{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T13:07:27Z","timestamp":1777640847921,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2016,10,31]],"date-time":"2016-10-31T00:00:00Z","timestamp":1477872000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2016,10,31]]},"DOI":"10.1145\/2993148.2997627","type":"proceedings-article","created":{"date-parts":[[2016,11,1]],"date-time":"2016-11-01T13:46:03Z","timestamp":1478007963000},"page":"433-436","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":134,"title":["Emotion recognition in the wild from videos using images"],"prefix":"10.1145","author":[{"given":"Sarah Adel","family":"Bargal","sequence":"first","affiliation":[{"name":"Boston University, USA"}]},{"given":"Emad","family":"Barsoum","sequence":"additional","affiliation":[{"name":"Microsoft Research, USA"}]},{"given":"Cristian Canton","family":"Ferrer","sequence":"additional","affiliation":[{"name":"Microsoft Research, USA"}]},{"given":"Cha","family":"Zhang","sequence":"additional","affiliation":[{"name":"Microsoft Research, USA"}]}],"member":"320","published-online":{"date-parts":[[2016,10,31]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"The fourth Emotion Recognition in the Wild (EmotiW) 2016 Challenge. https:\/\/sites.google.com\/site\/emotiw2016\/.  The fourth Emotion Recognition in the Wild (EmotiW) 2016 Challenge. https:\/\/sites.google.com\/site\/emotiw2016\/."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the International Conference on Image Processing, Computer Vision, and Pattern Recognition (IPCV)","author":"Bargal S. A.","year":"2012"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993165"},{"key":"e_1_3_2_1_4_1","volume-title":"Supervised transformer network for efficient face detection. arXiv preprint arXiv:1607.05477","author":"Chen D.","year":"2016"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997638"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2012.26"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830596"},{"key":"e_1_3_2_1_9_1","volume-title":"Facial action coding system","author":"Ekman P.","year":"1977"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-3203(02)00052-3"},{"key":"e_1_3_2_1_11_1","volume-title":"Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385","author":"He K.","year":"2015"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2004.830974"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_3_2_1_14_1","volume-title":"How deep neural networks can improve emotion recognition on video data. arXiv preprint arXiv:1602.07377","author":"Khorrami P.","year":"2016"},{"key":"e_1_3_2_1_15_1","first-page":"1105","volume-title":"Advances in neural information processing systems","author":"Krizhevsky A.","year":"2012"},{"key":"e_1_3_2_1_16_1","volume-title":"Do less and achieve more: Training CNNs for action recognition utilizing action images from the web. arXiv preprint arXiv:1512.07155","author":"Ma S.","year":"2015"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.01.004"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.456"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.438"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2008.08.005"},{"key":"e_1_3_2_1_21_1","first-page":"576","volume-title":"Advances in Neural Information Processing Systems","author":"Simonyan K.","year":"2014"},{"key":"e_1_3_2_1_22_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan K.","year":"2014"},{"key":"e_1_3_2_1_23_1","first-page":"8","volume-title":"Automatic Face and Gesture Recognition (FG), 2015 11th IEEE International Conference and Workshops on","volume":"1","author":"Walecki R."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.52"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1110"}],"event":{"name":"ICMI '16: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","location":"Tokyo Japan","acronym":"ICMI '16","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 18th ACM International Conference on Multimodal Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2993148.2997627","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2993148.2997627","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:39:44Z","timestamp":1750217984000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2993148.2997627"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10,31]]},"references-count":26,"alternative-id":["10.1145\/2993148.2997627","10.1145\/2993148"],"URL":"https:\/\/doi.org\/10.1145\/2993148.2997627","relation":{},"subject":[],"published":{"date-parts":[[2016,10,31]]},"assertion":[{"value":"2016-10-31","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}