2022
Ristea, Nicolae-Catalin; Madan, Neelu; Ionescu, Radu Tudor; Nasrollahi, Kamal; Khan, Fahad Shahbaz; Moeslund, Thomas B.; Shah, Mubarak
Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection Conference
IEEE Computer Vision and Pattern Recognition, 2022.
Tags: Anomaly Detection, CVPR, Self-Supervised Learning, Self-Supervision | Links:
@conference{nokey_101,
title = {Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection},
author = {Nicolae-Catalin Ristea and Neelu Madan and Radu Tudor Ionescu and Kamal Nasrollahi and Fahad Shahbaz Khan and Thomas B. Moeslund and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/SSPCAB_camera-arxiv.pdf},
year = {2022},
date = {2022-06-19},
urldate = {2022-06-19},
publisher = {IEEE Computer Vision and Pattern Recognition},
keywords = {Anomaly Detection, CVPR, Self-Supervised Learning, Self-Supervision},
pubstate = {published},
tppubtype = {conference}
}
Ristea, Nicolae-Catalin; Madan, Neelu; Ionescu, Radu Tudor; Nasrollahi, Kamal; Khan, Fahad Shahbaz; Moeslund, Thomas B.; Shah, Mubarak
Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection Conference
IEEE Computer Vision and Pattern Recognition, 2022.
Tags: Anomaly Detection, CVPR, Self-Supervised Learning, Self-Supervision | Links:
@conference{nokey_149,
title = {Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection},
author = {Nicolae-Catalin Ristea and Neelu Madan and Radu Tudor Ionescu and Kamal Nasrollahi and Fahad Shahbaz Khan and Thomas B. Moeslund and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/SSPCAB_camera-arxiv.pdf},
year = {2022},
date = {2022-06-19},
urldate = {2022-06-19},
publisher = {IEEE Computer Vision and Pattern Recognition},
keywords = {Anomaly Detection, CVPR, Self-Supervised Learning, Self-Supervision},
pubstate = {published},
tppubtype = {conference}
}
Dave, Ishan; Gupta, Rohit; Rizve, Mamshad Nayeem; Shah, Mubarak
TCLR: Temporal Contrastive Learning for Video Representation Journal Article
In: Computer Vision and Image Understanding, vol. 219, iss. 1077-3142, pp. 103406, 2022.
Abstract | Tags: Self-Supervised Learning | Links:
@article{nokey_110,
title = {TCLR: Temporal Contrastive Learning for Video Representation},
author = {Ishan Dave and Rohit Gupta and Mamshad Nayeem Rizve and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/1-s2.0-S1077314222000376-main.pdf
https://github.com/DAVEISHAN/TCLR},
doi = {https://doi.org/10.1016/j.cviu.2022.103406},
year = {2022},
date = {2022-05-01},
urldate = {2022-05-01},
journal = {Computer Vision and Image Understanding},
volume = {219},
issue = {1077-3142},
pages = {103406},
abstract = {Contrastive learning has nearly closed the gap between supervised and self-supervised learning of image representations, and has also been explored for videos. However, prior work on contrastive learning for video data has not explored the effect of explicitly encouraging the features to be distinct across the temporal dimension. We develop a new temporal contrastive learning framework consisting of two novel losses to improve upon existing contrastive self-supervised video representation learning methods. The local–local temporal contrastive loss adds the task of discriminating between non-overlapping clips from the same video, whereas the global–local temporal contrastive aims to discriminate between timesteps of the feature map of an input clip in order to increase the temporal diversity of the learned features. Our proposed temporal contrastive learning framework achieves significant improvement over the state-of-the-art results in various downstream video understanding tasks such as action recognition, limited-label action classification, and nearest-neighbor video retrieval on multiple video datasets and backbones. We also demonstrate significant improvement in fine-grained action classification for visually similar classes. With the commonly used 3D ResNet-18 architecture with UCF101 pretraining, we achieve 82.4% (+5.1% increase over the previous best) top-1 accuracy on UCF101 and 52.9% (+5.4% increase) on HMDB51 action classification, and 56.2% (+11.7% increase) Top-1 Recall on UCF101 nearest neighbor video retrieval. Code released at https://github.com/DAVEISHAN/TCLR.},
keywords = {Self-Supervised Learning},
pubstate = {published},
tppubtype = {article}
}
