{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T09:53:41Z","timestamp":1756461221920,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100010877","name":"Science, Technology and Innovation Commission of Shenzhen Municipality","doi-asserted-by":"publisher","award":["JCYJ20180307151516166"],"award-info":[{"award-number":["JCYJ20180307151516166"]}],"id":[{"id":"10.13039\/501100010877","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20191248"],"award-info":[{"award-number":["BK20191248"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science Foundation of China","award":["62072232"],"award-info":[{"award-number":["62072232"]}]},{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3479214","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T10:23:20Z","timestamp":1634552600000},"page":"4848-4852","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Joint Learning for Relationship and Interaction Analysis in Video with Multimodal Feature Fusion"],"prefix":"10.1145","author":[{"given":"Beibei","family":"Zhang","sequence":"first","affiliation":[{"name":"Nanjing University, Nanjing, China"}]},{"given":"Fan","family":"Yu","sequence":"additional","affiliation":[{"name":"Nanjing University & Shenzhen Research Institute of Nanjing University, Nanjing, China"}]},{"given":"Yanxin","family":"Gao","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}]},{"given":"Tongwei","family":"Ren","sequence":"additional","affiliation":[{"name":"Nanjing University & Shenzhen Research Institute of Nanjing University, Nanjing, China"}]},{"given":"Gangshan","family":"Wu","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/11744023_32"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00103"},{"volume-title":"Shot Contrastive Self-Supervised Learning for Scene Boundary Detection. In IEEE Conference on Computer Vision and Pattern Recognition. 9796--9805","year":"2021","author":"Chen Shixing","key":"e_1_3_2_2_3_1"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390742"},{"volume-title":"RetinaFace: Single-Shot Multi-Level Face Localisation in the Wild. In IEEE Conference on Computer Vision and Pattern Recognition. 5203--5212","year":"2020","author":"Deng Jiankang","key":"e_1_3_2_2_5_1"},{"volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT. 4171--4186.","year":"2019","author":"Devlin J.","key":"e_1_3_2_2_6_1"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.83"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1233903"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33712-3_20"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00987"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.12.004"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01016"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00809"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123380"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2072298.2072354"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.54"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_11"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416303"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_28"}],"event":{"name":"MM '21: ACM Multimedia Conference","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Virtual Event China","acronym":"MM '21"},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3479214","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3479214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:48Z","timestamp":1750193328000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3479214"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":21,"alternative-id":["10.1145\/3474085.3479214","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3479214","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}