CVPR 2025 Open Access Repository

The 6th Workshop on Fair, Data-Efficient, and Trusted Computer Vision

Coordinated Robustness Evaluation Framework for Vision-Language Models: Ashwin Ramesh Babu,

Sajad Mousavi,

Vineet Gundecha,

Sahand Ghorbanpour,

Avisek Naug,

Antonio Guillen,

Ricardo Luna,

Soumyendu Sarkar; [pdf] [arXiv]
[bibtex]
@InProceedings{Babu_2025_CVPR, author = {Babu, Ashwin Ramesh and Mousavi, Sajad and Gundecha, Vineet and Ghorbanpour, Sahand and Naug, Avisek and Guillen, Antonio and Luna, Ricardo and Sarkar, Soumyendu}, title = {Coordinated Robustness Evaluation Framework for Vision-Language Models}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {712-720} }
Balancing Privacy and Action Performance: A Penalty-Driven Approach to Image Anonymization: Nazia Aslam,

Kamal Nasrollahi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Aslam_2025_CVPR, author = {Aslam, Nazia and Nasrollahi, Kamal}, title = {Balancing Privacy and Action Performance: A Penalty-Driven Approach to Image Anonymization}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {729-738} }
A Large-Scale Analysis on Contextual Self-Supervised Video Representation Learning: Akash Kumar,

Ashlesha Kumar,

Vibhav Vineet,

Yogesh S Rawat; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kumar_2025_CVPR, author = {Kumar, Akash and Kumar, Ashlesha and Vineet, Vibhav and Rawat, Yogesh S}, title = {A Large-Scale Analysis on Contextual Self-Supervised Video Representation Learning}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {670-681} }
Is Temporal Prompting All We Need For Limited Labeled Action Recognition?: Shreyank Gowda,

Boyan Gao,

Xiao Gu,

Xiabo Jin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gowda_2025_CVPR, author = {Gowda, Shreyank and Gao, Boyan and Gu, Xiao and Jin, Xiabo}, title = {Is Temporal Prompting All We Need For Limited Labeled Action Recognition?}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {682-692} }
ProtoPatchNet: An Interpretable Patch-Based Prototypical Network: Mohana Singh,

Vivek B S,

Jayavardhana Gubbi,

R. Venkatesh Babu; [pdf]
[bibtex]
@InProceedings{Singh_2025_CVPR, author = {Singh, Mohana and S, Vivek B and Gubbi, Jayavardhana and Babu, R. Venkatesh}, title = {ProtoPatchNet: An Interpretable Patch-Based Prototypical Network}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {721-728} }
Defending Against Transfer-Based Adversarial Attacks Using SVD-Driven Feature Evolution: Xinlei Liu,

Tao Hu,

Peng Yi,

Qingtao Pan,

Hailong Ma,

Yiming Jiang,

Baolin Li; [pdf]
[bibtex]
@InProceedings{Liu_2025_CVPR, author = {Liu, Xinlei and Hu, Tao and Yi, Peng and Pan, Qingtao and Ma, Hailong and Jiang, Yiming and Li, Baolin}, title = {Defending Against Transfer-Based Adversarial Attacks Using SVD-Driven Feature Evolution}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {703-711} }
Optimising Vision Transformer Performance on Limited Datasets: A Multi-Gradient Approach: Mohsin Ali,

Haider Raza,

John Q. Gan,

Muhammad Haris; [pdf] [supp]
[bibtex]
@InProceedings{Ali_2025_CVPR, author = {Ali, Mohsin and Raza, Haider and Gan, John Q. and Haris, Muhammad}, title = {Optimising Vision Transformer Performance on Limited Datasets: A Multi-Gradient Approach}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {693-702} }