Conference
Nineteenth European Conference on Computer Vision
Malmö, Sweden
The European Conference on Computer Vision (ECCV) is one of the world’s premier conferences for computer vision and artificial intelligence research. Held biennially, ECCV brings together researchers, practitioners, and industry leaders to present and discuss the latest advances in computer vision, machine learning, image understanding, robotics, multimodal AI, and related fields.
ECCV is widely recognized as one of the top publication venues in computer vision and serves as a leading forum for groundbreaking research in areas such as visual recognition, vision-language models, generative AI, medical imaging, autonomous systems, remote sensing, and AI safety. The conference attracts thousands of participants from academia, industry, and government laboratories around the world.
The h5-index is the h-index for articles published in the last 5 complete years. According to Google Scholar Metrics, ECCV is ranked 2nd in the h5-index rankings for Computer Vision & Pattern Recognition venues.
This year’s conference will take place in Malmö, Sweden, from September 8-13, 2026. The Institute of Artificial Intelligence (IAI) is proud to celebrate the success of its researchers and collaborators, who have fifteen accepted papers at ECCV 2026 spanning topics including vision-language models, multimodal AI, medical AI, AI safety, geo-localization, model evaluation, and AI fairness.
You can access the IAI Publications Page for enhanced search capabilities and view the accepted papers below.
Accepted Papers
Xue, Haoyu Xie; Shengkai Xu; Cheng Guo; Muhammad Usama Saleem; Wenhan Wu; Chen Chen; Ahmed Helmy; Pu Wang; Hongfei
Monocular Models are Strong Learners for Multi-View Human Mesh Recovery Conference
European Conference on Computer Vision -- ECCV 2026, 2026.
@conference{nokey,
title = {Monocular Models are Strong Learners for Multi-View Human Mesh Recovery},
author = {Haoyu Xie; Shengkai Xu; Cheng Guo; Muhammad Usama Saleem; Wenhan Wu; Chen Chen; Ahmed Helmy; Pu Wang; Hongfei Xue},
url = {https://arxiv.org/abs/2603.20391},
year = {2026},
date = {2026-09-08},
publisher = {European Conference on Computer Vision -- ECCV 2026},
abstract = {Multi-view human mesh recovery (HMR) is broadly deployed in diverse domains where high accuracy and strong generalization are essential. Existing approaches can be broadly grouped into geometry-based and learning-based methods. However, geometry-based methods (e.g., triangulation) rely on cumbersome camera calibration, while learning-based approaches often generalize poorly to unseen camera configurations due to the lack of multi-view training data, limiting their performance in real-world scenarios. To enable calibration-free reconstruction that generalizes to arbitrary camera setups, we propose a training-free framework that leverages pretrained single-view HMR models as strong priors, eliminating the need for multi-view training data. Our method first constructs a robust and consistent multi-view initialization from single-view predictions, and then refines it via test-time optimization guided by multi-view consistency and anatomical constraints. Extensive experiments demonstrate state-of-the-art performance on standard benchmarks, surpassing multi-view models trained with explicit multi-view supervision.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Ding, Tianxingjian; Zou, Yuanhao; Chen, Chen; Shah, Mubarak; Tian, Yu
CLARITY: Medical World Model for Guiding Treatment Decisions by Modeling Context-Aware Disease Trajectories in Latent Space Conference
European Conference on Computer Vision -- ECCV 2026, 2026.
