarios, hourly estimates rely on cues like brightness, hue, and shadow positioning, while seasonal changes and weather inform date estimation. However, these visual cues significantly depend on geographic context, closely linking timestamp prediction to geo-localization. To address this interdependence, we introduce GT-Loc, a novel retrieval-based method that jointly predicts the capture time (hour and month) and geo-location (GPS coordinates) of an image. Our approach employs separate encoders for images, time, and location, aligning their embeddings within a shared high-dimensional feature space. Recognizing the cyclical nature of time, instead of conventional contrastive learning with hard positives and negatives, we propose a temporal metric-learning objective providing soft targets by modeling pairwise time differences over a cyclical toroidal surface. We present new benchmarks demonstrating that our joint optimization surpasses previous time prediction methods, even those using the ground-truth geo-location as an input during inference. Additionally, our approach achieves competitive results on standard geo-localization tasks, and the unified embedding space facilitates compositional and text-based image retrieval.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Shang2025,

title = {LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models},

author = {Yuzhang Shang and Mu Cai and Bingxin Xu and Yong Jae Lee and Yan Yan},

url = {https://llava-prumerge.github.io/

https://arxiv.org/abs/2403.15388

https://github.com/42Shawn/LLaVA-PruMerge},

year  = {2025},

date = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Large Multimodal Models (LMMs) have shown significant reasoning capabilities by connecting a visual encoder and a large language model. LMMs typically use a fixed amount of visual tokens, such as the penultimate layer features in the CLIP visual encoder, as the prefix content. Recent LMMs incorporate more complex visual inputs, such as high-resolution images and videos, which increase the number of visual tokens significantly. However, due to the design of the Transformer architecture, computational costs associated with these models tend to increase quadratically with the number of input tokens. To tackle this problem, we explore a token reduction mechanism and find, similar to prior work, that many visual tokens are spatially redundant. Based on this, we propose PruMerge, a novel adaptive visual token reduction approach, which largely reduces the number of visual tokens while maintaining comparable model performance. We first select the unpruned visual tokens based on their similarity to class tokens and spatial tokens. We then cluster the pruned tokens based on key similarity and merge the clustered tokens with the unpruned tokens to supplement their information. Empirically, when applied to LLaVA-1.5, our approach can compress the visual tokens by 18 times on average (14 times on MME/TextVQA), and achieve comparable performance across diverse visual question-answering and reasoning tasks. Code and checkpoints will be released. To facilitate future research, we will release our code, dataset, benchmark, and checkpoints at },

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Ma2025,

title = {Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion Models},

author = {Xuran Ma and Yexin Liu and Yaofu LIU and Xianfeng Wu and Mingzhe Zheng and Zihao Wang and Ser-Nam Lim and Harry Yang},

url = {https://iccv.thecvf.com/virtual/2025/poster/1031

https://arxiv.org/abs/2504.03140},

year  = {2025},

date = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Video generation using diffusion models has shown remarkable progress, yet it remains computationally expensive due to the repeated processing of redundant features across blocks and steps. To address this, we propose a novel adaptive feature reuse mechanism that dynamically identifies and caches the most informative features by focusing on foreground and caching more on background, significantly reducing computational overhead with less sacrificing video quality. By leveraging the step and block caching, our method achieves up to 1.8× speed up on HunyuanVideo while maintaining competitive performance on Vbench, PSNR, SSIM, FID and LPIPS. Extensive experiments demonstrate that our approach not only improves efficiency but also enhances the quality of generated videos. The proposed method is generalizable and can be integrated into existing diffusion transformer frameworks.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Abdullah2025,

title = {Punching Bag vs. Punching Person: Motion Transferability in Videos},

author = {Raiyaan Abdullah and Jared Claypoole and Michael Cogswell and Ajay Divakaran and Yogesh Singh Rawat},

url = {https://iccv.thecvf.com/virtual/2025/poster/935},

year  = {2025},

date = {2025-10-19},

urldate = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Action recognition models, both unimodal and multimodal, have demonstrated strong generalization in tasks such as zero-shot learning, base-to-novel transfer, and domain adaptation. However, can they effectively transfer high-level motion concepts across diverse contexts, even within similar distributions? For example, can a model recognize the broad action "Pushing" when presented with unknown variations such as "Pushing something from right to left"? To explore this, we introduce a motion transferability framework with three datasets: (1) Syn-TA, a synthetic dataset with 3D object motions; (2) Kinetics400-TA; and (3) Something-Something-v2-TA, both adapted from natural video datasets. We evaluate 13 state-of-the-art models on these benchmarks and observe a significant drop in performance when recognizing high-level actions in novel contexts. Our analysis reveals: 1) Multimodal models struggle more with fine-grained unknown actions than coarse ones; 2) The bias-free Syn-TA proves as challenging as real-world datasets, with models showing greater performance drops in controlled settings; 3) Larger models improve transferability when spatial cues dominate but struggle with intensive temporal reasoning, while reliance on object and background cues hinders generalization. We further explore how disentangling coarse and fine motions can improve recognition in temporally challenging datasets. Our study establishes a crucial benchmark for assessing motion transferability in action recognition.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Wang2025c,

title = {QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning},

author = {Haoxuan Wang and Yuzhang Shang and Zhihang Yuan and Junyi Wu and Junchi Yan and Yan Yan},

url = {https://arxiv.org/abs/2402.03666},

year  = {2025},

date = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {The practical deployment of diffusion models is still hindered by the high memory and computational overhead. Although quantization paves a way for model compression and acceleration, existing methods face challenges in achieving low-bit quantization efficiently. In this paper, we identify imbalanced activation distributions as a primary source of quantization difficulty, and propose to adjust these distributions through weight finetuning to be more quantization-friendly. We provide both theoretical and empirical evidence supporting finetuning as a practical and reliable solution. Building on this approach, we further distinguish two critical types of quantized layers: those responsible for retaining essential temporal information and those particularly sensitive to bit-width reduction. By selectively finetuning these layers under both local and global supervision, we mitigate performance degradation while enhancing quantization efficiency. Our method demonstrates its efficacy across three high-resolution image generation tasks, obtaining state-of-the-art performance across multiple bit-width settings.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Kang2025b,

title = {Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning},

author = {Weitai Kang and Haifeng Huang and Yuzhang Shang and Mubarak Shah and Yan Yan},

url = {https://arxiv.org/abs/2410.00255

https://github.com/WeitaiKang/Robin3D},

year  = {2025},

date = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Recent advancements in 3D Large Language Models (3DLLMs) have highlighted their potential in building general-purpose agents in the 3D real world, yet challenges remain due to the lack of high-quality robust instruction-following data, leading to limited discriminative power and generalization of 3DLLMs. In this paper, we introduce Robin3D, a powerful 3DLLM trained on large-scale instruction-following data generated by our novel data engine, Robust Instruction Generation (RIG) engine. RIG generates two key instruction data: 1) the Adversarial Instruction-following data, which features mixed negative and positive samples to enhance the model's discriminative understanding. 2) the Diverse Instruction-following data, which contains various instruction styles to enhance model's generalization. As a result, we construct 1 million instruction-following data, consisting of 344K Adversarial samples, 508K Diverse samples, and 165K benchmark training set samples. To better handle these complex instructions, Robin3D first incorporates Relation-Augmented Projector to enhance spatial understanding, and then strengthens the object referring and grounding ability through ID-Feature Bonding. Robin3D consistently outperforms previous methods across five widely-used 3D multimodal learning benchmarks, without the need for task-specific fine-tuning. Notably, we achieve a 7.8% improvement in the grounding task (Multi3DRefer) and a 6.9% improvement in the captioning task (Scan2Cap).},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Pinyoanuntapong2025,

title = {Spatio-Temporal Control for Masked Motion Synthesis},

author = {Ekkasit Pinyoanuntapong and Muhammad Usama Saleem and Korrawe Karunratanakul and Pu Wang and Hongfei Xue and Chen Chen and chuan guo and Junli Cao and Jian Ren and Sergey Tulyakov},

url = {https://www.ekkasit.com/ControlMM-page/

https://github.com/exitudio/MaskControl/},

year  = {2025},

date = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Recent advances in motion diffusion models have enabled spatially controllable text-to-motion generation. However, these models struggle to achieve high-precision control while maintaining high-quality motion generation. To address these challenges, we propose MaskControl, the first approach to introduce controllability to the generative masked motion model. Our approach introduces two key innovations. First, textit{Logits Regularizer} implicitly perturbs logits at training time to align the distribution of motion tokens with the controlled joint positions, while regularizing the categorical token prediction to ensure high-fidelity generation. Second, textit{Logit Optimization} explicitly optimizes the predicted logits during inference time, directly reshaping the token distribution that forces the generated motion to accurately align with the controlled joint positions. Moreover, we introduce textit{Differentiable Expectation Sampling (DES)} to combat the non-differential distribution sampling process encountered by logits regularizer and optimization. Extensive experiments demonstrate that MaskControl outperforms state-of-the-art methods, achieving superior motion quality (FID decreases by ~77%) and higher control precision (average error 0.91 vs. 1.08). Additionally, MaskControl enables diverse applications, including any-joint-any-frame control, body-part timeline control, and zero-shot objective control.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Fan2025,

title = {Test-Time Retrieval-Augmented Adaptation for Vision-Language Models},

author = {Xinqi Fan and Xueli Chen and Luoxiao Yang and Chuin Hong Yap and Rizwan Qureshi and Qi Dou and Moi Hoon Yap and Mubarak Shah},

url = {https://iccv.thecvf.com/virtual/2025/poster/2327},

year  = {2025},

date = {2025-10-19},

urldate = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Vision-language models (VLMs) have shown promise in test-time adaptation tasks due to their remarkable capabilities in understanding and reasoning about visual content through natural language descriptions. However, training VLMs typically demands substantial computational resources, and they often struggle to adapt efficiently to new domains or tasks. Additionally, dynamically estimating the test distribution from streaming data at test time remains a significant challenge. In this work, we propose a novel test-time retrieval-augmented adaption (TT-RAA) method that enables VLMs to maintain high performance across diverse visual recognition tasks without the need for task-specific training or large computational overhead. During inference, TT-RAA employs a streaming mixture of Gaussian database (SMGD) to continuously estimate test distributions, requiring minimal storage. Then, TT-RAA retrieves the most relevant information from the SMGD, enhancing the original VLM outputs. A key limitation of CLIP-based VLMs is their inter-modal vision-language optimization, which does not optimize vision-space similarity, leading to larger intra-modal variance. To address this, we propose a multimodal retrieval augmentation module that transforms the SMGD into a unified multimodal space, enabling retrieval that aligns both vision and language modalities. Extensive experiments across both cross-domain and out-of-distribution benchmarks comprising fourteen datasets demonstrate TT-RAA’s superior performance compared to state-of-the-art methods. Ablation studies and hyperparameter analyses further validate the effectiveness of the proposed modules.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Lyu2025,

title = {TLB-VFI: Temporal-Aware Latent Brownian Bridge Diffusion for Video Frame Interpolation},

author = {Zonglin Lyu and Chen Chen},

url = {https://arxiv.org/abs/2507.04984},

year  = {2025},

date = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Video Frame Interpolation (VFI) aims to predict the intermediate frame I_n (we use n to denote time in videos to avoid notation overload with the timestep t in diffusion models) based on two consecutive neighboring frames I_0 and I_1. Recent approaches apply diffusion models (both image-based and video-based) in this task and achieve strong performance. However, image-based diffusion models are unable to extract temporal information and are relatively inefficient compared to non-diffusion methods. Video-based diffusion models can extract temporal information, but they are too large in terms of training scale, model size, and inference time. To mitigate the above issues, we propose Temporal-Aware Latent Brownian Bridge Diffusion for Video Frame Interpolation (TLB-VFI), an efficient video-based diffusion model. By extracting rich temporal information from video inputs through our proposed 3D-wavelet gating and temporal-aware autoencoder, our method achieves 20% improvement in FID on the most challenging datasets over recent SOTA of image-based diffusion models. Meanwhile, due to the existence of rich temporal information, our method achieves strong performance while having 3times fewer parameters. Such a parameter reduction results in 2.3x speed up. By incorporating optical flow guidance, our method requires 9000x less training data and achieves over 20x fewer parameters than video-based diffusion models. },

