Cross-Modal Video Moment Retrieval with Spatial and Language-Temporal Attention.

@inproceedings{jiang-2019-crossmodal, author = {Bin Jiang and Xin Huang and Chao Yang and Junsong Yuan}, editor = {Abdulmotaleb El Saddik and Alberto Del Bimbo and Zhongfei Zhang and Alex Hauptmann and K. Sel\c{c}uk Candan and Marco Bertini and Lexing Xie and Xiaoyong Wei}, title = {{Cross-Modal Video Moment Retrieval with Spatial and Language-Temporal Attention}}, booktitle = {{Proceedings of the 2019 on International Conference on Multimedia Retrieval, ICMR 2019, Ottawa, ON, Canada, June 10-13, 2019}}, pages = {217--225}, publisher = {ACM}, year = {2019}, url = {https://doi.org/10.1145/3323873.3325019}, doi = {https://doi.org/10.1145/3323873.3325019} }