@conference{Tian2026,
title = {CLARITY: Medical World Model for Guiding Treatment Decisions by Modeling Context-Aware Disease Trajectories in Latent Space},
author = {Tianxingjian Ding and Yuanhao Zou and Chen Chen and Mubarak Shah and Yu Tian},
url = {https://arxiv.org/abs/2512.08029
https://ai.ucf.edu/wp-content/uploads/2026/09/CLARITY-1.pdf
https://youtu.be/4Gvaj6ppPzY?si=YYxdnLW-V4JhfGkx},
year = {2026},
date = {2026-09-08},
urldate = {2026-09-08},
publisher = {European Conference on Computer Vision -- ECCV 2026},
abstract = {Clinical decision-making in oncology requires predicting dynamic disease evolution, a task current static AI predictors cannot perform. While world models (WMs) offer a paradigm for generative prediction, existing medical applications remain limited. Existing methods often rely on stochastic diffusion models, focusing on visual reconstruction rather than causal, physiological transitions. Furthermore, in medical domain, models like MeWM typically ignore patient-specific temporal and clinical contexts and lack a feedback mechanism to link predictions to treatment decisions. To address these gaps, we introduce CLARITY, a medical world model that forecasts disease evolution directly within a structured latent space. It explicitly integrates time intervals (temporal context) and patient-specific data (clinical context) to model treatment-conditioned progression as a smooth, interpretable trajectory, and thus generate physiologically faithful, individualized treatment plans. Finally, CLARITY introduces a novel prediction-to-decision framework, translating latent rollouts into transparent, actionable recommendations. CLARITY demonstrates state-of-the-art performance in treatment planning. On the MU-Glioma-Post dataset, our approach outperforms recent MeWM by 12%, and significantly surpasses all other medical-specific large language models.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Hu, Jianing Deng; Yuanzhe LI; Jialu Wang; Song Wang; Tianlong Chen; Huanrui Yang; Jingtong
SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers Conference
European Conference on Computer Vision -- ECCV 2026, 2026.
@conference{nokey,
title = {SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers},
author = {Jianing Deng; Yuanzhe LI; Jialu Wang; Song Wang; Tianlong Chen; Huanrui Yang; Jingtong Hu},
url = {https://arxiv.org/abs/2607.03612},
year = {2026},
date = {2026-09-07},
publisher = {European Conference on Computer Vision -- ECCV 2026},
abstract = {Feed-forward 3D reconstruction (F3R) transformers have recently achieved remarkable success. However, scaling them to long image sequences remains challenging, as the quadratic complexity of cross-view global attention quickly becomes the dominant computational bottleneck. While recent efforts attempt to improve efficiency through compressed or sparse attention, they fail to fully exploit the inherent sparsity and dynamic behavior of global attention. In this work, we present a comprehensive analysis of global attention across multiple F3R transformers and reveal that attention patterns are highly heterogeneous, dynamic, and extremely sparse across layers and attention heads. Motivated by these findings, we propose SAF3R, a training-free dynamic sparse attention framework tailored to F3R transformers. SAF3R integrates tailored sparse attention mechanisms with offline head profiling and an efficient online adaptation strategy to match input-dependent attention behaviors. Extensive experiments demonstrate that SAF3R achieves high sparsity ratios while preserving camera pose estimation and 3D reconstruction quality, translating into substantial end-to-end speedup on F3R transformers compared to existing methods. },
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Modi, Rajat; Noel, S.; Liang, Xin; Rawat, Yogesh Singh
Forget, Anticipate and Adapt: Test Time Training for Long Videos Conference
European Conference on Computer Vision -- ECCV 2026, 2026.
@conference{nokey,
title = {Forget, Anticipate and Adapt: Test Time Training for Long Videos},
author = {Rajat Modi and S. Noel and Xin Liang and Yogesh Singh Rawat
},
url = {https://arxiv.org/abs/2606.26515},
year = {2026},
date = {2026-09-07},
urldate = {2026-09-07},
publisher = {European Conference on Computer Vision -- ECCV 2026},
abstract = {Test Time Training (TTT) is a mechanism in which a model adapts to an incoming test-sample by performing some self-supervised (SSL) task and updating its weights even during inference. This procedure does not require labels at test-time. This paper focuses on TTT for long-videos. A major concern with existing approaches is: 1) they perform TTT updates using a sliding window containing frames in the past, whose compute increases linearly with the size of window. This becomes computationally intractable when the videos are hours long. 2) TTT is performed even when temporally close frames look similar, thereby consuming a lot of compute.