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Jang2025,

title = {Towards Cross-modal Backward-compatible Representation Learning for Vision-Language Models},

author = {Young Kyun Jang and Ser-Nam Lim},

url = {https://arxiv.org/abs/2405.14715},

year  = {2025},

date = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Modern retrieval systems often struggle with upgrading to new and more powerful models due to the incompatibility of embeddings between the old and new models. This necessitates a costly process known as backfilling, which involves re-computing the embeddings for a large number of data samples. In vision, Backward-compatible Training (BT) has been proposed to ensure that the new model aligns with the old model's embeddings. This paper extends the concept of vision-only BT to the field of cross-modal retrieval, marking the first attempt to address Cross-modal BT (XBT). Our goal is to achieve backward-compatibility between Vision-Language Pretraining (VLP) models, such as CLIP, for the cross-modal retrieval task. To address XBT challenges, we propose an efficient solution: a projection module that maps the new model's embeddings to those of the old model. This module, pretrained solely with text data, significantly reduces the number of image-text pairs required for XBT learning, and, once it is pretrained, it avoids using the old model during training. Furthermore, we utilize parameter-efficient training strategies that improve efficiency and preserve the off-the-shelf new model's knowledge by avoiding any modifications. Experimental results on cross-modal retrieval datasets demonstrate the effectiveness of XBT and its potential to enable backfill-free upgrades when a new VLP model emerges.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Pathak2025b,

title = {Colors See Colors Ignore: Clothes Changing ReID with Color Disentanglement},

author = {Priyank Pathak and Yogesh Rawat},

url = {https://arxiv.org/abs/2507.07230},

year  = {2025},

date = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Clothes-Changing Re-Identification (CC-ReID) aims to recognize individuals across different locations and times, irrespective of clothing. Existing methods often rely on additional models or annotations to learn robust, clothing-invariant features, making them resource-intensive. In contrast, we explore the use of color - specifically foreground and background colors - as a lightweight, annotation-free proxy for mitigating appearance bias in ReID models. We propose Colors See, Colors Ignore (CSCI), an RGB-only method that leverages color information directly from raw images or video frames. CSCI efficiently captures color-related appearance bias ('Color See') while disentangling it from identity-relevant ReID features ('Color Ignore'). To achieve this, we introduce S2A self-attention, a novel self-attention to prevent information leak between color and identity cues within the feature space. Our analysis shows a strong correspondence between learned color embeddings and clothing attributes, validating color as an effective proxy when explicit clothing labels are unavailable. We demonstrate the effectiveness of CSCI on both image and video ReID with extensive experiments on four CC-ReID datasets. We improve the baseline by Top-1 2.9% on LTCC and 5.0% on PRCC for image-based ReID, and 1.0% on CCVID and 2.5% on MeVID for video-based ReID without relying on additional supervision. Our results highlight the potential of color as a cost-effective solution for addressing appearance bias in CC-ReID. Github: this https URL.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Shatwell2025b,

title = {GT-Loc: Unifying When and Where in Images through a Joint Embedding Space},

author = {David Shatwell and Ishan Dave and Swetha Sirnam and Mubarak Shah},

url = {https://chatpaper.com/fr/chatpaper/paper/163729 https://arxiv.org/abs/2507.10473#:~:text=14%20Jul%202025%5D-,GT%2DLoc%3A%20Unifying%20When%20and%20Where%20in%20Images,Through%20a%20Joint%20Embedding%20Space&text=Abstract%3ATimestamp%20prediction%20aims%20to,%2C%20retrieval%2C%20and%20digital%20forensics.},

year  = {2025},

date = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Timestamp prediction aims to determine when an image was captured using only visual information, supporting applications such as metadata correction, retrieval, and digital forensics. In outdoor scenarios, hourly estimates rely on cues like brightness, hue, and shadow positioning, while seasonal changes and weather inform date estimation. However, these visual cues significantly depend on geographic context, closely linking timestamp prediction to geo-localization. To address this interdependence, we introduce GT-Loc, a novel retrieval-based method that jointly predicts the capture time (hour and month) and geo-location (GPS coordinates) of an image. Our approach employs separate encoders for images, time, and location, aligning their embeddings within a shared high-dimensional feature space. Recognizing the cyclical nature of time, instead of conventional contrastive learning with hard positives and negatives, we propose a temporal metric-learning objective providing soft targets by modeling pairwise time differences over a cyclical toroidal surface. We present new benchmarks demonstrating that our joint optimization surpasses previous time prediction methods, even those using the ground-truth geo-location as an input during inference. Additionally, our approach achieves competitive results on standard geo-localization tasks, and the unified embedding space facilitates compositional and text-based image retrieval.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Thawakar2025b,

title = {Beyond Simple Edits: Composed Video Retrieval with Dense Modifications},

author = {Omkar Thawakar and Dmitry Demidov and Ritesh Thawkar and Rao Anwer and Mubarak Shah and Fahad Khan and Salman Khan},

url = {https://iccv.thecvf.com/virtual/2025/poster/1966},

year  = {2025},

date = {2025-10-19},

urldate = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Composed video retrieval is a challenging task that strives to retrieve a target video based on a query video and a textual description detailing specific modifications. Standard retrieval frameworks typically struggle to handle the complexity of fine-grained compositional queries and variations in temporal understanding limiting their retrieval ability in the fine-grained setting. To address this issue, we introduce a novel dataset that captures both fine-grained and composed actions across diverse video segments, enabling more detailed compositional changes in retrieved video content.The proposed dataset, named Dense-WebVid-CoVR, consists of 1.6 million samples with dense modification text that is around seven times more than its existing counterpart. We further develop a new model that integrates visual and textual information through Cross-Attention (CA) fusion using grounded text encoder, enabling precise alignment between dense query modifications and target videos. The proposed model achieves state-of-the-art results surpassing existing methods on all metrics. Notably, it achieves 71.3% Recall@1 in visual+text setting and outperforms the state-of-the-art by 3.4%, highlighting its efficacy in terms of leveraging detailed video descriptions and dense modification texts. Our proposed dataset, code, and model will be publicly released.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Wang2025cb,

title = {CaO$_2$ : Rectifying Inconsistencies in Diffusion-Based Dataset Distillation},

author = {Haoxuan Wang and Zhenghao Zhao and Junyi Wu and Yuzhang Shang and Gaowen Liu and Yan Yan},

url = {https://arxiv.org/abs/2506.22637},

year  = {2025},

date = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {The recent introduction of diffusion models in dataset distillation has shown promising potential in creating compact surrogate datasets for large, high-resolution target datasets, offering improved efficiency and performance over traditional bi-level/uni-level optimization methods. However, current diffusion-based dataset distillation approaches overlook the evaluation process and exhibit two critical inconsistencies in the distillation process: (1) Objective Inconsistency, where the distillation process diverges from the evaluation objective, and (2) Condition Inconsistency, leading to mismatches between generated images and their corresponding conditions. To resolve these issues, we introduce Condition-aware Optimization with Objective-guided Sampling (CaO_2), a two-stage diffusion-based framework that aligns the distillation process with the evaluation objective. The first stage employs a probability-informed sample selection pipeline, while the second stage refines the corresponding latent representations to improve conditional likelihood. CaO_2 achieves state-of-the-art performance on ImageNet and its subsets, surpassing the best-performing baselines by an average of 2.3% accuracy.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Ma2025b,

title = {Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion Models},

author = {Xuran Ma and Yexin Liu and Yaofu LIU and Xianfeng Wu and Mingzhe Zheng and Zihao Wang and Ser-Nam Lim and Harry Yang},

url = {https://iccv.thecvf.com/virtual/2025/poster/1031 

https://arxiv.org/abs/2504.03140},

year  = {2025},

date = {2025-10-19},

urldate = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Video generation using diffusion models has shown remarkable progress, yet it remains computationally expensive due to the repeated processing of redundant features across blocks and steps. To address this, we propose a novel adaptive feature reuse mechanism that dynamically identifies and caches the most informative features by focusing on foreground and caching more on background, significantly reducing computational overhead with less sacrificing video quality. By leveraging the step and block caching, our method achieves up to 1.8× speed up on HunyuanVideo while maintaining competitive performance on Vbench, PSNR, SSIM, FID and LPIPS. Extensive experiments demonstrate that our approach not only improves efficiency but also enhances the quality of generated videos. The proposed method is generalizable and can be integrated into existing diffusion transformer frameworks.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Pathak2025bb,

title = {Colors See Colors Ignore: Clothes Changing ReID with Color Disentanglement},

author = {Priyank Pathak and Yogesh Rawat},

url = {https://arxiv.org/abs/2507.07230},

year  = {2025},

date = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Clothes-Changing Re-Identification (CC-ReID) aims to recognize individuals across different locations and times, irrespective of clothing. Existing methods often rely on additional models or annotations to learn robust, clothing-invariant features, making them resource-intensive. In contrast, we explore the use of color - specifically foreground and background colors - as a lightweight, annotation-free proxy for mitigating appearance bias in ReID models. We propose Colors See, Colors Ignore (CSCI), an RGB-only method that leverages color information directly from raw images or video frames. CSCI efficiently captures color-related appearance bias ('Color See') while disentangling it from identity-relevant ReID features ('Color Ignore'). To achieve this, we introduce S2A self-attention, a novel self-attention to prevent information leak between color and identity cues within the feature space. Our analysis shows a strong correspondence between learned color embeddings and clothing attributes, validating color as an effective proxy when explicit clothing labels are unavailable. We demonstrate the effectiveness of CSCI on both image and video ReID with extensive experiments on four CC-ReID datasets. We improve the baseline by Top-1 2.9% on LTCC and 5.0% on PRCC for image-based ReID, and 1.0% on CCVID and 2.5% on MeVID for video-based ReID without relying on additional supervision. Our results highlight the potential of color as a cost-effective solution for addressing appearance bias in CC-ReID. Github: this https URL.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Thawakar2025c,

