Learning Joint Embedding with Multimodal Cues for Cross-Modal Video-Text Retrieval.

@inproceedings{mithun-2018-learning, author = {Niluthpol Chowdhury Mithun and Juncheng Li and Florian Metze and Amit K. Roy-Chowdhury}, editor = {Kiyoharu Aizawa and Michael S. Lew and Shin'ichi Satoh}, title = {{Learning Joint Embedding with Multimodal Cues for Cross-Modal Video-Text Retrieval}}, booktitle = {{Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval, ICMR 2018, Yokohama, Japan, June 11-14, 2018}}, pages = {19--27}, publisher = {ACM}, year = {2018}, url = {https://doi.org/10.1145/3206025.3206064}, doi = {https://doi.org/10.1145/3206025.3206064} }