Fine-grained Text-Video Retrieval with Patch-level Temporal Difference and Aggregation.

@inproceedings{hu-2026-finegrained, author = {Jialong Hu and Zijie Song and Yang Wang and Zhenzhen Hu and Jia Li and Yixiao Ma and Richang Hong}, editor = {Stevan Rudinac and Zi Huang and Marcel Worring and Lucia Vadicamo and Xirong Li and Pascal Mettes and Lizi Liao}, title = {{Fine-grained Text-Video Retrieval with Patch-level Temporal Difference and Aggregation}}, booktitle = {{Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026}}, pages = {327--336}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805622.3810695}, doi = {https://doi.org/10.1145/3805622.3810695} }