title = {Beyond Simple Edits: Composed Video Retrieval with Dense Modifications},

author = {Omkar Thawakar and Dmitry Demidov and Ritesh Thawkar and Rao Anwer and Mubarak Shah and Fahad Khan and Salman Khan},

url = {https://iccv.thecvf.com/virtual/2025/poster/1966},

year  = {2025},

date = {2025-10-19},

urldate = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Composed video retrieval is a challenging task that strives to retrieve a target video based on a query video and a textual description detailing specific modifications. Standard retrieval frameworks typically struggle to handle the complexity of fine-grained compositional queries and variations in temporal understanding limiting their retrieval ability in the fine-grained setting. To address this issue, we introduce a novel dataset that captures both fine-grained and composed actions across diverse video segments, enabling more detailed compositional changes in retrieved video content.The proposed dataset, named Dense-WebVid-CoVR, consists of 1.6 million samples with dense modification text that is around seven times more than its existing counterpart. We further develop a new model that integrates visual and textual information through Cross-Attention (CA) fusion using grounded text encoder, enabling precise alignment between dense query modifications and target videos. The proposed model achieves state-of-the-art results surpassing existing methods on all metrics. Notably, it achieves 71.3% Recall@1 in visual+text setting and outperforms the state-of-the-art by 3.4%, highlighting its efficacy in terms of leveraging detailed video descriptions and dense modification texts. Our proposed dataset, code, and model will be publicly released.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Wang2025cc,

title = {CaO$_2$ : Rectifying Inconsistencies in Diffusion-Based Dataset Distillation},

author = {Haoxuan Wang and Zhenghao Zhao and Junyi Wu and Yuzhang Shang and Gaowen Liu and Yan Yan},

url = {https://arxiv.org/abs/2506.22637},

year  = {2025},

date = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {The recent introduction of diffusion models in dataset distillation has shown promising potential in creating compact surrogate datasets for large, high-resolution target datasets, offering improved efficiency and performance over traditional bi-level/uni-level optimization methods. However, current diffusion-based dataset distillation approaches overlook the evaluation process and exhibit two critical inconsistencies in the distillation process: (1) Objective Inconsistency, where the distillation process diverges from the evaluation objective, and (2) Condition Inconsistency, leading to mismatches between generated images and their corresponding conditions. To resolve these issues, we introduce Condition-aware Optimization with Objective-guided Sampling (CaO_2), a two-stage diffusion-based framework that aligns the distillation process with the evaluation objective. The first stage employs a probability-informed sample selection pipeline, while the second stage refines the corresponding latent representations to improve conditional likelihood. CaO_2 achieves state-of-the-art performance on ImageNet and its subsets, surpassing the best-performing baselines by an average of 2.3% accuracy.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Ma2025c,

title = {Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion Models},

author = {Xuran Ma and Yexin Liu and Yaofu LIU and Xianfeng Wu and Mingzhe Zheng and Zihao Wang and Ser-Nam Lim and Harry Yang},

url = {https://iccv.thecvf.com/virtual/2025/poster/1031 

https://arxiv.org/abs/2504.03140},

year  = {2025},

date = {2025-10-19},

urldate = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Video generation using diffusion models has shown remarkable progress, yet it remains computationally expensive due to the repeated processing of redundant features across blocks and steps. To address this, we propose a novel adaptive feature reuse mechanism that dynamically identifies and caches the most informative features by focusing on foreground and caching more on background, significantly reducing computational overhead with less sacrificing video quality. By leveraging the step and block caching, our method achieves up to 1.8× speed up on HunyuanVideo while maintaining competitive performance on Vbench, PSNR, SSIM, FID and LPIPS. Extensive experiments demonstrate that our approach not only improves efficiency but also enhances the quality of generated videos. The proposed method is generalizable and can be integrated into existing diffusion transformer frameworks.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Azad2025bb,

title = {DisenQ: Disentangling Q-Former for Activity-Biometrics},

author = {Shehreen Azad and Yogesh Rawat},

url = {https://chatpaper.com/pt/chatpaper/paper/163039 

https://arxiv.org/abs/2507.07262},

year  = {2025},

date = {2025-10-19},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {In this work, we address activity-biometrics, which involves identifying individuals across diverse set of activities. Unlike traditional person identification, this setting introduces additional challenges as identity cues become entangled with motion dynamics and appearance variations, making biometrics feature learning more complex. While additional visual data like pose and/or silhouette help, they often struggle from extraction inaccuracies. To overcome this, we propose a multimodal language-guided framework that replaces reliance on additional visual data with structured textual supervision. At its core, we introduce textbfDisenQ (textbfDisentangling textbfQ-Former), a unified querying transformer that disentangles biometrics, motion, and non-biometrics features by leveraging structured language guidance. This ensures identity cues remain independent of appearance and motion variations, preventing misidentifications. We evaluate our approach on three activity-based video benchmarks, achieving state-of-the-art performance. Additionally, we demonstrate strong generalization to complex real-world scenario with competitive performance on a traditional video-based identification benchmark, showing the effectiveness of our framework.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Li2023,

title = {AlignDet: Aligning Pre-training and Fine-tuning in Object Detection},

author = {Ming Li and Jie Wu and Xionghui Wang and Chen Chen and Jie Qin and Xuefeng Xiao and Rui Wang and Min Zheng and Xin Pan},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2307.11077.pdf 

https://arxiv.org/abs/2307.11077 

https://github.com/liming-ai/AlignDet https://openreview.net/forum?id=8PA2nX9v_r2 

https://liming-ai.github.io/AlignDet/},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Peng2023,

title = {Source-free Domain Adaptive Human Pose Estimation},

author = {Qucheng Peng and Ce Zheng and Chen Chen},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2308.03202.pdf 

https://arxiv.org/abs/2308.03202 

https://github.com/davidpengucf/SFDAHPE},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Human Pose Estimation (HPE) is widely used in various fields, including motion analysis, healthcare, and virtual reality. However, the great expenses of labeled real-world datasets present a significant challenge for HPE. To overcome this, one approach is to train HPE models on synthetic datasets and then perform domain adaptation (DA) on realworld data. Unfortunately, existing DA methods for HPE neglect data privacy and security by using both source and target data in the adaptation process. To this end, we propose a new task, named sourcefree domain adaptive HPE, which aims to address the challenges of cross-domain learning of HPE without access to source data during the adaptation process. We further propose a novel framework that consists of three models: source model, intermediate model, and target model, which explores the task from both sourceprotect and target-relevant perspectives. The sourceprotect module preserves source information more effectively while resisting noise, and the target-relevant module reduces the sparsity of spatial representations by building a novel spatial probability space, and pose-specific contrastive learning and information maximization are proposed on the basis of this space. Comprehensive experiments on several domain adaptive HPE benchmarks show that the proposed method outperforms existing approaches by a considerable margin.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey_88,

title = {FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learning},

author = {Guangyu Sun and Matias Mendieta and Chen Chen},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2308.09160.pdf 

https://arxiv.org/abs/2308.09160 

https://github.com/imguangyu/FedPerfix},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {We propose and analyze a general framework of federated learning with partial model personalization. Compared with full model personalization, partial model personalization relies on domain knowledge to select a small portion of the model to personalize, thus imposing a much smaller on-device memory footprint. We propose two federated optimization algorithms for training partially personalized models, where the shared and personal parameters are updated either simultaneously or alternately on each device, but only the shared parameters are communicated and aggregated at the server. We give convergence analyses of both algorithms for minimizing smooth nonconvex functions, providing theoretical support of them for training deep learning models. Our experiments on real-world image and text datasets demonstrate that (a) partial model personalization can obtain most of the benefit of full model personalization with a small fraction of personalized parameters, and, (b) the alternating update algorithm often outperforms the simultaneous update algorithm.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey_89,

title = {PGFed: Personalize Each Client's Global Objective for Federated Learning},

author = {Jun Luo and Matias Mendieta and Chen Chen},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2212.01448.pdf 

https://github.com/ljaiverson/pgfed},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {The mediocre performance of conventional federated learning (FL) over heterogeneous data has been facilitating personalized FL solutions, where, unlike conventional FL which trains a single global consensus model, different models are allowed for different clients. However, in most existing personalized FL algorithms, the collaborative knowledge across the federation was only implicitly passed to the clients in ways such as model aggregation or regularization. We observed that this implicit knowledge transfer fails to maximize the potential value of each client's empirical risk toward other clients. Based on our observation, in this work, we propose Personalized Global Federated Learning (PGFed), a novel personalized FL framework that enables each client to personalize its own global objective by explicitly and adaptively aggregating the empirical risks of itself and other clients. To avoid massive (O(N2)) communication overhead and potential privacy leakage, each client's risk is estimated through a first-order approximation for other clients' adaptive risk aggregation. On top of PGFed, we develop a momentum upgrade, dubbed PGFedMo, to more efficiently utilize clients' empirical risks. Our extensive experiments under different federated settings with benchmark datasets show consistent improvements of PGFed over the compared state-of-the-art alternatives.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey_90,

title = {A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition},

author = {Andong Dang and Taojiannan Yang and Chen Chen},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2303.13505.pdf 

https://arxiv.org/abs/2303.13505 

https://github.com/AndongDeng/BEAR},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {The goal of building a benchmark (suite of datasets) is to provide a unified protocol for fair evaluation and thus facilitate the evolution of a specific area. Nonetheless, we point out that existing protocols of action recognition could yield partial evaluations due to several limitations. To comprehensively probe the effectiveness of spatiotemporal representation learning, we introduce BEAR, a new BEnchmark on video Action Recognition. BEAR is a collection of 18 video datasets grouped into 5 categories (anomaly, gesture, daily, sports, and instructional), which covers a diverse set of real-world applications. With BEAR, we thoroughly evaluate 6 common spatiotemporal models pre-trained by both supervised and self-supervised learning. We also report transfer performance via standard finetuning, few-shot finetuning, and unsupervised domain adaptation. Our observation suggests that current state-of-the-art cannot solidly guarantee high performance on datasets close to real-world applications, and we hope BEAR can serve as a fair and challenging evaluation benchmark to gain insights on building next-generation spatiotemporal learners. Our dataset, code, and models are released at: https://github.com/AndongDeng/BEAR},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey_91,

title = {Towards Geospatial Foundation Models via Continual Pretraining},

author = {Matias Mendieta and Chen Chen},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2302.04476.pdf 

https://arxiv.org/abs/2302.04476 

https://github.com/mmendiet/GFM},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Geospatial technologies are becoming increasingly essential in our world for a wide range of applications, including agriculture, urban planning, and disaster response. To help improve the applicability and performance of deep learning models on these geospatial tasks, various works have begun investigating foundation models for this domain. Researchers have explored two prominent approaches for introducing such models in geospatial applications, but both have drawbacks in terms of limited performance benefit or prohibitive training cost. Therefore, in this work, we propose a novel paradigm for building highly effective geospatial foundation models with minimal resource cost and carbon impact. We first construct a compact yet diverse dataset from multiple sources to promote feature diversity, which we term GeoPile. Then, we investigate the potential of continual pretraining from large-scale ImageNet-22k models and propose a multi-objective continual pretraining paradigm, which leverages the strong representations of ImageNet while simultaneously providing the freedom to learn valuable in-domain features. Our approach outperforms previous state-of-the-art geospatial pretraining methods in an extensive evaluation on seven downstream datasets covering various tasks such as change detection, classification, multi-label classification, semantic segmentation, and super-resolution.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey_92,

title = {Multi-view Self-supervised Disentanglement for General Image Denoising},

author = {Hao Chen and Chenyuan Qu and Yu Zhang and Chen Chen and Jianbo Jiao},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/ICCV2023_MeD_Final_Version.pdf 