Contrastive learning has nearly closed the gap between supervised and self-supervised learning of image representations, and has also been explored for videos. However, prior work on contrastive learning for video data has not explored the effect of explicitly encouraging the features to be distinct across the temporal dimension. We develop a new temporal contrastive learning framework consisting of two novel losses to improve upon existing contrastive self-supervised video representation learning methods. The local–local temporal contrastive loss adds the task of discriminating between non-overlapping clips from the same video, whereas the global–local temporal contrastive aims to discriminate between timesteps of the feature map of an input clip in order to increase the temporal diversity of the learned features. Our proposed temporal contrastive learning framework achieves significant improvement over the state-of-the-art results in various downstream video understanding tasks such as action recognition, limited-label action classification, and nearest-neighbor video retrieval on multiple video datasets and backbones. We also demonstrate significant improvement in fine-grained action classification for visually similar classes. With the commonly used 3D ResNet-18 architecture with UCF101 pretraining, we achieve 82.4% (+5.1% increase over the previous best) top-1 accuracy on UCF101 and 52.9% (+5.4% increase) on HMDB51 action classification, and 56.2% (+11.7% increase) Top-1 Recall on UCF101 nearest neighbor video retrieval. Code released at https://github.com/DAVEISHAN/TCLR.
Dave, Ishan; Gupta, Rohit; Rizve, Mamshad Nayeem; Shah, Mubarak
TCLR: Temporal Contrastive Learning for Video Representation Journal Article
In: Computer Vision and Image Understanding, vol. 219, iss. 1077-3142, pp. 103406, 2022.
Abstract | Tags: Self-Supervised Learning | Links:
@article{nokey_158,
title = {TCLR: Temporal Contrastive Learning for Video Representation},
author = {Ishan Dave and Rohit Gupta and Mamshad Nayeem Rizve and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/1-s2.0-S1077314222000376-main.pdf
https://github.com/DAVEISHAN/TCLR},
doi = {https://doi.org/10.1016/j.cviu.2022.103406},
year = {2022},
date = {2022-05-01},
urldate = {2022-05-01},
journal = {Computer Vision and Image Understanding},
volume = {219},
issue = {1077-3142},
pages = {103406},
abstract = {Contrastive learning has nearly closed the gap between supervised and self-supervised learning of image representations, and has also been explored for videos. However, prior work on contrastive learning for video data has not explored the effect of explicitly encouraging the features to be distinct across the temporal dimension. We develop a new temporal contrastive learning framework consisting of two novel losses to improve upon existing contrastive self-supervised video representation learning methods. The local–local temporal contrastive loss adds the task of discriminating between non-overlapping clips from the same video, whereas the global–local temporal contrastive aims to discriminate between timesteps of the feature map of an input clip in order to increase the temporal diversity of the learned features. Our proposed temporal contrastive learning framework achieves significant improvement over the state-of-the-art results in various downstream video understanding tasks such as action recognition, limited-label action classification, and nearest-neighbor video retrieval on multiple video datasets and backbones. We also demonstrate significant improvement in fine-grained action classification for visually similar classes. With the commonly used 3D ResNet-18 architecture with UCF101 pretraining, we achieve 82.4% (+5.1% increase over the previous best) top-1 accuracy on UCF101 and 52.9% (+5.4% increase) on HMDB51 action classification, and 56.2% (+11.7% increase) Top-1 Recall on UCF101 nearest neighbor video retrieval. Code released at https://github.com/DAVEISHAN/TCLR.},
keywords = {Self-Supervised Learning},
pubstate = {published},
tppubtype = {article}
}
Contrastive learning has nearly closed the gap between supervised and self-supervised learning of image representations, and has also been explored for videos. However, prior work on contrastive learning for video data has not explored the effect of explicitly encouraging the features to be distinct across the temporal dimension. We develop a new temporal contrastive learning framework consisting of two novel losses to improve upon existing contrastive self-supervised video representation learning methods. The local–local temporal contrastive loss adds the task of discriminating between non-overlapping clips from the same video, whereas the global–local temporal contrastive aims to discriminate between timesteps of the feature map of an input clip in order to increase the temporal diversity of the learned features. Our proposed temporal contrastive learning framework achieves significant improvement over the state-of-the-art results in various downstream video understanding tasks such as action recognition, limited-label action classification, and nearest-neighbor video retrieval on multiple video datasets and backbones. We also demonstrate significant improvement in fine-grained action classification for visually similar classes. With the commonly used 3D ResNet-18 architecture with UCF101 pretraining, we achieve 82.4% (+5.1% increase over the previous best) top-1 accuracy on UCF101 and 52.9% (+5.4% increase) on HMDB51 action classification, and 56.2% (+11.7% increase) Top-1 Recall on UCF101 nearest neighbor video retrieval. Code released at https://github.com/DAVEISHAN/TCLR.