We present the Frame Forgetting Network (FFN) that: 1) operates on only three frames within the sliding window, namely the frame that exits, the current frame and the frame after that. The model still manages to retain temporal context and work for hours long-videos; 2) mathematically define a surprise metric: how much new information the incoming frame contains with respect to the past seen frame. This facilitates determining how to modify the effective window size during TTT and constitutes the core mechanism of an adaptive windowing algorithm. Additionally, we curate a dataset EpicTours containing up to 3 hour long videos of walking city-tours, whereas earlier datasets on this problem were only 5 min long. We demonstrate FFNs empirical effectiveness on dense-segmentation, video classification tasks, generalization to depth-estimation, and multi-hour long videos.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
We present the Frame Forgetting Network (FFN) that: 1) operates on only three frames within the sliding window, namely the frame that exits, the current frame and the frame after that. The model still manages to retain temporal context and work for hours long-videos; 2) mathematically define a surprise metric: how much new information the incoming frame contains with respect to the past seen frame. This facilitates determining how to modify the effective window size during TTT and constitutes the core mechanism of an adaptive windowing algorithm. Additionally, we curate a dataset EpicTours containing up to 3 hour long videos of walking city-tours, whereas earlier datasets on this problem were only 5 min long. We demonstrate FFNs empirical effectiveness on dense-segmentation, video classification tasks, generalization to depth-estimation, and multi-hour long videos.
Priyank Pathak; M. Karuppasamy, A. Baranwal; Shruti Vyas; Yogesh Singh Rawat
Robust Onion: Peeling Open Vocab Object Detectors Under Noise Conference
European Conference on Computer Vision -- ECCV 2026, 2026.
@conference{nokey,
title = {Robust Onion: Peeling Open Vocab Object Detectors Under Noise},
author = {Priyank Pathak; M. Karuppasamy, A. Baranwal; Shruti Vyas; Yogesh Singh Rawat
},
url = {https://arxiv.org/abs/2606.26734},
year = {2026},
date = {2026-09-07},
urldate = {2026-09-07},
publisher = {European Conference on Computer Vision -- ECCV 2026},
abstract = {The impact of real-world noise on Open Vocabulary Object Detectors (OV-ODs) remains poorly understood due to their architectural complexity. We present our comprehensive analysis Robust Onion, an empirical study that uses controlled synthetic visual degradations to peel OV-ODs layer-by-layer, revealing how, why, and where robustness degrades, systematically analyzing feature collapse. Our findings reveal that models with similar vision backbones exhibit comparable robustness, driven by similar feature collapse at similar layers, while factors such as pretraining strategy, architectural nuances, and caption supervision contribute little. Robustness is primarily governed by the image domain rather than annotations, explaining the similar robustness impact on COCO and LVIS, and why datasets like ODinW-13 can give an impression of inflated robustness due to large, isolated objects. Finally, we validate our insights by improving robustness on real-world BDD100K, WiderFace, and VisDRONE via our lightweight plug-and-play NN & TK0 approach, using 96x fewer trainable parameters than end-to-end training. We also explain the prior works' robustness observations.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Grover, Shresth; Pathak, Priyank; Kumar, Akash; Rawat, Yogesh Singh
CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates Conference
European Conference on Computer Vision -- ECCV 2026, 2026.