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/ICCV2023_MeD_Supplymentary_Final_Version.pdf 

https://chqwer2.github.io/MeD/ 

https://github.com/chqwer2/Multi-view-Self-supervised-Disentanglement-Denoising},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {With its significant performance improvements, the deep 

learning paradigm has become a standard tool for modern 

image denoisers. While promising performance has been 

shown on seen noise distributions, existing approaches often suffer from generalisation to unseen noise types or general and real noise. It is understandable as the model is 

designed to learn paired mapping (e.g. from a noisy image 

to its clean version). In this paper, we instead propose to 

learn to disentangle the noisy image, under the intuitive 

assumption that different corrupted versions of the same 

clean image share a common latent space. A self-supervised 

learning framework is proposed to achieve the goal, without looking at the latent clean image. By taking two different corrupted versions of the same image as input, the proposed Multi-view Self-supervised Disentanglement (MeD) approach learns to disentangle the latent clean features from the corruptions and recover the clean image consequently. Extensive experimental analysis on both synthetic and real noise shows the superiority of the proposed method over prior self-supervised approaches, especially on unseen novel noise types. On real noise, the proposed method even outperforms its supervised counterparts by over 3 dB.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey_93,

title = {RenderIH: A large-scale synthetic dataset for 3D interacting hand pose estimation},

author = {Linrui Tian Lijun Li and Xindi Zhang and Qi Wang and Bang Zhang and Liefeng Bo and Mengyuan Liu and Chen Chen},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Vahidian2023b,

title = {When Do Curricula Work in Federated Learning?},

author = {Saeed Vahidian and Sreevatsank Kadaveru and Woonjoon Baek and Weijia Wang and Vyacheslav Kungurtsev and Chen Chen and Mubarak Shah and Bill Lin},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2212.12712.pdf 

https://arxiv.org/abs/2212.12712},

doi = {https://doi.org/10.48550/arXiv.2212.12712},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {An oft-cited open problem of federated learning is the existence of data heterogeneity at the clients. One pathway to understanding the drastic accuracy drop in federated learning is by scrutinizing the behavior of the clients' deep models on data with different levels of "difficulty", which has been left unaddressed. In this paper, we investigate a different and rarely studied dimension of FL: ordered learning. Specifically, we aim to investigate how ordered learning principles can contribute to alleviating the heterogeneity effects in FL. We present theoretical analysis and conduct extensive empirical studies on the efficacy of orderings spanning three kinds of learning: curriculum, anti-curriculum, and random curriculum. We find that curriculum learning largely alleviates non-IIDness. Interestingly, the more disparate the data distributions across clients the more they benefit from ordered learning. We provide analysis explaining this phenomenon, specifically indicating how curriculum training appears to make the objective landscape progressively less convex, suggesting fast converging iterations at the beginning of the training procedure. We derive quantitative results of convergence for both convex and nonconvex objectives by modeling the curriculum training on federated devices as local SGD with locally biased stochastic gradients. Also, inspired by ordered learning, we propose a novel client selection technique that benefits from the real-world disparity in the clients. Our proposed approach to client selection has a synergic effect when applied together with ordered learning in FL.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Samarasinghe2023,

title = {CDFSL-V: Cross-Domain Few-Shot Learning for Videos},

author = {Sarinda Samarasinghe and Mamshad Nayeem and Rizve Navid Kardan and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/CDFSL_Video_Combined_Final.pdf 

https://sarinda251.github.io/CDFSL-V-site/ https://www.youtube.com/watch?v=RdlEzfW013o},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Few-shot video action recognition is an effective approach to recognizing new categories with only a few labeled examples, thereby reducing the challenges associated with collecting and annotating large-scale video datasets. Existing methods in video action recognition rely on large labeled datasets from the same domain. However, this setup is not realistic as novel categories may come from different data domains that may have different spatial and temporal characteristics. This dissimilarity between the source and target domains can pose a significant challenge, rendering traditional few-shot action recognition techniques ineffective. To address this issue, in this work, we propose a novel cross-domain few-shot video action recognition method that leverages self-supervised learning and curriculum learning to balance the information from the source and target domains. To be particular, our method employs a masked autoencoder-based self-supervised training objective to learn from both source and target data in a self-supervised manner. Then a progressive curriculum balances learning the discriminative information from the source dataset with the generic information learned from the target domain. Initially, our curriculum utilizes supervised learning to learn class discriminative features from the source data. As the training progresses, we transition to learning target-domain-specific features. We propose a progressive curriculum to encourage the emergence of rich features in the target domain based on class discriminative supervised features in the source domain. %a schedule that helps with this transition. We evaluate our method on several challenging benchmark datasets and demonstrate that our approach outperforms existing cross-domain few-shot learning techniques.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey_94,

title = {Preserving Modality Structure Improves Multi-Modal Learning},

author = {Swetha Sirnam and Mamshad Nayeem Rizve and Hilde Kuhne and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2308.13077.pdf 

https://arxiv.org/abs/2308.13077 

https://github.com/Swetha5/Multi_Sinkhorn_Knopp 

https://swetha5.github.io/MultiSK/ 

https://youtu.be/1CrGkUATy50},

doi = {https://doi.org/10.48550/arXiv.2308.13077},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Self-supervised learning on large-scale multi-modal datasets allows learning semantically meaningful embeddings in a joint multi-modal representation space without relying on human annotations. These joint embeddings enable zero-shot cross-modal tasks like retrieval and classification. However, these methods often struggle to generalize well on out-of-domain data as they ignore the semantic structure present in modality-specific embeddings. In this context, we propose a novel Semantic-Structure-Preserving Consistency approach to improve generalizability by preserving the modality-specific relationships in the joint embedding space. To capture modality-specific semantic relationships between samples, we propose to learn multiple anchors and represent the multifaceted relationship between samples with respect to their relationship with these anchors. To assign multiple anchors to each sample, we propose a novel Multi-Assignment Sinkhorn-Knopp algorithm. Our experimentation demonstrates that our proposed approach learns semantically meaningful anchors in a self-supervised manner. Furthermore, our evaluation on MSR-VTT and YouCook2 datasets demonstrates that our proposed multi-anchor assignment based solution achieves state-of-the-art performance and generalizes to both inand out-of-domain datasets. Code: https://github.com/Swetha5/Multi_Sinkhorn_Knopp},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Liu2023b,

title = {Diffusion Action Segmentation},

author = {Daochang Liu and Qiyue Li and Anh-Dung Dinh and Tingting Jiang and Mubarak Shah and Chang Xu},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2303.17959.pdf 

https://arxiv.org/abs/2303.17959 

https://finspire13.github.io/DiffAct-Project-Page/ 

https://github.com/Finspire13/DiffAct 

https://youtu.be/o_Jp8shth7U 

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Slides.pptx},

doi = {https://doi.org/10.48550/arXiv.2303.17959},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Temporal action segmentation is crucial for understanding long-form videos. Previous works on this task commonly adopt an iterative refinement paradigm by using multi-stage models. We propose a novel framework via denoising diffusion models, which nonetheless shares the same inherent spirit of such iterative refinement. In this framework, action predictions are iteratively generated from random noise with input video features as conditions. To enhance the modeling of three striking characteristics of human actions, including the position prior, the boundary ambiguity, and the relational dependency, we devise a unified masking strategy for the conditioning inputs in our framework. Extensive experiments on three benchmark datasets, i.e., GTEA, 50Salads, and Breakfast, are performed and the proposed method achieves superior or comparable results to state-of-the-art methods, showing the effectiveness of a generative approach for action segmentation.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Fioresi2023,

title = {TeD-SPAD: Temporal Distinctiveness for Self-supervised Privacy-preservation for video Anomaly Detection},

author = {Joseph Fioresi and Ishan Dave and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2308.11072.pdf 

https://arxiv.org/abs/2308.11072 

https://github.com/UCF-CRCV/TeD-SPAD 

https://joefioresi718.github.io/TeD-SPAD_webpage/ 

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/TeDSPAD_ICCV_poster.pdf 

https://youtu.be/3a9qeJUD1GU},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey_95,

title = {Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition},

author = {Syed Talal Wasim and Muhammad Uzair Khattak and Muzammal Naseer and Salman Khan and Mubarak Shah and Fahad Shahbaz Khan},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2307.06947.pdf 

https://arxiv.org/abs/2307.06947 

https://talalwasim.github.io/Video-FocalNets/ 

https://github.com/TalalWasim/Video-FocalNets 

https://talalwasim.github.io/Video-FocalNets/#BibTeX},

doi = {https://doi.org/10.48550/arXiv.2307.06947},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Recent video recognition models utilize Transformer models for long-range spatio-temporal context modeling. Video transformer designs are based on self-attention that can model global context at a high computational cost. In comparison, convolutional designs for videos offer an efficient alternative but lack long-range dependency modeling. Towards achieving the best of both designs, this work proposes Video-FocalNet, an effective and efficient architecture for video recognition that models both local and global contexts. Video-FocalNet is based on a spatio-temporal focal modulation architecture that reverses the interaction and aggregation steps of self-attention for better efficiency. Further, the aggregation step and the interaction step are both implemented using efficient convolution and element-wise multiplication operations that are computationally less expensive than their self-attention counterparts on video representations. We extensively explore the design space of focal modulation-based spatio-temporal context modeling and demonstrate our parallel spatial and temporal encoding design to be the optimal choice. Video-FocalNets perform favorably well against the state-of-the-art transformer-based models for video recognition on three large-scale datasets (Kinetics-400, Kinetics-600, and SS-v2) at a lower computational cost. Our code/models are publicly released.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey_96,

title = {Efficiently Robustify Pre-Trained Models},

author = {Nishant Jain and Harkirat Behl and Yogesh Singh Rawat and Vibhav Vineet},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/ICCV23_Robust_Learning.pdf},

