{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:05:32Z","timestamp":1775228732338,"version":"3.50.1"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,10]],"date-time":"2023-09-10T00:00:00Z","timestamp":1694304000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,10]],"date-time":"2023-09-10T00:00:00Z","timestamp":1694304000000},"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":[[2023,9,10]]},"DOI":"10.1109\/aciiw59127.2023.10388162","type":"proceedings-article","created":{"date-parts":[[2024,1,16]],"date-time":"2024-01-16T18:17:34Z","timestamp":1705429054000},"page":"1-8","source":"Crossref","is-referenced-by-count":3,"title":["Social Event Context and Affect Prediction in Group Videos"],"prefix":"10.1109","author":[{"given":"Aarti","family":"Malhotra","sequence":"first","affiliation":[{"name":"University of Waterloo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Garima","family":"Sharma","sequence":"additional","affiliation":[{"name":"Monash University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rishikesh","family":"Kumar","sequence":"additional","affiliation":[{"name":"DeepSync Technologies"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhinav","family":"Dhall","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Ropar"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jesse","family":"Hoey","sequence":"additional","affiliation":[{"name":"University of Waterloo"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3143010"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2910017.2910624"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/1529100619832930"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0963721411422522"},{"key":"ref7","first-page":"81","article-title":"Group emotion: A view from top and bottom","volume":"1","author":"Barsade","year":"1998","journal-title":"Research on managing groups and teams"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2396531"},{"key":"ref9","article-title":"Is Space-Time Attention All You Need for Video Understanding?","author":"Bertasius","year":"2021","journal-title":"arXiv preprint arXiv:2102.05095"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.151"},{"key":"ref11","article-title":"A^2-Nets: Double Attention Networks","author":"Chen","year":"2018","journal-title":"arXiv preprint arXiv:1810.11579"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298815"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2986969"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2397456"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37444-9_48"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7163151"},{"key":"ref17","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv:2010.11929"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00092"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3264990"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239348"},{"key":"ref22","article-title":"Textual Emotion Processing from Event Analysis","volume-title":"CIPS-SIGHAN Joint Conference on Chinese Language Processing","author":"Huang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2818015"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1991996.1992025"},{"key":"ref25","article-title":"Would mega-scale datasets further enhance spatiotemporal 3D CNNs?","author":"Kataoka","year":"2020","journal-title":"arXiv preprint arXiv:2004.04968"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1006\/obhd.2001.2974"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.285"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-57837-8_38"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1902661116"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2072508.2072511"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00561"},{"key":"ref32","article-title":"Non-volume preserving-based feature fusion approach to group-level expression recognition on crowd videos","author":"Quach","year":"2018","journal-title":"arXiv preprint arXiv:1811.11849"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3143007"},{"key":"ref34","article-title":"Social event detection at mediaeval 2013: Challenges, datasets, and evaluation","volume-title":"Proceedings of the MediaEval 2013 Multimedia Benchmark Workshop Barcelona, Spain, October 18-19,2013","author":"Reuter"},{"key":"ref35","article-title":"An Image is Worth 16x16 Words, What is a Video Worth?","author":"Sharir","year":"2021","journal-title":"arXiv preprint arXiv:2103.13915"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3104170"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ACIIW.2019.8925231"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3143008"},{"key":"ref39","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_27"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.520"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123282"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298768"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.105695"}],"event":{"name":"2023 11th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW)","location":"Cambridge, MA, USA","start":{"date-parts":[[2023,9,10]]},"end":{"date-parts":[[2023,9,13]]}},"container-title":["2023 11th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388069\/10388071\/10388162.pdf?arnumber=10388162","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T01:55:22Z","timestamp":1705542922000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10388162\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,10]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/aciiw59127.2023.10388162","relation":{},"subject":[],"published":{"date-parts":[[2023,9,10]]}}}