Structuring Video Semantics with Temporal Triplets for Zero-Shot Video Question Answering.

@inproceedings{zong-2025-structuring, author = {Linlin Zong and Xinyu Zhai and Xinyue Liu and Wenxin Liang and Xianchao Zhang and Bo Xu}, editor = {Meeyoung Cha and Carl Yang and Senjuti Basu Roy and Chanyoung Park and Zhenhui Jessie Li and Noseong Park and Carl Yang and Senjuti Basu Roy and Zhenhui Jessie Li and Jaap Kamps and Kijung Shin and Bryan Hooi and Lifang He}, title = {{Structuring Video Semantics with Temporal Triplets for Zero-Shot Video Question Answering}}, booktitle = {{Proceedings of the 34th ACM International Conference on Information and Knowledge Management, CIKM 2025, Seoul, Republic of Korea, November 10-14, 2025}}, pages = {5545--5549}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3746252.3760857}, doi = {https://doi.org/10.1145/3746252.3760857} }