year  = {2023},

date = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {A recent trend in deep learning algorithms has been towards training large scale models, having high parameter count and trained on big dataset. However, robustness of such large scale models towards real-world settings is still a less-explored topic. In this work, we first benchmark the performance of these models under different perturbations and datasets thereby representing real-world shifts, and highlight their degrading performance under these shifts. We then discuss on how complete model fine-tuning based existing robustification schemes might not be a scalable option given very large scale networks and can also lead them to forget some of the desired characteristics. Finally, we propose a simple and cost-effective method to solve this problem, inspired by knowledge transfer literature. It involves robustifying smaller models, at a lower computation cost, and then use them as teachers to tune a fraction of these large scale networks, reducing the overall computational overhead. We evaluate our proposed method under various vision perturbations including ImageNet-C,R,S,A datasets and also for transfer learning, zero-shot evaluation setups on different datasets. Benchmark results show that our method is able to induce robustness to these large scale models efficiently, requiring significantly lower time and also preserves the transfer learning, zero-shot properties of the original model which none of the existing methods are able to achieve.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Zhou2023,

title = {BT^2 : Backward-compatible Training with Basis Transformation},

author = {Yifei Zhou and Zilu Li and Abhinav Shrivasta and Hengshuang Zhao and Antonio Torralba and Taipeng Tian and Ser-Nam Lim},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2211.03989v3.pdf 

https://arxiv.org/abs/2211.03989v3},

doi = {https://doi.org/10.48550/arXiv.2211.03989},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Modern retrieval system often requires recomputing the representation of every piece of data in the gallery when updating to a better representation model. This process is known as backfilling and can be especially costly in the real world where the gallery often contains billions of samples. Recently, researchers have proposed the idea of Backward Compatible Training (BCT) where the new representation model can be trained with an auxiliary loss to make it backward compatible with the old representation. In this way, the new representation can be directly compared with the old representation, in principle avoiding the need for any backfilling. However, followup work shows that there is an inherent tradeoff where a backward compatible representation model cannot simultaneously maintain the performance of the new model itself. This paper reports our ``not-so-surprising'' finding that adding extra dimensions to the representation can help here. However, we also found that naively increasing the dimension of the representation did not work. To deal with this, we propose Backward-compatible Training with a novel Basis Transformation (BT2). A basis transformation (BT) is basically a learnable set of parameters that applies an orthonormal transformation. Such a transformation possesses an important property whereby the original information contained in its input is retained in its output. We show in this paper how a BT can be utilized to add only the necessary amount of additional dimensions. We empirically verify the advantage of BT2 over other state-of-the-art methods in a wide range of settings. We then further extend BT2 to other challenging yet more practical settings, including significant change in model architecture (CNN to Transformers), modality change, and even a series of updates in the model architecture mimicking the evolution of deep learning models.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Chen2023b,

title = {Open-vocabulary Panoptic Segmentation with Embedding Modulation},

author = {Xi Chen and Shuang Li and Ser-Nam Lim and Antonio Torralba and Hengshuang Zhao},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2303.11324.pdf 

https://arxiv.org/abs/2303.11324 

https://opsnet-page.github.io/},

doi = {https://doi.org/10.48550/arXiv.2303.11324},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Open-vocabulary image segmentation is attracting increasing attention due to its critical applications in the real world. Traditional closed-vocabulary segmentation methods are not able to characterize novel objects, whereas several recent open-vocabulary attempts obtain unsatisfactory results, i.e., notable performance reduction on the closed vocabulary and massive demand for extra data. To this end, we propose OPSNet, an omnipotent and data-efficient framework for Open-vocabulary Panoptic Segmentation. Specifically, the exquisitely designed Embedding Modulation module, together with several meticulous components, enables adequate embedding enhancement and information exchange between the segmentation model and the visual-linguistic well-aligned CLIP encoder, resulting in superior segmentation performance under both open- and closed-vocabulary settings with much fewer need of additional data. Extensive experimental evaluations are conducted across multiple datasets (e.g., COCO, ADE20K, Cityscapes, and PascalContext) under various circumstances, where the proposed OPSNet achieves state-of-the-art results, which demonstrates the effectiveness and generality of the proposed approach. The code and trained models will be made publicly available.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Hammoud2023,

title = {Towards a True Evaluation of Rapid Adaptation in Online Continual Learning},

author = {Hasan Abed Al Kader Hammoud and Ameya Prabhu and Ser-Nam Lim and Philip Torr and Adel Bibi and Bernard Ghanem},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2305.09275.pdf 

https://arxiv.org/abs/2305.09275 

https://github.com/drimpossible/EvalOCL},

doi = {https://doi.org/10.48550/arXiv.2305.09275},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {We revisit the common practice of evaluating adaptation of Online Continual Learning (OCL) algorithms through the metric of online accuracy, which measures the accuracy of the model on the immediate next few samples. However, we show that this metric is unreliable, as even vacuous blind classifiers, which do not use input images for prediction, can achieve unrealistically high online accuracy by exploiting spurious label correlations in the data stream. Our study reveals that existing OCL algorithms can also achieve high online accuracy, but perform poorly in retaining useful information, suggesting that they unintentionally learn spurious label correlations. To address this issue, we propose a novel metric for measuring adaptation based on the accuracy on the near-future samples, where spurious correlations are removed. We benchmark existing OCL approaches using our proposed metric on large-scale datasets under various computational budgets and find that better generalization can be achieved by retaining and reusing past seen information. We believe that our proposed metric can aid in the development of truly adaptive OCL methods. We provide code to reproduce our results at https://github.com/drimpossible/EvalOCL.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Li2023b,

title = {AlignDet: Aligning Pre-training and Fine-tuning in Object Detection},

author = {Ming Li and Jie Wu and Xionghui Wang and Chen Chen and Jie Qin and Xuefeng Xiao and Rui Wang and Min Zheng and Xin Pan},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2307.11077.pdf 

https://arxiv.org/abs/2307.11077 

https://github.com/liming-ai/AlignDet https://openreview.net/forum?id=8PA2nX9v_r2 

https://liming-ai.github.io/AlignDet/},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Peng2023b,

title = {Source-free Domain Adaptive Human Pose Estimation},

author = {Qucheng Peng and Ce Zheng and Chen Chen},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2308.03202.pdf 

https://arxiv.org/abs/2308.03202 

https://github.com/davidpengucf/SFDAHPE},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Human Pose Estimation (HPE) is widely used in various fields, including motion analysis, healthcare, and virtual reality. However, the great expenses of labeled real-world datasets present a significant challenge for HPE. To overcome this, one approach is to train HPE models on synthetic datasets and then perform domain adaptation (DA) on realworld data. Unfortunately, existing DA methods for HPE neglect data privacy and security by using both source and target data in the adaptation process. To this end, we propose a new task, named sourcefree domain adaptive HPE, which aims to address the challenges of cross-domain learning of HPE without access to source data during the adaptation process. We further propose a novel framework that consists of three models: source model, intermediate model, and target model, which explores the task from both sourceprotect and target-relevant perspectives. The sourceprotect module preserves source information more effectively while resisting noise, and the target-relevant module reduces the sparsity of spatial representations by building a novel spatial probability space, and pose-specific contrastive learning and information maximization are proposed on the basis of this space. Comprehensive experiments on several domain adaptive HPE benchmarks show that the proposed method outperforms existing approaches by a considerable margin.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey_136,

title = {FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learning},

author = {Guangyu Sun and Matias Mendieta and Chen Chen},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2308.09160.pdf 

https://arxiv.org/abs/2308.09160 

https://github.com/imguangyu/FedPerfix},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {We propose and analyze a general framework of federated learning with partial model personalization. Compared with full model personalization, partial model personalization relies on domain knowledge to select a small portion of the model to personalize, thus imposing a much smaller on-device memory footprint. We propose two federated optimization algorithms for training partially personalized models, where the shared and personal parameters are updated either simultaneously or alternately on each device, but only the shared parameters are communicated and aggregated at the server. We give convergence analyses of both algorithms for minimizing smooth nonconvex functions, providing theoretical support of them for training deep learning models. Our experiments on real-world image and text datasets demonstrate that (a) partial model personalization can obtain most of the benefit of full model personalization with a small fraction of personalized parameters, and, (b) the alternating update algorithm often outperforms the simultaneous update algorithm.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey_137,

title = {PGFed: Personalize Each Client's Global Objective for Federated Learning},

author = {Jun Luo and Matias Mendieta and Chen Chen},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2212.01448.pdf 

https://github.com/ljaiverson/pgfed},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {The mediocre performance of conventional federated learning (FL) over heterogeneous data has been facilitating personalized FL solutions, where, unlike conventional FL which trains a single global consensus model, different models are allowed for different clients. However, in most existing personalized FL algorithms, the collaborative knowledge across the federation was only implicitly passed to the clients in ways such as model aggregation or regularization. We observed that this implicit knowledge transfer fails to maximize the potential value of each client's empirical risk toward other clients. Based on our observation, in this work, we propose Personalized Global Federated Learning (PGFed), a novel personalized FL framework that enables each client to personalize its own global objective by explicitly and adaptively aggregating the empirical risks of itself and other clients. To avoid massive (O(N2)) communication overhead and potential privacy leakage, each client's risk is estimated through a first-order approximation for other clients' adaptive risk aggregation. On top of PGFed, we develop a momentum upgrade, dubbed PGFedMo, to more efficiently utilize clients' empirical risks. Our extensive experiments under different federated settings with benchmark datasets show consistent improvements of PGFed over the compared state-of-the-art alternatives.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey_138,

title = {A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition},

author = {Andong Dang and Taojiannan Yang and Chen Chen},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2303.13505.pdf 

https://arxiv.org/abs/2303.13505 

https://github.com/AndongDeng/BEAR},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {The goal of building a benchmark (suite of datasets) is to provide a unified protocol for fair evaluation and thus facilitate the evolution of a specific area. Nonetheless, we point out that existing protocols of action recognition could yield partial evaluations due to several limitations. To comprehensively probe the effectiveness of spatiotemporal representation learning, we introduce BEAR, a new BEnchmark on video Action Recognition. BEAR is a collection of 18 video datasets grouped into 5 categories (anomaly, gesture, daily, sports, and instructional), which covers a diverse set of real-world applications. With BEAR, we thoroughly evaluate 6 common spatiotemporal models pre-trained by both supervised and self-supervised learning. We also report transfer performance via standard finetuning, few-shot finetuning, and unsupervised domain adaptation. Our observation suggests that current state-of-the-art cannot solidly guarantee high performance on datasets close to real-world applications, and we hope BEAR can serve as a fair and challenging evaluation benchmark to gain insights on building next-generation spatiotemporal learners. Our dataset, code, and models are released at: https://github.com/AndongDeng/BEAR},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey_139,

title = {Towards Geospatial Foundation Models via Continual Pretraining},

author = {Matias Mendieta and Chen Chen},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2302.04476.pdf 

https://arxiv.org/abs/2302.04476 

https://github.com/mmendiet/GFM},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Geospatial technologies are becoming increasingly essential in our world for a wide range of applications, including agriculture, urban planning, and disaster response. To help improve the applicability and performance of deep learning models on these geospatial tasks, various works have begun investigating foundation models for this domain. Researchers have explored two prominent approaches for introducing such models in geospatial applications, but both have drawbacks in terms of limited performance benefit or prohibitive training cost. Therefore, in this work, we propose a novel paradigm for building highly effective geospatial foundation models with minimal resource cost and carbon impact. We first construct a compact yet diverse dataset from multiple sources to promote feature diversity, which we term GeoPile. Then, we investigate the potential of continual pretraining from large-scale ImageNet-22k models and propose a multi-objective continual pretraining paradigm, which leverages the strong representations of ImageNet while simultaneously providing the freedom to learn valuable in-domain features. Our approach outperforms previous state-of-the-art geospatial pretraining methods in an extensive evaluation on seven downstream datasets covering various tasks such as change detection, classification, multi-label classification, semantic segmentation, and super-resolution.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey_140,

title = {Multi-view Self-supervised Disentanglement for General Image Denoising},

author = {Hao Chen and Chenyuan Qu and Yu Zhang and Chen Chen and Jianbo Jiao},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/ICCV2023_MeD_Final_Version.pdf 