Kini, Jyoti; Khan, Fahad Shahbaz; Khan, Salman; Shah, Mubarak
Self-Supervised Video Object Segmentation via Cutout Prediction and Tagging Technical Report
no. arXiv:2204.10846, 2022.
Tags: Self-Supervised Learning, Video Object Segmentation | Links:
@techreport{Kini2022,
title = {Self-Supervised Video Object Segmentation via Cutout Prediction and Tagging},
author = {Jyoti Kini and Fahad Shahbaz Khan and Salman Khan and Mubarak Shah},
url = {https://arxiv.org/pdf/2204.10846.pdf},
year = {2022},
date = {2022-04-24},
urldate = {2022-04-24},
number = {arXiv:2204.10846},
keywords = {Self-Supervised Learning, Video Object Segmentation},
pubstate = {published},
tppubtype = {techreport}
}
Kini, Jyoti; Khan, Fahad Shahbaz; Khan, Salman; Shah, Mubarak
Self-Supervised Video Object Segmentation via Cutout Prediction and Tagging Technical Report
no. arXiv:2204.10846, 2022.
Tags: Self-Supervised Learning, Video Object Segmentation | Links:
@techreport{Kini2022d,
title = {Self-Supervised Video Object Segmentation via Cutout Prediction and Tagging},
author = {Jyoti Kini and Fahad Shahbaz Khan and Salman Khan and Mubarak Shah},
url = {https://arxiv.org/pdf/2204.10846.pdf},
year = {2022},
date = {2022-04-24},
urldate = {2022-04-24},
number = {arXiv:2204.10846},
keywords = {Self-Supervised Learning, Video Object Segmentation},
pubstate = {published},
tppubtype = {techreport}
}
2021
Georgescu, Mariana Iuliana; Bărbălău, Antonio; Ionescu, Radu Tudor; Khan, Fahad Shahbaz; Popescu, Marius; Shah, Mubarak
Anomaly Detection in Video via Self-Supervised and Multi-Task Learning Conference
IEEE Conference on Computer Vision and Pattern Recognition, 2021.
Abstract | Tags: Anomaly Detection, Multi-Task Learning, Self-Supervised Learning | Links:
@conference{georgescu2020anomaly,
title = {Anomaly Detection in Video via Self-Supervised and Multi-Task Learning},
author = {Mariana Iuliana Georgescu and Antonio Bărbălău and Radu Tudor Ionescu and Fahad Shahbaz Khan and Marius Popescu and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Publications_Anomaly-Detection-in-Video-via-Self-Supervised-and-Multi-Task-Learning.pdf
https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Publications_Anomaly-Detection-in-Video-via-Self-Supervised-and-Multi-Task-Learning_Supp.pdf
https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Anomaly-Detection-in-Video-via-Self-Supervised-and-Multi-Task-Learning.pptx
https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Anomaly-Detection-in-Video-via-Self-Supervised-and-Multi-Task-Learning.mp4},
year = {2021},
date = {2021-06-19},
urldate = {2021-06-19},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
abstract = {Anomaly detection in video is a challenging computer vision problem. Due to the lack of anomalous events at training time, anomaly detection requires the design of learning methods without full supervision. In this paper, we approach anomalous event detection in video through self-supervised and multi-task learning at the object level. We first utilize a pre-trained detector to detect objects. Then, we train a 3D convolutional neural network to produce discriminative anomaly-specific information by jointly learning multiple proxy tasks: three self-supervised and one based on knowledge distillation. The self-supervised tasks are: (i) discrimination of forward/backward moving objects (arrow of time), (ii) discrimination of objects in consecutive/intermittent frames (motion irregularity) and (iii) reconstruction of object-specific appearance information. The knowledge distillation task takes into account both classification and detection information, generating large prediction discrepancies between teacher and student models when anomalies occur. To the best of our knowledge, we are the first to approach anomalous event detection in video as a multi-task learning problem, integrating multiple self-supervised and knowledge distillation proxy tasks in a single architecture. Our lightweight architecture outperforms the state-of-the-art methods on three benchmarks: Avenue, ShanghaiTech and UCSD Ped2. Additionally, we perform an ablation study demonstrating the importance of integrating self-supervised learning and normality-specific distillation in a multi-task learning setting.},
