DenseSpeech: Dense Multi-Segment Temporal Grounding in Public Speaking Videos.

@inproceedings{tan-2026-densespeech, author = {Jiachen Tan and Tingting Zhang and Tao Zhou and Guangyao Su and Jianwei Fang and Bin Wu and Chunping Zheng}, editor = {Stevan Rudinac and Zi Huang and Marcel Worring and Lucia Vadicamo and Xirong Li and Pascal Mettes and Lizi Liao}, title = {{DenseSpeech: Dense Multi-Segment Temporal Grounding in Public Speaking Videos}}, booktitle = {{Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026}}, pages = {1317--1326}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805622.3810702}, doi = {https://doi.org/10.1145/3805622.3810702} }