@conference{nokey,
title = {CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates},
author = {Shresth Grover and Priyank Pathak and Akash Kumar and Yogesh Singh Rawat
},
url = {https://arxiv.org/abs/2512.10342
https://shroglck.github.io/cos_plan/},
year = {2026},
date = {2026-09-07},
urldate = {2026-09-07},
publisher = {European Conference on Computer Vision -- ECCV 2026},
abstract = {Vision Language Models (VLMs) have shown promising planning capabilities, yet their success remains confined to the text domain, leaving visual decision-making relatively underexplored. Addressing this gap, we introduce Corrective Sequence Planning (CoSPlan) benchmark, where VLMs must plan a sequence of visual actions from an initial scene to a target scene. CoSPlan evaluates models on their ability to imagine and execute a coherent set of visual steps required to reach the goal (Step Completion). To prevent any shortcuts that simply describe the final scene, we introduce an erroneous action in decision-making, which must be detected (Error Detection) and corrected to reach the goal, enabling a deeper understanding of the task. CoSPlan spans across 4 tasks: maze navigation, block re-arrangement, image reconstruction, and object re-organization. Despite using advanced reasoning strategies such as Chain-of-Thought and Scene Graphs, VLMs struggle on CoSPlan, while still showing promising performance in the text domain. Addressing this, we propose Scene Graph Incremental updates (SGI), a novel training-free method to transform images into `textual' scene graphs, enabling step-by-step reasoning through iterative scene graph refinement. SGI yields an average of ~4.4% improvement on CoSPlan w/ generalization on PlanBench and VQA. Link for solving puzzles on the project page.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Abdullah, Raiyaan; Azad, Shehreen; Rawat, Yogesh Singh
Learning to Deny: Action Denial in Multimodal Large Language Models Conference
European Conference on Computer Vision -- ECCV 2026, 2026.
@conference{nokey,
title = {Learning to Deny: Action Denial in Multimodal Large Language Models},
author = {Raiyaan Abdullah and Shehreen Azad and Yogesh Singh Rawat
},
url = {https://arxiv.org/abs/2606.31187},
year = {2026},
date = {2026-09-07},
urldate = {2026-09-07},
publisher = {European Conference on Computer Vision -- ECCV 2026},
abstract = {Multimodal large language models (MLLMs) have rapidly advanced video understanding, achieving strong zero-shot and few-shot recognition across standard benchmarks. Yet their ability to deny an action by recognizing when an activity is not happening despite strong contextual cues remains largely unexplored. We introduce UCF101-AD, a large-scale benchmark consisting of paired Action-Presence and Action-Denial clips, designed to evaluate this capacity for denial. Each negative video in UCF101-AD preserves the same contextual and motion cues, including persons, objects, and locations, as its positive counterpart, but the defining action itself is explicitly absent. Evaluating 20 state-of-the-art MLLMs reveals a consistent failure: models that exceed 85% accuracy on the positive action classes collapse below 50% on their action-denial counterparts, indicating a strong inclination to affirm plausible actions rather than verify that they truly occur. This exposes a critical blind spot in modern video understanding: the inability to reason causally about whether a motion actually happens. To probe this issue, we explore a causal graph formulation, CausalAct, which expresses scene structure through natural-language prompts linking context, interaction, and motion. Incorporating such causal cues substantially reduces false positives, demonstrating that denial is a learnable reasoning skill. UCF101-AD provides a new lens for diagnosing and improving causal reasoning in multimodal models. },
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Campos, Ron; Maity, Subhajit; Li, Xin; Das, Srijan; Dutta, Aritra
DnA: Denoising Attention for Visual Tasks Conference
European Conference on Computer Vision -- ECCV 2026, 2026.
@conference{nokey,
title = {DnA: Denoising Attention for Visual Tasks},
author = {Ron Campos and Subhajit Maity and Xin Li and Srijan Das and Aritra Dutta},
url = {https://rjccv.github.io/DnA/},
year = {2026},
date = {2026-09-07},
publisher = {European Conference on Computer Vision -- ECCV 2026},
abstract = {The softmax activation in multihead attention (MHA) is the de facto standard for attention-based models in visual perception tasks. However, standard softmax can produce noisy attention patterns that dilute relevant features and degrade its performance. In this paper, we propose Denoising Attention or DnA, in which, first, a positive query identifies which image features belong to the correct class, and a negative query identifies closely associated but irrelevant image features. DnA then projects these interactions into two distinct subspaces with larger principal angles, promoting subspace separation and improved discriminability. Using a ViT-B backbone, our proposed DnA achieves a 0.8% absolute gain on ImageNet-1K compared to the baseline. We further show improvements across multiple visual understanding tasks, including video understanding with video transformers (1.8%) and video LLMs (0.5%). Our extensive empirical analyses justify the design choices involving two interacting subspaces and the denoising effect of DnA.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Fioresi, Joseph; Heilbron, Fabian Caba; Nathani, Pankaj; Shah, Mubarak; Kafle, Kushal
Controlling Embedding Spaces with Text-Conditioned Transformations Conference
European Conference on Computer Vision (ECCV), Springer, 2026.
