Short-Form Video Understanding: The Next Frontier in Video Intelligence


Hashtag2Action: Data Engineering and Self-Supervised Pre-Training for Action Recognition in Short-Form Videos
Yang Qian,
Ali Kargarandehkordi,
Yinan Sun,
Parnian Azizian,
Onur Cezmi Mutlu,
Saimourya Surabhi,
Zain Jabbar,
Dennis Wall,
Peter Washington,
Huaijin Chen
[pdf]
[bibtex]
@InProceedings{Qian_2025_ICCV, author = {Qian, Yang and Kargarandehkordi, Ali and Sun, Yinan and Azizian, Parnian and Mutlu, Onur Cezmi and Surabhi, Saimourya and Jabbar, Zain and Wall, Dennis and Washington, Peter and Chen, Huaijin}, title = {Hashtag2Action: Data Engineering and Self-Supervised Pre-Training for Action Recognition in Short-Form Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {2965-2975} }

Watch, Listen, Understand, Mislead: Tri-modal Adversarial Attacks on Short Videos for Content Appropriateness Evaluation
Sahid Hossain Mustakim,
S M Jishanul Islam,
Ummay Maria Muna,
Montasir Chowdhury,
Mohammed Jawwadul Islam,
Sadia Ahmmed,
Tashfia Sikder,
Syed Tasdid Azam Dhrubo,
Swakkhar Shatabda
[pdf] [arXiv]
[bibtex]
@InProceedings{Mustakim_2025_ICCV, author = {Mustakim, Sahid Hossain and Islam, S M Jishanul and Muna, Ummay Maria and Chowdhury, Montasir and Islam, Mohammed Jawwadul and Ahmmed, Sadia and Sikder, Tashfia and Dhrubo, Syed Tasdid Azam and Shatabda, Swakkhar}, title = {Watch, Listen, Understand, Mislead: Tri-modal Adversarial Attacks on Short Videos for Content Appropriateness Evaluation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {2955-2964} }

Difformer for Action Segmentation
Nicolas Aziere,
Tieqiao Wang,
Sinisa Todorovic
[pdf]
[bibtex]
@InProceedings{Aziere_2025_ICCV, author = {Aziere, Nicolas and Wang, Tieqiao and Todorovic, Sinisa}, title = {Difformer for Action Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {2986-2995} }

End-to-End Action Segmentation Transformer
Tieqiao Wang,
Sinisa Todorovic
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Tieqiao and Todorovic, Sinisa}, title = {End-to-End Action Segmentation Transformer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2025}, pages = {2976-2985} }