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/ICCV2023_MeD_Supplymentary_Final_Version.pdf 

https://chqwer2.github.io/MeD/ 

https://github.com/chqwer2/Multi-view-Self-supervised-Disentanglement-Denoising},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {With its significant performance improvements, the deep 

learning paradigm has become a standard tool for modern 

image denoisers. While promising performance has been 

shown on seen noise distributions, existing approaches often suffer from generalisation to unseen noise types or general and real noise. It is understandable as the model is 

designed to learn paired mapping (e.g. from a noisy image 

to its clean version). In this paper, we instead propose to 

learn to disentangle the noisy image, under the intuitive 

assumption that different corrupted versions of the same 

clean image share a common latent space. A self-supervised 

learning framework is proposed to achieve the goal, without looking at the latent clean image. By taking two different corrupted versions of the same image as input, the proposed Multi-view Self-supervised Disentanglement (MeD) approach learns to disentangle the latent clean features from the corruptions and recover the clean image consequently. Extensive experimental analysis on both synthetic and real noise shows the superiority of the proposed method over prior self-supervised approaches, especially on unseen novel noise types. On real noise, the proposed method even outperforms its supervised counterparts by over 3 dB.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey_141,

title = {RenderIH: A large-scale synthetic dataset for 3D interacting hand pose estimation},

author = {Linrui Tian Lijun Li and Xindi Zhang and Qi Wang and Bang Zhang and Liefeng Bo and Mengyuan Liu and Chen Chen},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Vahidian2023bb,

title = {When Do Curricula Work in Federated Learning?},

author = {Saeed Vahidian and Sreevatsank Kadaveru and Woonjoon Baek and Weijia Wang and Vyacheslav Kungurtsev and Chen Chen and Mubarak Shah and Bill Lin},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2212.12712.pdf 

https://arxiv.org/abs/2212.12712},

doi = {https://doi.org/10.48550/arXiv.2212.12712},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {An oft-cited open problem of federated learning is the existence of data heterogeneity at the clients. One pathway to understanding the drastic accuracy drop in federated learning is by scrutinizing the behavior of the clients' deep models on data with different levels of "difficulty", which has been left unaddressed. In this paper, we investigate a different and rarely studied dimension of FL: ordered learning. Specifically, we aim to investigate how ordered learning principles can contribute to alleviating the heterogeneity effects in FL. We present theoretical analysis and conduct extensive empirical studies on the efficacy of orderings spanning three kinds of learning: curriculum, anti-curriculum, and random curriculum. We find that curriculum learning largely alleviates non-IIDness. Interestingly, the more disparate the data distributions across clients the more they benefit from ordered learning. We provide analysis explaining this phenomenon, specifically indicating how curriculum training appears to make the objective landscape progressively less convex, suggesting fast converging iterations at the beginning of the training procedure. We derive quantitative results of convergence for both convex and nonconvex objectives by modeling the curriculum training on federated devices as local SGD with locally biased stochastic gradients. Also, inspired by ordered learning, we propose a novel client selection technique that benefits from the real-world disparity in the clients. Our proposed approach to client selection has a synergic effect when applied together with ordered learning in FL.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Samarasinghe2023b,

title = {CDFSL-V: Cross-Domain Few-Shot Learning for Videos},

author = {Sarinda Samarasinghe and Mamshad Nayeem and Rizve Navid Kardan and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/CDFSL_Video_Combined_Final.pdf 

https://sarinda251.github.io/CDFSL-V-site/ https://www.youtube.com/watch?v=RdlEzfW013o},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Few-shot video action recognition is an effective approach to recognizing new categories with only a few labeled examples, thereby reducing the challenges associated with collecting and annotating large-scale video datasets. Existing methods in video action recognition rely on large labeled datasets from the same domain. However, this setup is not realistic as novel categories may come from different data domains that may have different spatial and temporal characteristics. This dissimilarity between the source and target domains can pose a significant challenge, rendering traditional few-shot action recognition techniques ineffective. To address this issue, in this work, we propose a novel cross-domain few-shot video action recognition method that leverages self-supervised learning and curriculum learning to balance the information from the source and target domains. To be particular, our method employs a masked autoencoder-based self-supervised training objective to learn from both source and target data in a self-supervised manner. Then a progressive curriculum balances learning the discriminative information from the source dataset with the generic information learned from the target domain. Initially, our curriculum utilizes supervised learning to learn class discriminative features from the source data. As the training progresses, we transition to learning target-domain-specific features. We propose a progressive curriculum to encourage the emergence of rich features in the target domain based on class discriminative supervised features in the source domain. %a schedule that helps with this transition. We evaluate our method on several challenging benchmark datasets and demonstrate that our approach outperforms existing cross-domain few-shot learning techniques.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey_142,

title = {Preserving Modality Structure Improves Multi-Modal Learning},

author = {Swetha Sirnam and Mamshad Nayeem Rizve and Hilde Kuhne and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2308.13077.pdf 

https://arxiv.org/abs/2308.13077 

https://github.com/Swetha5/Multi_Sinkhorn_Knopp 

https://swetha5.github.io/MultiSK/ 

https://youtu.be/1CrGkUATy50},

doi = {https://doi.org/10.48550/arXiv.2308.13077},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Self-supervised learning on large-scale multi-modal datasets allows learning semantically meaningful embeddings in a joint multi-modal representation space without relying on human annotations. These joint embeddings enable zero-shot cross-modal tasks like retrieval and classification. However, these methods often struggle to generalize well on out-of-domain data as they ignore the semantic structure present in modality-specific embeddings. In this context, we propose a novel Semantic-Structure-Preserving Consistency approach to improve generalizability by preserving the modality-specific relationships in the joint embedding space. To capture modality-specific semantic relationships between samples, we propose to learn multiple anchors and represent the multifaceted relationship between samples with respect to their relationship with these anchors. To assign multiple anchors to each sample, we propose a novel Multi-Assignment Sinkhorn-Knopp algorithm. Our experimentation demonstrates that our proposed approach learns semantically meaningful anchors in a self-supervised manner. Furthermore, our evaluation on MSR-VTT and YouCook2 datasets demonstrates that our proposed multi-anchor assignment based solution achieves state-of-the-art performance and generalizes to both inand out-of-domain datasets. Code: https://github.com/Swetha5/Multi_Sinkhorn_Knopp},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Liu2023bb,

title = {Diffusion Action Segmentation},

author = {Daochang Liu and Qiyue Li and Anh-Dung Dinh and Tingting Jiang and Mubarak Shah and Chang Xu},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2303.17959.pdf 

https://arxiv.org/abs/2303.17959 

https://finspire13.github.io/DiffAct-Project-Page/ 

https://github.com/Finspire13/DiffAct 

https://youtu.be/o_Jp8shth7U 

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Slides.pptx},

doi = {https://doi.org/10.48550/arXiv.2303.17959},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Temporal action segmentation is crucial for understanding long-form videos. Previous works on this task commonly adopt an iterative refinement paradigm by using multi-stage models. We propose a novel framework via denoising diffusion models, which nonetheless shares the same inherent spirit of such iterative refinement. In this framework, action predictions are iteratively generated from random noise with input video features as conditions. To enhance the modeling of three striking characteristics of human actions, including the position prior, the boundary ambiguity, and the relational dependency, we devise a unified masking strategy for the conditioning inputs in our framework. Extensive experiments on three benchmark datasets, i.e., GTEA, 50Salads, and Breakfast, are performed and the proposed method achieves superior or comparable results to state-of-the-art methods, showing the effectiveness of a generative approach for action segmentation.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Fioresi2023b,

title = {TeD-SPAD: Temporal Distinctiveness for Self-supervised Privacy-preservation for video Anomaly Detection},

author = {Joseph Fioresi and Ishan Dave and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2308.11072.pdf 

https://arxiv.org/abs/2308.11072 

https://github.com/UCF-CRCV/TeD-SPAD 

https://joefioresi718.github.io/TeD-SPAD_webpage/ 

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/TeDSPAD_ICCV_poster.pdf 

https://youtu.be/3a9qeJUD1GU},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey_143,

title = {Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition},

author = {Syed Talal Wasim and Muhammad Uzair Khattak and Muzammal Naseer and Salman Khan and Mubarak Shah and Fahad Shahbaz Khan},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2307.06947.pdf 

https://arxiv.org/abs/2307.06947 

https://talalwasim.github.io/Video-FocalNets/ 

https://github.com/TalalWasim/Video-FocalNets 

https://talalwasim.github.io/Video-FocalNets/#BibTeX},

doi = {https://doi.org/10.48550/arXiv.2307.06947},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Recent video recognition models utilize Transformer models for long-range spatio-temporal context modeling. Video transformer designs are based on self-attention that can model global context at a high computational cost. In comparison, convolutional designs for videos offer an efficient alternative but lack long-range dependency modeling. Towards achieving the best of both designs, this work proposes Video-FocalNet, an effective and efficient architecture for video recognition that models both local and global contexts. Video-FocalNet is based on a spatio-temporal focal modulation architecture that reverses the interaction and aggregation steps of self-attention for better efficiency. Further, the aggregation step and the interaction step are both implemented using efficient convolution and element-wise multiplication operations that are computationally less expensive than their self-attention counterparts on video representations. We extensively explore the design space of focal modulation-based spatio-temporal context modeling and demonstrate our parallel spatial and temporal encoding design to be the optimal choice. Video-FocalNets perform favorably well against the state-of-the-art transformer-based models for video recognition on three large-scale datasets (Kinetics-400, Kinetics-600, and SS-v2) at a lower computational cost. Our code/models are publicly released.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey_144,

title = {Efficiently Robustify Pre-Trained Models},

author = {Nishant Jain and Harkirat Behl and Yogesh Singh Rawat and Vibhav Vineet},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/ICCV23_Robust_Learning.pdf},

