VideoAVE: A Multi-Attribute Video-to-Text Attribute Value Extraction Dataset and Benchmark Models.

@inproceedings{cheng-2025-videoave, author = {Ming Cheng and Tong Wu and Jiazhen Hu and Jiaying Gong and Hoda Eldardiry}, 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 = {{VideoAVE: A Multi-Attribute Video-to-Text Attribute Value Extraction Dataset and Benchmark Models}}, booktitle = {{Proceedings of the 34th ACM International Conference on Information and Knowledge Management, CIKM 2025, Seoul, Republic of Korea, November 10-14, 2025}}, pages = {6340--6345}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3746252.3761621}, doi = {https://doi.org/10.1145/3746252.3761621} }