@conference{fioresi2026controlembedb,
title = {Controlling Embedding Spaces with Text-Conditioned Transformations},
author = {Joseph Fioresi and Fabian Caba Heilbron and Pankaj Nathani and Mubarak Shah and Kushal Kafle},
url = {https://arxiv.org/abs/2607.22919
https://ai.ucf.edu/wp-content/uploads/2026/09/ControlEmbed_ECCV_poster.pdf
https://youtu.be/n0Hy5GSCrtw?si=9n-OekUWO_aRF2cN},
year = {2026},
date = {2026-09-07},
urldate = {2026-09-07},
booktitle = {European Conference on Computer Vision (ECCV)},
publisher = {Springer},
abstract = {Multimodal embedding spaces in models like CLIP enable powerful capabilities such as semantic similarity retrieval and cross-modal zero-shot classification. These embeddings compress high-level semantics into a single vector, which comes at the cost of primarily expressing a dominant semantics like main object while suppressing other important attributes such as camera angle or color tone. We propose a text-conditioned transformation of visual embeddings that makes such attributes explicitly accessible. Given a natural language description of an attribute category (e.g., "color" or "art style"), a network generates an affine transformation that emphasizes the specified attribute. Conditioning on text enables it to learn many attributes simultaneously, accessing them at inference time through an intuitive interface. The network is trained to align transformed embeddings with the frozen latent space, enabling retrieval using existing large-scale embeddings without any re-encoding. When applied to a full set, the same mechanism transforms the latent space for attribute disentanglement tasks such as multi-clustering. By operating directly in latent space, our method provides a unified and efficient framework for controlling embedding spaces, demonstrating state-of-the-art performance across both attribute-based retrieval and multi-attribute organization tasks with near-zero inference cost. Project page: this https URL},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Yousaf, Adeel; Ghosh, Soumik; Beetham, James; Bedi, Amrit Singh; Shah, Mubarak
The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models Conference
European Conference on Computer Vision (ECCV), Springer, 2026.
@conference{yousaf2026sageb,
title = {The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models},
author = {Adeel Yousaf and Soumik Ghosh and James Beetham and Amrit Singh Bedi and Mubarak Shah},
url = {https://arxiv.org/abs/2607.00402
https://ai.ucf.edu/wp-content/uploads/2026/09/Illusion-of-High-Utility-in-Safety-JPG-1.jpg
https://youtu.be/BVw6WnfG2iw?si=WtAX_hPSnDRR0-1u},
year = {2026},
date = {2026-09-07},
urldate = {2026-09-07},
booktitle = {European Conference on Computer Vision (ECCV)},
publisher = {Springer},
abstract = {Safety alignment of text-to-image (T2I) diffusion models aims to suppress harmful generations while preserving utility on benign prompts. Recent methods often appear to deliver high safety with high utility, but this conclusion rests largely on coarse global utility metrics (e.g., FID, CLIPScore) that are insensitive to fine-grained semantic correctness, creating an illusion of high utility. We show that when utility is measured with structured evaluation, this illusion breaks: on TIFA (Text-to-Image Faithfulness evaluation with Question Answering), safety-aligned models suffer substantial drops in semantic fidelity, including failures in object counts, attributes, and relationships. To diagnose the source of this gap, we analyze the text-encoder prompt embedding space and uncover semantic collapse, a contraction of embedding spread coupled with distortion of inter-prompt similarity structure, which strongly correlates with structured utility loss. Guided by this insight, we propose StructureAware Geometric Regularization (SAGE), a safety alignment objective that explicitly preserves embedding spread and inter-prompt relational structure during adaptation. Our method restores structured utility (TIFA +5.0% over prior state-of-the-art) while maintaining strong safety performance and competitive coarse-grained utility scores. Our source code and trained models are available at this https URL.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Zhang, Sicheng; Naseer, Muhammad Muzammal; Xie, Binzhu; Suryanto, Naufal; Qiu, Shi; Bentahar, Jamal; Akhtar, Naveed; Shah, Mubarak
ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP Conference
European Conference on Computer Vision (ECCV), Springer, 2026.