keywords = {Anomaly Detection, Multi-Task Learning, Self-Supervised Learning},
pubstate = {published},
tppubtype = {conference}
}
Anomaly detection in video is a challenging computer vision problem. Due to the lack of anomalous events at training time, anomaly detection requires the design of learning methods without full supervision. In this paper, we approach anomalous event detection in video through self-supervised and multi-task learning at the object level. We first utilize a pre-trained detector to detect objects. Then, we train a 3D convolutional neural network to produce discriminative anomaly-specific information by jointly learning multiple proxy tasks: three self-supervised and one based on knowledge distillation. The self-supervised tasks are: (i) discrimination of forward/backward moving objects (arrow of time), (ii) discrimination of objects in consecutive/intermittent frames (motion irregularity) and (iii) reconstruction of object-specific appearance information. The knowledge distillation task takes into account both classification and detection information, generating large prediction discrepancies between teacher and student models when anomalies occur. To the best of our knowledge, we are the first to approach anomalous event detection in video as a multi-task learning problem, integrating multiple self-supervised and knowledge distillation proxy tasks in a single architecture. Our lightweight architecture outperforms the state-of-the-art methods on three benchmarks: Avenue, ShanghaiTech and UCSD Ped2. Additionally, we perform an ablation study demonstrating the importance of integrating self-supervised learning and normality-specific distillation in a multi-task learning setting.
Georgescu, Mariana Iuliana; Bărbălău, Antonio; Ionescu, Radu Tudor; Khan, Fahad Shahbaz; Popescu, Marius; Shah, Mubarak
Anomaly Detection in Video via Self-Supervised and Multi-Task Learning Conference
IEEE Conference on Computer Vision and Pattern Recognition, 2021.
Abstract | Tags: Anomaly Detection, Multi-Task Learning, Self-Supervised Learning | Links:
@conference{georgescu2020anomalyb,
title = {Anomaly Detection in Video via Self-Supervised and Multi-Task Learning},
author = {Mariana Iuliana Georgescu and Antonio Bărbălău and Radu Tudor Ionescu and Fahad Shahbaz Khan and Marius Popescu and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Publications_Anomaly-Detection-in-Video-via-Self-Supervised-and-Multi-Task-Learning.pdf
https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Publications_Anomaly-Detection-in-Video-via-Self-Supervised-and-Multi-Task-Learning_Supp.pdf
https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Anomaly-Detection-in-Video-via-Self-Supervised-and-Multi-Task-Learning.pptx
https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Anomaly-Detection-in-Video-via-Self-Supervised-and-Multi-Task-Learning.mp4},
year = {2021},
date = {2021-06-19},
urldate = {2021-06-19},
publisher = {IEEE Conference on Computer Vision and Pattern Recognition},
abstract = {Anomaly detection in video is a challenging computer vision problem. Due to the lack of anomalous events at training time, anomaly detection requires the design of learning methods without full supervision. In this paper, we approach anomalous event detection in video through self-supervised and multi-task learning at the object level. We first utilize a pre-trained detector to detect objects. Then, we train a 3D convolutional neural network to produce discriminative anomaly-specific information by jointly learning multiple proxy tasks: three self-supervised and one based on knowledge distillation. The self-supervised tasks are: (i) discrimination of forward/backward moving objects (arrow of time), (ii) discrimination of objects in consecutive/intermittent frames (motion irregularity) and (iii) reconstruction of object-specific appearance information. The knowledge distillation task takes into account both classification and detection information, generating large prediction discrepancies between teacher and student models when anomalies occur. To the best of our knowledge, we are the first to approach anomalous event detection in video as a multi-task learning problem, integrating multiple self-supervised and knowledge distillation proxy tasks in a single architecture. Our lightweight architecture outperforms the state-of-the-art methods on three benchmarks: Avenue, ShanghaiTech and UCSD Ped2. Additionally, we perform an ablation study demonstrating the importance of integrating self-supervised learning and normality-specific distillation in a multi-task learning setting.},
