DeepSVU: Towards In-depth Security-oriented Video Understanding via Unified Physical-world Regularized MoE.

@inproceedings{jin-2026-deepsvu, author = {Yujie Jin and Wenxin Zhang and Jingjing Wang and Guodong Zhou}, editor = {Hakim Hacid and Yoelle Maarek and Francesco Bonchi and Ido Guy and Emine Yilmaz}, title = {{DeepSVU: Towards In-depth Security-oriented Video Understanding via Unified Physical-world Regularized MoE}}, booktitle = {{Proceedings of the ACM Web Conference 2026, WWW 2026, Dubai, United Arab Emirates, originally scheduled for April 13-17, 2026, rescheduled for June 29 - July 3, 2026}}, pages = {3207--3217}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3774904.3792509}, doi = {https://doi.org/10.1145/3774904.3792509} }