@conference{zhang2026reasonclipb,
title = {ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP},
author = {Sicheng Zhang and Muhammad Muzammal Naseer and Binzhu Xie and Naufal Suryanto and Shi Qiu and Jamal Bentahar and Naveed Akhtar and Mubarak Shah},
url = {https://arxiv.org/abs/2606.26794},
year = {2026},
date = {2026-09-07},
urldate = {2026-01-01},
booktitle = {European Conference on Computer Vision (ECCV)},
publisher = {Springer},
abstract = {CLIP and its variants are widely adopted visual backbones in multimodal systems, but their pretraining remains dominated by descriptive image-text alignment. As downstream applications increasingly demand visually grounded commonsense inference and compositional reasoning, it remains unclear whether CLIP-style encoders can support such reasoning without architectural changes. To address this, we present ReasonCLIP-58M, a continual pretraining framework that integrates large-scale reasoning supervision into CLIP-style models through our two-stage strategy, which progressively integrates reasoning signals while preserving descriptive alignment, followed by category-structured reasoning supervision. To support this framework, we construct two complementary datasets and a benchmark: ReasonLite-42M, with open-form, visually verifiable reasoning captions; ReasonPro-16M, with category-specific reasoning supervision; and RCLIP-Bench for diagnostic evaluation of visually grounded reasoning. We train a family of ReasonCLIP that improves visually grounded commonsense and compositional reasoning while also enhancing zero-shot retrieval performance. As a drop-in visual encoder for multimodal large language models such as LLaVA-NeXT, ReasonCLIP delivers consistent gains without additional inference cost, demonstrating that structured reasoning supervision enhances the expressive capacity of CLIP-style visual representations. All datasets, models, and training code are available at this https URL.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Narnaware, Vishal; Gupta, Animesh; Zhai, Kevin; Wang, Zhenyi; Shah, Mubarak
Seeing to Ground: Visual Attention for Hallucination-Resilient MDLLMs Conference
European Conference on Computer Vision (ECCV), Springer, 2026.
@conference{narnaware2026visageb,
title = {Seeing to Ground: Visual Attention for Hallucination-Resilient MDLLMs},
author = {Vishal Narnaware and Animesh Gupta and Kevin Zhai and Zhenyi Wang and Mubarak Shah},
url = {https://arxiv.org/abs/2603.25711
https://ai.ucf.edu/wp-content/uploads/2026/09/Seeing-to-Ground-ECCV.jpg
https://youtu.be/60Acip-ylyM?si=WtRA0tTr-quzOOCO},
year = {2026},
date = {2026-09-07},
urldate = {2026-09-07},
booktitle = {European Conference on Computer Vision (ECCV)},
publisher = {Springer},
abstract = {Multimodal Diffusion Large Language Models (MDLLMs) achieve high-concurrency generation through parallel masked decoding, yet the architectures remain prone to multimodal hallucinations. This structural vulnerability stems from an algorithmic flaw: the decoder ranks candidate tokens based on textual likelihood without verifying localized visual support. We establish that this language-only ranking induces an objective mismatch, where language probability mass acts as a misspecified proxy for the intended multimodal task. Consequently, we reinterpret hallucination as a localized optimization error, a phenomenon where the decoder exploits language shortcuts to maximize a proxy score at the expense of visual grounding. To address this objective mismatch, we introduce VISAGE, a training-free decoding framework that calibrates the objective at inference time. VISAGE estimates the proxy discrepancy by quantifying the spatial entropy of cross-attention distributions. By enforcing a localization consensus across attention heads, the method penalizes spatially uniform distributions and re-ranks token commitments to favor visually grounded outcomes. We provide an analytical stability guarantee establishing that VISAGE maintains a bounded objective loss under estimation error. Evaluations across hallucination-sensitive and general-purpose benchmarks demonstrate the robustness of the framework, yielding relative gains of 8.59% on MMMU-val and 7.75% on HallusionBench.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Liu, Qingyang; Shatwell, David G.; Kulkarni, Parth Parag; Shah, Mubarak
Pixel-wise Geo-registration of Drone Images Conference
European Conference on Computer Vision (ECCV), Springer, 2026.