keywords = {Anomaly Detection, Multi-Task Learning, Self-Supervised Learning},
pubstate = {published},
tppubtype = {conference}
}
Anomaly detection in video is a challenging computer vision problem. Due to the lack of anomalous events at training time, anomaly detection requires the design of learning methods without full supervision. In this paper, we approach anomalous event detection in video through self-supervised and multi-task learning at the object level. We first utilize a pre-trained detector to detect objects. Then, we train a 3D convolutional neural network to produce discriminative anomaly-specific information by jointly learning multiple proxy tasks: three self-supervised and one based on knowledge distillation. The self-supervised tasks are: (i) discrimination of forward/backward moving objects (arrow of time), (ii) discrimination of objects in consecutive/intermittent frames (motion irregularity) and (iii) reconstruction of object-specific appearance information. The knowledge distillation task takes into account both classification and detection information, generating large prediction discrepancies between teacher and student models when anomalies occur. To the best of our knowledge, we are the first to approach anomalous event detection in video as a multi-task learning problem, integrating multiple self-supervised and knowledge distillation proxy tasks in a single architecture. Our lightweight architecture outperforms the state-of-the-art methods on three benchmarks: Avenue, ShanghaiTech and UCSD Ped2. Additionally, we perform an ablation study demonstrating the importance of integrating self-supervised learning and normality-specific distillation in a multi-task learning setting.
2020
Georgescu, Mariana-Iuliana; Barbalau, Antonio; Ionescu, Radu Tudor; Khan, Fahad Shahbaz; Popescu, Marius; Shah, Mubarak
Anomaly Detection in Video via Self-Supervised and Multi-Task Learning Technical Report
no. arXiv:2011.07491, 2020.
Tags: Anomaly Detection, CVPR-2021, Multi-Task Learning, Self-Supervised Learning | Links:
@techreport{Georgescu2020b,
title = {Anomaly Detection in Video via Self-Supervised and Multi-Task Learning},
author = {Mariana-Iuliana Georgescu and Antonio Barbalau and Radu Tudor Ionescu and Fahad Shahbaz Khan and Marius Popescu and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Publicatons_Anomaly-Detection-in-Video-via-Self-Supervised-and-Multi-Task-Learning.pdf},
year = {2020},
date = {2020-11-15},
urldate = {2020-11-15},
number = {arXiv:2011.07491},
howpublished = {CVPR-2021},
keywords = {Anomaly Detection, CVPR-2021, Multi-Task Learning, Self-Supervised Learning},
pubstate = {published},
tppubtype = {techreport}
}
Georgescu, Mariana-Iuliana; Barbalau, Antonio; Ionescu, Radu Tudor; Khan, Fahad Shahbaz; Popescu, Marius; Shah, Mubarak
Anomaly Detection in Video via Self-Supervised and Multi-Task Learning Technical Report
no. arXiv:2011.07491, 2020.
Tags: Anomaly Detection, CVPR-2021, Multi-Task Learning, Self-Supervised Learning | Links:
@techreport{Georgescu2020bb,
title = {Anomaly Detection in Video via Self-Supervised and Multi-Task Learning},
author = {Mariana-Iuliana Georgescu and Antonio Barbalau and Radu Tudor Ionescu and Fahad Shahbaz Khan and Marius Popescu and Mubarak Shah},
url = {https://www.crcv.ucf.edu/wp-content/uploads/2018/11/Publicatons_Anomaly-Detection-in-Video-via-Self-Supervised-and-Multi-Task-Learning.pdf},
year = {2020},
date = {2020-11-15},
urldate = {2020-11-15},
number = {arXiv:2011.07491},
howpublished = {CVPR-2021},
keywords = {Anomaly Detection, CVPR-2021, Multi-Task Learning, Self-Supervised Learning},
pubstate = {published},
tppubtype = {techreport}
}