{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:40:12Z","timestamp":1777128012946,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T00:00:00Z","timestamp":1571097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Joint Research Program of ZJU & Hikvision Research Institute"},{"name":"Chinese Knowledge Center for Engineering Sciences and Technology"},{"name":"the Fundamental Research Funds for the Central Universities"},{"name":"National Natural Science Foundation of China","award":["61572431,61602405,61836002,61751209"],"award-info":[{"award-number":["61572431,61602405,61836002,61751209"]}]},{"name":"Zhejiang Natural Science Foundation","award":["LR19F020002,LZ17F020001"],"award-info":[{"award-number":["LR19F020002,LZ17F020001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3351065","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"1193-1201","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":50,"title":["Multi-interaction Network with Object Relation for Video Question Answering"],"prefix":"10.1145","author":[{"given":"Weike","family":"Jin","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mao","family":"Gu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Xiao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_1_2_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E Hinton","author":"Ba Jimmy Lei","year":"2016"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"e_1_3_2_1_6_1","volume-title":"Structured Two-stream Attention Network for Video Question Answering. In AAAI Conference on Artificial Intelligence.","author":"Gao Lianli","year":"2019"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_9_1","volume-title":"Long short-term memory. Neural computation","author":"Hochreiter Sepp","year":"1997"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"e_1_3_2_1_13_1","unstructured":"Jin-Hwa Kim Sang-Woo Lee Donghyun Kwak Min-Oh Heo Jeonghee Kim Jung-Woo Ha and Byoung-Tak Zhang. 2016. Multimodal residual learning for visual qa. In Advances in Neural Information Processing Systems. 361--369.  Jin-Hwa Kim Sang-Woo Lee Donghyun Kwak Min-Oh Heo Jeonghee Kim Jung-Woo Ha and Byoung-Tak Zhang. 2016. Multimodal residual learning for visual qa. In Advances in Neural Information Processing Systems. 361--369."},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on Machine Learning. 1378--1387","author":"Kumar Ankit","year":"2016"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_3"},{"key":"e_1_3_2_1_16_1","volume-title":"Focal Visual-Text Attention for Visual Question Answering. In IEEE Conference on Computer Vision and Pattern Recognition. 6135--6143","author":"Liang Junwei","year":"2018"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.469"},{"key":"e_1_3_2_1_18_1","unstructured":"Jiasen Lu Jianwei Yang Dhruv Batra and Devi Parikh. 2016. Hierarchical question-image co-attention for visual question answering. In Advances in Neural Information Processing Systems. 289--297.  Jiasen Lu Jianwei Yang Dhruv Batra and Devi Parikh. 2016. Hierarchical question-image co-attention for visual question answering. In Advances in Neural Information Processing Systems. 289--297."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00710"},{"key":"e_1_3_2_1_20_1","unstructured":"Mateusz Malinowski and Mario Fritz. 2014. A multi-world approach to question answering about real-world scenes based on uncertain input. In Advances in Neural Information Processing Systems. 1682--1690.  Mateusz Malinowski and Mario Fritz. 2014. A multi-world approach to question answering about real-world scenes based on uncertain input. In Advances in Neural Information Processing Systems. 1682--1690."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.80"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_25_1","unstructured":"Mengye Ren Ryan Kiros and Richard Zemel. 2015. Exploring models and data for image question answering. In Advances in Neural Information Processing Systems. 2953--2961.  Mengye Ren Ryan Kiros and Richard Zemel. 2015. Exploring models and data for image question answering. In Advances in Neural Information Processing Systems. 2953--2961."},{"key":"e_1_3_2_1_26_1","unstructured":"Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in Neural Information Processing Systems. 91--99.  Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in Neural Information Processing Systems. 91--99."},{"key":"e_1_3_2_1_27_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014"},{"key":"e_1_3_2_1_28_1","volume-title":"Explore Multi- Step Reasoning in Video Question Answering. In ACM International Conference on Multimedia. 239--247","author":"Song Xiaomeng","year":"2018"},{"key":"e_1_3_2_1_29_1","unstructured":"Sainbayar Sukhbaatar JasonWeston Rob Fergus etal 2015. End-to-end memory networks. In Advances in Neural Information Processing Systems. 2440--2448.  Sainbayar Sukhbaatar JasonWeston Rob Fergus et al. 2015. End-to-end memory networks. In Advances in Neural Information Processing Systems. 2440--2448."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_32_1","volume-title":"ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017"},{"key":"e_1_3_2_1_33_1","volume-title":"International Conference on Machine Learning. 2397--2406","author":"Xiong Caiming","year":"2016"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.446"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.347"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"e_1_3_2_1_41_1","volume-title":"AAAI Conference on Artificial Intelligence. 4334--4340","author":"Zeng Kuo-Hao","year":"2017"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/512"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00674"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1033-7"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"}],"event":{"name":"MM '19: The 27th ACM International Conference on Multimedia","location":"Nice France","acronym":"MM '19","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 27th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351065","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3351065","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:12Z","timestamp":1750201992000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351065"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":45,"alternative-id":["10.1145\/3343031.3351065","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3351065","relation":{},"subject":[],"published":{"date-parts":[[2019,10,15]]},"assertion":[{"value":"2019-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}