{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:21:31Z","timestamp":1778048491066,"version":"3.51.4"},"reference-count":77,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00462","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"4755-4765","source":"Crossref","is-referenced-by-count":0,"title":["Learning Unified Spatio-temporal Representations for Efficient Compressed Video Understanding"],"prefix":"10.1109","author":[{"given":"Shristi Das","family":"Biswas","sequence":"first","affiliation":[{"name":"Purdue University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Efstathia","family":"Soufleri","sequence":"additional","affiliation":[{"name":"Purdue University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arani","family":"Roy","sequence":"additional","affiliation":[{"name":"Purdue University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaushik","family":"Roy","sequence":"additional","affiliation":[{"name":"Purdue University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"11","key":"ref1","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"key":"ref2","article-title":"Cisco visual networking index (vni) global mobile data traffic forecast update","author":"Pepper","year":"2013","journal-title":"Mobile World Congress"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3170358.3170376"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00631"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref9","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"Simonyan","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref11","first-page":"55","article-title":"Spatiotemporal residual networks for video action recognition. corr abs\/1611.02155 (2016)","volume":"54","author":"Feichtenhofer","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref13","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref15","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref16","article-title":"A short note about kinetics-600","author":"Carreira","year":"2018"},{"key":"ref17","first-page":"5842","article-title":"The","volume-title":"something something\" video database for learning and evaluating visual common sense,\" in Proceedings of the IEEE international conference on computer vision","author":"Goyal"},{"key":"ref18","article-title":"A short note on the kinetics-700 human action dataset","author":"Carreira","year":"2019"},{"key":"ref19","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Alexey","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01332"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01768"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01267"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01752"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_40"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/103085.103090"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.138"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2019.101695"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SIBGRAPI.2019.00012"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096477"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097076"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1424-8"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.99"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref45","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"International conference on machine learning","author":"Tan"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00630"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01233"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.522"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00333"},{"key":"ref55","article-title":"Uniformer: Unified transformer for efficient spatiotemporal representation learning","author":"Li","year":"2022"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2000.899352"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00350"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00136"},{"key":"ref59","article-title":"Training independent subnetworks for robust prediction","author":"Havasi","year":"2020"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00086"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0304"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/S0361-9230(99)00161-6"},{"key":"ref63","article-title":"Theoretical neuroscience (vol. 806)","author":"Dayan","year":"2001"},{"key":"ref64","article-title":"Heaviside step function","author":"Weisstein","year":"2002"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_22"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1003560"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2010.04.028"},{"key":"ref68","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1809.00219"},{"key":"ref70","article-title":"Better plain vit baselines for imagenet-1k","author":"Beyer","year":"2022"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref73","article-title":"Adam: A method for stochastic optimization","author":"Diederik","year":"2014","journal-title":"(No Title)"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-61068-4_7"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2019.2931595"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2016.00508"},{"key":"ref77","article-title":"Convolutional lstm network: A machine learning approach for precipitation nowcasting","volume":"28","author":"Shi","year":"2015","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492186.pdf?arnumber=11492186","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:05:49Z","timestamp":1778047549000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492186\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00462","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}