%0 Conference Paper %1 conf/cvpr/MonfortJLHFGO21 %A Monfort, Mathew %A Jin, SouYoung %A Liu, Alexander H. %A Harwath, David %A Feris, Rogério %A Glass, James R. %A Oliva, Aude %B CVPR %D 2021 %I Computer Vision Foundation / IEEE %K dblp %P 14871-14881 %T Spoken Moments: Learning Joint Audio-Visual Representations From Video Descriptions. %U http://dblp.uni-trier.de/db/conf/cvpr/cvpr2021.html#MonfortJLHFGO21

@inproceedings{conf/cvpr/MonfortJLHFGO21, added-at = {2022-07-18T00:00:00.000+0200}, author = {Monfort, Mathew and Jin, SouYoung and Liu, Alexander H. and Harwath, David and Feris, Rogério and Glass, James R. and Oliva, Aude}, biburl = {https://www.bibsonomy.org/bibtex/2a8d6827988abc467d19f44df24aec0fb/dblp}, booktitle = {CVPR}, crossref = {conf/cvpr/2021}, ee = {https://doi.org/10.1109/CVPR46437.2021.01463}, interhash = {1da26a69d0ffaf9e372045b95881cb1b}, intrahash = {a8d6827988abc467d19f44df24aec0fb}, keywords = {dblp}, pages = {14871-14881}, publisher = {Computer Vision Foundation / IEEE}, timestamp = {2024-04-09T20:53:51.000+0200}, title = {Spoken Moments: Learning Joint Audio-Visual Representations From Video Descriptions.}, url = {http://dblp.uni-trier.de/db/conf/cvpr/cvpr2021.html#MonfortJLHFGO21}, year = 2021 }