year  = {2023},

date = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {A recent trend in deep learning algorithms has been towards training large scale models, having high parameter count and trained on big dataset. However, robustness of such large scale models towards real-world settings is still a less-explored topic. In this work, we first benchmark the performance of these models under different perturbations and datasets thereby representing real-world shifts, and highlight their degrading performance under these shifts. We then discuss on how complete model fine-tuning based existing robustification schemes might not be a scalable option given very large scale networks and can also lead them to forget some of the desired characteristics. Finally, we propose a simple and cost-effective method to solve this problem, inspired by knowledge transfer literature. It involves robustifying smaller models, at a lower computation cost, and then use them as teachers to tune a fraction of these large scale networks, reducing the overall computational overhead. We evaluate our proposed method under various vision perturbations including ImageNet-C,R,S,A datasets and also for transfer learning, zero-shot evaluation setups on different datasets. Benchmark results show that our method is able to induce robustness to these large scale models efficiently, requiring significantly lower time and also preserves the transfer learning, zero-shot properties of the original model which none of the existing methods are able to achieve.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Zhou2023b,

title = {BT^2 : Backward-compatible Training with Basis Transformation},

author = {Yifei Zhou and Zilu Li and Abhinav Shrivasta and Hengshuang Zhao and Antonio Torralba and Taipeng Tian and Ser-Nam Lim},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2211.03989v3.pdf 

https://arxiv.org/abs/2211.03989v3},

doi = {https://doi.org/10.48550/arXiv.2211.03989},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Modern retrieval system often requires recomputing the representation of every piece of data in the gallery when updating to a better representation model. This process is known as backfilling and can be especially costly in the real world where the gallery often contains billions of samples. Recently, researchers have proposed the idea of Backward Compatible Training (BCT) where the new representation model can be trained with an auxiliary loss to make it backward compatible with the old representation. In this way, the new representation can be directly compared with the old representation, in principle avoiding the need for any backfilling. However, followup work shows that there is an inherent tradeoff where a backward compatible representation model cannot simultaneously maintain the performance of the new model itself. This paper reports our ``not-so-surprising'' finding that adding extra dimensions to the representation can help here. However, we also found that naively increasing the dimension of the representation did not work. To deal with this, we propose Backward-compatible Training with a novel Basis Transformation (BT2). A basis transformation (BT) is basically a learnable set of parameters that applies an orthonormal transformation. Such a transformation possesses an important property whereby the original information contained in its input is retained in its output. We show in this paper how a BT can be utilized to add only the necessary amount of additional dimensions. We empirically verify the advantage of BT2 over other state-of-the-art methods in a wide range of settings. We then further extend BT2 to other challenging yet more practical settings, including significant change in model architecture (CNN to Transformers), modality change, and even a series of updates in the model architecture mimicking the evolution of deep learning models.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Chen2023bb,

title = {Open-vocabulary Panoptic Segmentation with Embedding Modulation},

author = {Xi Chen and Shuang Li and Ser-Nam Lim and Antonio Torralba and Hengshuang Zhao},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2303.11324.pdf 

https://arxiv.org/abs/2303.11324 

https://opsnet-page.github.io/},

doi = {https://doi.org/10.48550/arXiv.2303.11324},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {Open-vocabulary image segmentation is attracting increasing attention due to its critical applications in the real world. Traditional closed-vocabulary segmentation methods are not able to characterize novel objects, whereas several recent open-vocabulary attempts obtain unsatisfactory results, i.e., notable performance reduction on the closed vocabulary and massive demand for extra data. To this end, we propose OPSNet, an omnipotent and data-efficient framework for Open-vocabulary Panoptic Segmentation. Specifically, the exquisitely designed Embedding Modulation module, together with several meticulous components, enables adequate embedding enhancement and information exchange between the segmentation model and the visual-linguistic well-aligned CLIP encoder, resulting in superior segmentation performance under both open- and closed-vocabulary settings with much fewer need of additional data. Extensive experimental evaluations are conducted across multiple datasets (e.g., COCO, ADE20K, Cityscapes, and PascalContext) under various circumstances, where the proposed OPSNet achieves state-of-the-art results, which demonstrates the effectiveness and generality of the proposed approach. The code and trained models will be made publicly available.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{Hammoud2023b,

title = {Towards a True Evaluation of Rapid Adaptation in Online Continual Learning},

author = {Hasan Abed Al Kader Hammoud and Ameya Prabhu and Ser-Nam Lim and Philip Torr and Adel Bibi and Bernard Ghanem},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/2305.09275.pdf 

https://arxiv.org/abs/2305.09275 

https://github.com/drimpossible/EvalOCL},

doi = {https://doi.org/10.48550/arXiv.2305.09275},

year  = {2023},

date = {2023-10-02},

urldate = {2023-10-02},

publisher = {IEEE/CVF International Conference on Computer Vision},

abstract = {We revisit the common practice of evaluating adaptation of Online Continual Learning (OCL) algorithms through the metric of online accuracy, which measures the accuracy of the model on the immediate next few samples. However, we show that this metric is unreliable, as even vacuous blind classifiers, which do not use input images for prediction, can achieve unrealistically high online accuracy by exploiting spurious label correlations in the data stream. Our study reveals that existing OCL algorithms can also achieve high online accuracy, but perform poorly in retaining useful information, suggesting that they unintentionally learn spurious label correlations. To address this issue, we propose a novel metric for measuring adaptation based on the accuracy on the near-future samples, where spurious correlations are removed. We benchmark existing OCL approaches using our proposed metric on large-scale datasets under various computational budgets and find that better generalization can be achieved by retaining and reusing past seen information. We believe that our proposed metric can aid in the development of truly adaptive OCL methods. We provide code to reproduce our results at https://github.com/drimpossible/EvalOCL.},

keywords = {ICCV},

pubstate = {published},

tppubtype = {conference}

}

@conference{ZaeemzadehICCV2021,

title = {Face Image Retrieval with Attribute Manipulation},

author = {Alireza Zaeemzadeh and Shabnam Ghadar and Baldo Faieta and Zhe Lin and Nazanin Rahnavard and Mubarak Shah and Ratheesh Kalarot},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/06328.pdf 

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/06328-supp.pdf},

year  = {2021},

date = {2021-10-11},

urldate = {2021-10-11},

booktitle = {International Conference on Computer Vision},

abstract = {Current face image retrieval solutions are limited, since they treat different facial attributes the same and cannot incorporate 

user’s preference for a subset of attributes in their search criteria. This paper introduces a new face image retrieval framework, where the input face query is augmented by both an adjustment vector that specifies the desired modifications 

to the facial attributes, and a preference vector that assigns different levels of importance to different attributes. For example, a user can ask for retrieving images similar to a query image, but with a different hair color, and no preference for absence/presence of eyeglasses in the results. To achieve this, we propose to disentangle the semantics, corresponding to various attributes, by learning a set of sparse and orthogonal basis vectors in the latent space of StyleGAN. Such basis vectors are then employed to decompose the dissimilarity between face images in terms of dissimilarity between their attributes, assign preference to the attributes, and adjust the attributes in the query. Enforcing sparsity on the basis vectors helps us to disentangle the latent space and adjust each attribute independently from other attributes, while enforcing orthogonality facilitates preference assignment and the dissimilarity decomposition. The effectiveness of our approach is illustrated by achieving state-of-the-art results for the face image retrieval task.},

keywords = {ICCV, Style GAN, Visual Search},

pubstate = {published},

tppubtype = {conference}

}

@conference{RegmiICCV2021,

title = {Video Geo-Localization Employing Geo-Temporal Feature Learning and GPS Trajectory Smoothing},

author = {Krishna Regmi and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/video_geolocalization_ICCV2021.pdf 

https://github.com/kregmi/VTE},

year  = {2021},

date = {2021-10-11},

urldate = {2021-10-11},

booktitle = {International Conference on Computer Vision},

abstract = {In this paper, we address the problem of video geolocalization by proposing a Geo-Temporal Feature Learning (GTFL) Network to simultaneously learn the discriminative features for the query video frames and the gallery images for estimating the geo-spatial trajectory of a query video. Based on a transformer encoder architecture, our 

GTFL model encodes query and gallery data separately, via two dedicated branches. The proposed GPS Loss and Clip Triplet Loss exploit the geographical and temporal proximity between the frames and the clips to jointly learn the query and the gallery features. We also propose a deep learning approach to trajectory smoothing by predicting the outliers in the estimated GPS positions and learning the offsets to smooth the trajectory. We build a large dataset from four different regions of USA; New York, San Francisco, Berkeley and Bay Area using BDD driving videos as query, and by collecting corresponding Google StreetView (GSV) Images for gallery. Extensive 

evaluations of proposed method on this new dataset are provided. Code and dataset details is publicly available at 

https://github.com/kregmi/VTE.},

keywords = {Geo-Localization, ICCV, Transformers, Video Geo-localization},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey_116,

title = {3D Human Pose Estimation with Spatial and Temporal Transformers},

author = {Ce Zheng and Sijie Zhu and Matias Mendieta and Taojiannan Yang and Chen Chen and Zhengming Ding},

url = {https://arxiv.org/pdf/2103.10455.pdf},

year  = {2021},

date = {2021-10-11},

urldate = {2021-10-11},

booktitle = {International Conference on Computer Vision},

keywords = {Action Recognition, Human Pose Estimation, ICCV, Pose},

pubstate = {published},

tppubtype = {conference}

}

@conference{BhuniaICCV2021,

title = {Handwriting Transformers},

author = {Ankan Kumar Bhunia and Salman Khan and Hisham Cholakkal and Rao Muhammad Anwer and Fahad Shahbaz Khan and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Handwriting_Generation_ICCV21.pdf 

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Handwriting_Generation_ICCV21_supp.pdf},

year  = {2021},

date = {2021-10-11},

urldate = {2021-10-11},

booktitle = {International Conference on Computer Vision},

abstract = {We propose a novel transformer-based styled handwritten text image generation approach, HWT, that strives to learn both style-content entanglement as well as global and local writing style patterns. The proposed HWT captures the long and short range relationships within the style examples through a self-attention mechanism, thereby encoding both global and local style patterns. Further, the proposed transformer-based HWT comprises an encoder-decoder attention that enables style-content entanglement by gathering the style representation of each query character. To the best of our knowledge, we are the first to introduce a transformer-based generative network for styled handwritten text generation. 

