Video Description Generation using Audio and Visual Cues.

@inproceedings{jin-2016-video, author = {Qin Jin and Junwei Liang}, editor = {John R. Kender and John R. Smith and Jiebo Luo and Susanne Boll and Winston H. Hsu}, title = {{Video Description Generation using Audio and Visual Cues}}, booktitle = {{Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval, ICMR 2016, New York, New York, USA, June 6-9, 2016}}, pages = {239--242}, publisher = {ACM}, year = {2016}, url = {https://doi.org/10.1145/2911996.2912043}, doi = {https://doi.org/10.1145/2911996.2912043} }