{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:23:08Z","timestamp":1772907788101,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":23,"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":[{"name":"National Key Research and Development Program of China","award":["2020AAA0106400"],"award-info":[{"award-number":["2020AAA0106400"]}]},{"name":"Beijing Natural Science Foundation","award":["4192059, JQ20022"],"award-info":[{"award-number":["4192059, JQ20022"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61922086, 61872366"],"award-info":[{"award-number":["61922086, 61872366"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3479216","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T10:23:20Z","timestamp":1634552600000},"page":"4853-4857","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["MM21 Pre-training for Video Understanding Challenge"],"prefix":"10.1145","author":[{"given":"Sihan","family":"Chen","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinxin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongze","family":"Hao","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zijia","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longteng","family":"Guo","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 6077--6086","author":"Gould Stephen","year":"2018","unstructured":"Stephen Gould , and Lei Zhang . 2018 . Bottom-up and top-down attention for image captioning and visual question answering . In Proceedings of the IEEE conference on computer vision and pattern recognition. 6077--6086 . Stephen Gould, and Lei Zhang. 2018. Bottom-up and top-down attention for image captioning and visual question answering. In Proceedings of the IEEE conference on computer vision and pattern recognition. 6077--6086."},{"key":"e_1_3_2_1_2_1","volume-title":"Continuously differentiable exponential linear units. arXiv preprint arXiv:1704.07483","author":"Barron Jonathan T","year":"2017","unstructured":"Jonathan T Barron . 2017. Continuously differentiable exponential linear units. arXiv preprint arXiv:1704.07483 ( 2017 ). Jonathan T Barron. 2017. Continuously differentiable exponential linear units. arXiv preprint arXiv:1704.07483 (2017)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_20"},{"key":"e_1_3_2_1_5_1","volume-title":"Non-autoregressive image captioning with counterfactuals-critical multi-agent learning. arXiv preprint arXiv:2005.04690","author":"Guo Longteng","year":"2020","unstructured":"Longteng Guo , Jing Liu , Xinxin Zhu , Xingjian He , Jie Jiang , and Hanqing Lu. 2020. Non-autoregressive image captioning with counterfactuals-critical multi-agent learning. arXiv preprint arXiv:2005.04690 ( 2020 ). Longteng Guo, Jing Liu, Xinxin Zhu, Xingjian He, Jie Jiang, and Hanqing Lu. 2020. Non-autoregressive image captioning with counterfactuals-critical multi-agent learning. arXiv preprint arXiv:2005.04690 (2020)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00901"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"e_1_3_2_1_10_1","volume-title":"OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation. arXiv preprint arXiv:2107.00249","author":"Liu Jing","year":"2021","unstructured":"Jing Liu , Xinxin Zhu , Fei Liu , Longteng Guo , Zijia Zhao , Mingzhen Sun , Weining Wang , Jinqiao Wang , and Hanqing Lu . 2021 . OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation. arXiv preprint arXiv:2107.00249 (2021). Jing Liu, Xinxin Zhu, Fei Liu, Longteng Guo, Zijia Zhao, Mingzhen Sun, Weining Wang, Jinqiao Wang, and Hanqing Lu. 2021. OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation. arXiv preprint arXiv:2107.00249 (2021)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455028"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00971"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"}],"event":{"name":"MM '21: ACM Multimedia Conference","location":"Virtual Event China","acronym":"MM '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3479216","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3479216","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\/3474085.3479216"}},"subtitle":["Video Captioning with Pretraining Techniques"],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":23,"alternative-id":["10.1145\/3474085.3479216","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3479216","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"}}]}}