@conference{liu2026skyregb,
title = {Pixel-wise Geo-registration of Drone Images},
author = {Qingyang Liu and David G. Shatwell and Parth Parag Kulkarni and Mubarak Shah},
url = {https://qingyangliu.github.io/qingyang.github.io/static/Georegistration.pdf
https://ai.ucf.edu/wp-content/uploads/2026/09/Pixel-Wise-Geo-Registration-JPG.png
https://youtu.be/jgVuME3oFJ4?si=R-AkoBd3rlG_791Z},
year = {2026},
date = {2026-09-07},
urldate = {2026-09-07},
booktitle = {European Conference on Computer Vision (ECCV)},
publisher = {Springer},
abstract = {Cross-view geo-registration is the task of aligning a query image to a geodetically accurate reference (e.g., satellite image), so that each query pixel maps to a real-world GPS coordinate. Most existing work addresses the related problem of cross-view geo-localization, where the goal is typically to estimate the camera center using retrieval, classification, matching, or regression. Because these approaches do not provide dense supervision, they are poorly suited for learning and evaluating pixel-wise alignment. We introduce SkyReg, a geometry-aware geo-registration model that estimates the transformation between the query and reference images by explicitly modeling the 3D scene geometry. Applying this transformation to warp the query into the reference frame yields pixel-wise geo-localization, without relying on 2D point matches, and remains robust to occlusions and large viewpoint changes. To enable training and standardized evaluation, we release (i) SkyReg-Train, a large-scale dataset of drone–satellite images annotated with per-pixel GPS coordinates, depth maps, and camera parameters derived from LiDAR and structure-from-motion, and (ii) SkyReg-Bench, a held-out benchmark of unseen Urban and Suburban scenes with the same dense annotations. SkyReg achieves state-of-the-art performance against strong retrieval and homography baselines, demonstrating the value of geometry-aware models and dense geodetic benchmarks for cross-view geo-registration. Dataset available at https://parthpk.github.io/sk yreg-webpage.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Mollah, Sabbir; Gupta, Rohit; Sirnam, Swetha; Liu, Qingyang; Munir, Ahnaf; Shah, Mubarak
The Telephone Game: Evaluating Semantic Drift in Unified Models Conference
European Conference on Computer Vision (ECCV), Springer, 2026.
