VideoTG-R1: Boosting Video Temporal Grounding via Curriculum Reinforcement Learning on Reflected Boundary Annotations.

@inproceedings{dong-2026-videotgr1, author = {Lu Dong and Haiyu Zhang and Han Lin and Ziang Yan and Xiangyu Zeng and Hongjie Zhang and Yifei Huang and Yi Wang and Zhen-Hua Ling and Limin Wang and Yali Wang}, editor = {Stevan Rudinac and Zi Huang and Marcel Worring and Lucia Vadicamo and Xirong Li and Pascal Mettes and Lizi Liao}, title = {{VideoTG-R1: Boosting Video Temporal Grounding via Curriculum Reinforcement Learning on Reflected Boundary Annotations}}, booktitle = {{Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026}}, pages = {1432--1441}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805622.3810709}, doi = {https://doi.org/10.1145/3805622.3810709} }