Our proposed HWT generates realistic styled handwritten text images and significantly outperforms the state-of-the-art demonstrated through extensive qualitative, quantitative and human-based evaluations. The proposed HWT can handle arbitrary length of text and any desired writing style in a few-shot setting. Further, our HWT generalizes well to the challenging scenario where both words and writing style are unseen during training, generating realistic styled handwritten text images.},

keywords = {ICCV, Transformers},

pubstate = {published},

tppubtype = {conference}

}

@conference{NarayanICCV2021,

title = {Discriminative Region-based Multi-Label Zero-Shot Learning},

author = {Sanath Narayan and Akshita Gupta and Salman Khan and Fahad Shahbaz Khan and Ling Shao and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/02617.pdf 

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/02617-supp.pdf},

year  = {2021},

date = {2021-10-11},

urldate = {2021-10-11},

booktitle = {International Conference on Computer Vision},

abstract = {Multi-label zero-shot learning (ZSL) is a more realistic counter-part of standard single-label ZSL since several objects can co-exist in a natural image. However, the occurrence of multiple objects complicates the reasoning and re-quires region-specific processing of visual features to pre-serve their contextual cues. We note that the best existing multi-label ZSL method takes a shared approach towards attending to region features with a common set of attention maps for all the classes. Such shared maps lead to diffused attention, which does not discriminatively focus on relevant locations when the number of classes are large. Moreover, mapping spatially-pooled visual features to the class semantics leads to inter-class feature entanglement, thus hampering the classification. Here, we propose an alternate approach towards region-based discriminability-preserving multi-label zero-shot classification. Our approach maintains the spatial resolution to preserve region-level characteristics and utilizes a bi-level attention module (BiAM) to enrich the features by incorporating both region and scene context information. The enriched region-level features are then mapped to the class semantics and only their class predictions are spatially pooled to obtain image-level predictions, thereby keeping the multi-class features disentangled. Our approach sets a new state of the art on two large-scale multi-label zero-shot benchmarks: NUS-WIDE and Open Images. On NUS-WIDE, our approach achieves an absolute gain of 6.9% mAP for ZSL, compared to the best published results. Source code is available at <a href="https://github.com/akshitac8/BiAM" target="_blank">https://github.com/akshitac8/BiAM</a>.},

keywords = {ICCV, Transformers, Zero-Shot Learning},

pubstate = {published},

tppubtype = {conference}

}

@conference{ChenICCV2021,

title = {Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos},

author = {Brian Chen and Andrew Rouditchenko and Kevin Duarte and Hilde Kuehne and Samuel Thomas and Angie Boggust and Rameswar Panda and Brian Kingsbury and Rogerio Feris and David Harwatch and James Glass and Michael Picheny and Shih-Fu Chang},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/02965.pdf 

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/02965-supp.pdf},

year  = {2021},

date = {2021-10-11},

urldate = {2021-10-11},

booktitle = {International Conference on Computer Vision},

abstract = {Multimodal self-supervised learning is getting more and more attention as it allows not only to train large networks without human supervision but also to search and retrieve data across various modalities. In this context, this paper proposes a framework that, starting from a pre- trained backbone, learns a common multimodal embedding space that, in addition to sharing representations across different modalities, enforces a grouping of semantically similar instances. 

To this end, we extend the concept of instance-level contrastive learning with a multimodal lustering step in the training pipeline to capture semantic similarities across modalities. The resulting embedding space enables retrieval of samples across all modalities, even from unseen datasets and different domains. To evaluate our approach, we train our model on the HowTo100M dataset and evaluate its zero-shot retrieval capabilities in two challenging domains, 

namely text-to-video retrieval, and temporal action localization, showing state-of-the-art results on four different datasets.},

keywords = {ICCV, Multi-Modal Learning},

pubstate = {published},

tppubtype = {conference}

}

@conference{ZaeemzadehICCV2021b,

title = {Face Image Retrieval with Attribute Manipulation},

author = {Alireza Zaeemzadeh and Shabnam Ghadar and Baldo Faieta and Zhe Lin and Nazanin Rahnavard and Mubarak Shah and Ratheesh Kalarot},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/06328.pdf 

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/06328-supp.pdf},

year  = {2021},

date = {2021-10-11},

urldate = {2021-10-11},

booktitle = {International Conference on Computer Vision},

abstract = {Current face image retrieval solutions are limited, since they treat different facial attributes the same and cannot incorporate 

user’s preference for a subset of attributes in their search criteria. This paper introduces a new face image retrieval framework, where the input face query is augmented by both an adjustment vector that specifies the desired modifications 

to the facial attributes, and a preference vector that assigns different levels of importance to different attributes. For example, a user can ask for retrieving images similar to a query image, but with a different hair color, and no preference for absence/presence of eyeglasses in the results. To achieve this, we propose to disentangle the semantics, corresponding to various attributes, by learning a set of sparse and orthogonal basis vectors in the latent space of StyleGAN. Such basis vectors are then employed to decompose the dissimilarity between face images in terms of dissimilarity between their attributes, assign preference to the attributes, and adjust the attributes in the query. Enforcing sparsity on the basis vectors helps us to disentangle the latent space and adjust each attribute independently from other attributes, while enforcing orthogonality facilitates preference assignment and the dissimilarity decomposition. The effectiveness of our approach is illustrated by achieving state-of-the-art results for the face image retrieval task.},

keywords = {ICCV, Style GAN, Visual Search},

pubstate = {published},

tppubtype = {conference}

}

@conference{RegmiICCV2021b,

title = {Video Geo-Localization Employing Geo-Temporal Feature Learning and GPS Trajectory Smoothing},

author = {Krishna Regmi and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/video_geolocalization_ICCV2021.pdf 

https://github.com/kregmi/VTE},

year  = {2021},

date = {2021-10-11},

urldate = {2021-10-11},

booktitle = {International Conference on Computer Vision},

abstract = {In this paper, we address the problem of video geolocalization by proposing a Geo-Temporal Feature Learning (GTFL) Network to simultaneously learn the discriminative features for the query video frames and the gallery images for estimating the geo-spatial trajectory of a query video. Based on a transformer encoder architecture, our 

GTFL model encodes query and gallery data separately, via two dedicated branches. The proposed GPS Loss and Clip Triplet Loss exploit the geographical and temporal proximity between the frames and the clips to jointly learn the query and the gallery features. We also propose a deep learning approach to trajectory smoothing by predicting the outliers in the estimated GPS positions and learning the offsets to smooth the trajectory. We build a large dataset from four different regions of USA; New York, San Francisco, Berkeley and Bay Area using BDD driving videos as query, and by collecting corresponding Google StreetView (GSV) Images for gallery. Extensive 

evaluations of proposed method on this new dataset are provided. Code and dataset details is publicly available at 

https://github.com/kregmi/VTE.},

keywords = {Geo-Localization, ICCV, Transformers, Video Geo-localization},

pubstate = {published},

tppubtype = {conference}

}

@conference{BhuniaICCV2021b,

title = {Handwriting Transformers},

author = {Ankan Kumar Bhunia and Salman Khan and Hisham Cholakkal and Rao Muhammad Anwer and Fahad Shahbaz Khan and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Handwriting_Generation_ICCV21.pdf 

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Handwriting_Generation_ICCV21_supp.pdf},

year  = {2021},

date = {2021-10-11},

urldate = {2021-10-11},

booktitle = {International Conference on Computer Vision},

abstract = {We propose a novel transformer-based styled handwritten text image generation approach, HWT, that strives to learn both style-content entanglement as well as global and local writing style patterns. The proposed HWT captures the long and short range relationships within the style examples through a self-attention mechanism, thereby encoding both global and local style patterns. Further, the proposed transformer-based HWT comprises an encoder-decoder attention that enables style-content entanglement by gathering the style representation of each query character. To the best of our knowledge, we are the first to introduce a transformer-based generative network for styled handwritten text generation. 

Our proposed HWT generates realistic styled handwritten text images and significantly outperforms the state-of-the-art demonstrated through extensive qualitative, quantitative and human-based evaluations. The proposed HWT can handle arbitrary length of text and any desired writing style in a few-shot setting. Further, our HWT generalizes well to the challenging scenario where both words and writing style are unseen during training, generating realistic styled handwritten text images.},

keywords = {ICCV, Transformers},

pubstate = {published},

tppubtype = {conference}

}

@conference{NarayanICCV2021b,

title = {Discriminative Region-based Multi-Label Zero-Shot Learning},

author = {Sanath Narayan and Akshita Gupta and Salman Khan and Fahad Shahbaz Khan and Ling Shao and Mubarak Shah},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/02617.pdf 

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/02617-supp.pdf},

year  = {2021},

date = {2021-10-11},

urldate = {2021-10-11},

booktitle = {International Conference on Computer Vision},

abstract = {Multi-label zero-shot learning (ZSL) is a more realistic counter-part of standard single-label ZSL since several objects can co-exist in a natural image. However, the occurrence of multiple objects complicates the reasoning and re-quires region-specific processing of visual features to pre-serve their contextual cues. We note that the best existing multi-label ZSL method takes a shared approach towards attending to region features with a common set of attention maps for all the classes. Such shared maps lead to diffused attention, which does not discriminatively focus on relevant locations when the number of classes are large. Moreover, mapping spatially-pooled visual features to the class semantics leads to inter-class feature entanglement, thus hampering the classification. Here, we propose an alternate approach towards region-based discriminability-preserving multi-label zero-shot classification. Our approach maintains the spatial resolution to preserve region-level characteristics and utilizes a bi-level attention module (BiAM) to enrich the features by incorporating both region and scene context information. The enriched region-level features are then mapped to the class semantics and only their class predictions are spatially pooled to obtain image-level predictions, thereby keeping the multi-class features disentangled. Our approach sets a new state of the art on two large-scale multi-label zero-shot benchmarks: NUS-WIDE and Open Images. On NUS-WIDE, our approach achieves an absolute gain of 6.9% mAP for ZSL, compared to the best published results. Source code is available at <a href="https://github.com/akshitac8/BiAM" target="_blank">https://github.com/akshitac8/BiAM</a>.},

keywords = {ICCV, Transformers, Zero-Shot Learning},

pubstate = {published},

tppubtype = {conference}

}

@conference{ChenICCV2021b,

title = {Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos},

author = {Brian Chen and Andrew Rouditchenko and Kevin Duarte and Hilde Kuehne and Samuel Thomas and Angie Boggust and Rameswar Panda and Brian Kingsbury and Rogerio Feris and David Harwatch and James Glass and Michael Picheny and Shih-Fu Chang},

url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/02965.pdf 

https://www.crcv.ucf.edu/wp-content/uploads/2018/11/02965-supp.pdf},

year  = {2021},

date = {2021-10-11},

urldate = {2021-10-11},

booktitle = {International Conference on Computer Vision},

abstract = {Multimodal self-supervised learning is getting more and more attention as it allows not only to train large networks without human supervision but also to search and retrieve data across various modalities. In this context, this paper proposes a framework that, starting from a pre- trained backbone, learns a common multimodal embedding space that, in addition to sharing representations across different modalities, enforces a grouping of semantically similar instances. 

To this end, we extend the concept of instance-level contrastive learning with a multimodal lustering step in the training pipeline to capture semantic similarities across modalities. The resulting embedding space enables retrieval of samples across all modalities, even from unseen datasets and different domains. To evaluate our approach, we train our model on the HowTo100M dataset and evaluate its zero-shot retrieval capabilities in two challenging domains, 

namely text-to-video retrieval, and temporal action localization, showing state-of-the-art results on four different datasets.},

keywords = {ICCV, Multi-Modal Learning},

pubstate = {published},

tppubtype = {conference}

}