@conference{mollah2026telephonegameb,
title = {The Telephone Game: Evaluating Semantic Drift in Unified Models},
author = {Sabbir Mollah and Rohit Gupta and Swetha Sirnam and Qingyang Liu and Ahnaf Munir and Mubarak Shah},
url = {https://arxiv.org/abs/2509.04438
https://ai.ucf.edu/wp-content/uploads/2026/09/Poster__Telephone_Game.pdf
https://youtu.be/1y_Pn6xD0fw?si=Oab_zk-25L591fLO},
year = {2026},
date = {2026-09-07},
urldate = {2026-09-07},
booktitle = {European Conference on Computer Vision (ECCV)},
publisher = {Springer},
abstract = {Employing a single, unified model (UM) for both visual understanding (image-to-text: I2T) and visual generation (text-to-image: T2I) has opened a new direction in Visual Language Model (VLM) research. While UMs can also support broader unimodal tasks (e.g., text-to-text, image-to-image), we focus on the core cross-modal pair T2I and I2T. Existing evaluation benchmarks consider these capabilities in isolation: FID and GenEval for T2I, and benchmarks such as MME, MMBench for I2T. These isolated single-pass metrics do not reveal cross-consistency: whether a model that "understands" a concept can also "render" it, nor whether semantic meaning is preserved when cycling between image and text modalities. To address this, we introduce the Semantic Drift Protocol (SDP) for Unified Models, a cyclic evaluation protocol that alternates I2T and T2I over multiple generations to quantify semantic drift. We propose two metrics: (i) Mean Cumulative Drift (MCD), an embedding-based measure of overall semantic drift; and (ii) Multi-Generation GenEval (MGG), an object-level compliance score extending GenEval. To assess generalization beyond COCO dataset, which is widely used in training; we create a new benchmark Nocaps+Docci400, sampled from NoCaps and DOCCI and evaluated on seven recent models. SDP reveals substantial variation in cross-modal stability: some models like BAGEL maintain semantic meaning over many alternations, whereas others like VILA-U drift quickly despite strong single-pass scores. Our results highlight SDP as a necessary complement to standard I2T and T2I evaluations. Code is available at this https URL},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Narnaware, Vishal; Vayani, Ashmal; Gupta, Rohit; Sirnam, Swetha; Shah, Mubarak
BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Models Conference
European Conference on Computer Vision (ECCV), Springer, 2026.
@conference{narnaware2026bbqvb,
title = {BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Models},
author = {Vishal Narnaware and Ashmal Vayani and Rohit Gupta and Swetha Sirnam and Mubarak Shah},
url = {https://arxiv.org/abs/2502.08779
https://ai.ucf.edu/wp-content/uploads/2026/09/BBQ-V-ECCV.jpg
https://youtu.be/y4bLLiA_gGA?si=J61V2M-LkFjyrHMy},
year = {2026},
date = {2026-09-07},
urldate = {2026-09-07},
booktitle = {European Conference on Computer Vision (ECCV)},
publisher = {Springer},
abstract = {Stereotype biases in Large Multimodal Models (LMMs) perpetuate harmful societal prejudices, undermining the fairness and equity of AI applications. As LMMs grow increasingly influential, addressing and mitigating inherent biases related to stereotypes, harmful generations, and ambiguous assumptions in real-world scenarios has become essential. However, existing datasets evaluating stereotype biases in LMMs often lack diversity, rely on synthetic images, and often have single-actor images, leaving a gap in bias evaluation for real-world visual contexts. To address the gap in bias evaluation using real images, we introduce the BBQ-Vision (BBQ-V), the most comprehensive framework for assessing stereotype biases across nine diverse categories and 50 sub-categories with real and multi-actor images. BBQ-V benchmark contains 14,144 image-question pairs and rigorously evaluates LMMs through carefully curated, visually grounded scenarios, challenging them to reason accurately about visual stereotypes. It offers a robust evaluation framework featuring real-world visual samples, image variations, and open-ended question formats. BBQ-V enables a precise and nuanced assessment of a model's reasoning capabilities across varying levels of difficulty. Through rigorous testing of 19 state-of-the-art open-source (general-purpose and reasoning) and closed-source LMMs, we highlight that these top-performing models are often biased on several social stereotypes, and demonstrate that the thinking models induce more bias in the reasoning chains. This benchmark represents a significant step toward fostering fairness in AI systems and reducing harmful biases, laying the groundwork for more equitable and socially responsible LMMs. Our dataset and evaluation code are publicly available.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Updated 8/20/2026