End-to-end Multi-task Learning Framework for Spatio-Temporal Grounding in Video Corpus.

@inproceedings{gao-2022-endtoend, author = {Yingqi Gao and Zhiling Luo and Shiqian Chen and Wei Zhou}, editor = {Mohammad Al Hasan and Li Xiong}, title = {{End-to-end Multi-task Learning Framework for Spatio-Temporal Grounding in Video Corpus}}, booktitle = {{Proceedings of the 31st ACM International Conference on Information & Knowledge Management, Atlanta, GA, USA, October 17-21, 2022}}, pages = {3958--3962}, publisher = {ACM}, year = {2022}, url = {https://doi.org/10.1145/3511808.3557596}, doi = {https://doi.org/10.1145/3511808.3557596} }