{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T16:28:29Z","timestamp":1793377709166,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":37,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3350971","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"1166-1174","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":60,"title":["Learnable Aggregating Net with Diversity Learning for Video Question Answering"],"prefix":"10.1145","author":[{"given":"Xiangpeng","family":"Li","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lianli","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanhan","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wu","family":"Liu","sequence":"additional","affiliation":[{"name":"AI Research of JD.COM, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"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","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018110"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123391"},{"key":"e_1_3_2_1_5_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018"},{"key":"e_1_3_2_1_6_1","volume-title":"Daylen Yang, Anna Rohrbach, Trevor Darrell, and Marcus Rohrbach.","author":"Fukui Akira","year":"2016"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.30"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.201"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2894139"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240687"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.41"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"e_1_3_2_1_15_1","unstructured":"Jin-Hwa Kim Jaehyun Jun and Byoung-Tak Zhang. 2018. Bilinear attention networks. In Advances in Neural Information Processing Systems .  Jin-Hwa Kim Jaehyun Jun and Byoung-Tak Zhang. 2018. Bilinear attention networks. In Advances in Neural Information Processing Systems ."},{"key":"e_1_3_2_1_16_1","unstructured":"Jin-Hwa Kim Sang-Woo Lee Donghyun Kwak Min-Oh Heo Jeonghee Kim Jung-Woo Ha and Byoung-Tak Zhang. 2016a. Multimodal residual learning for visual qa. In Advances in Neural Information Processing Systems .  Jin-Hwa Kim Sang-Woo Lee Donghyun Kwak Min-Oh Heo Jeonghee Kim Jung-Woo Ha and Byoung-Tak Zhang. 2016a. Multimodal residual learning for visual qa. In Advances in Neural Information Processing Systems ."},{"key":"e_1_3_2_1_17_1","volume-title":"Hadamard product for low-rank bilinear pooling. arXiv preprint arXiv:1610.04325","author":"Kim Jin-Hwa","year":"2016"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.3113\/JSOA.2018.0261"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00642"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00013"},{"key":"e_1_3_2_1_22_1","unstructured":"Jiasen Lu Jianwei Yang Dhruv Batra and Devi Parikh. 2016. Hierarchical Question-Image Co-Attention for Visual Question Answering.  Jiasen Lu Jianwei Yang Dhruv Batra and Devi Parikh. 2016. Hierarchical Question-Image Co-Attention for Visual Question Answering."},{"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":"10.1109\/CVPR.2018.00637"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition .","author":"Teney Damien"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition .","author":"Teney Damien"},{"key":"e_1_3_2_1_27_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems .  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems ."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.31193\/ssap.01.9787509752807"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080655"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.347"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision .","author":"Yu Z."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/492"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.145"}],"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\/3343031.3350971","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3350971","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:18Z","timestamp":1750201998000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3350971"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":37,"alternative-id":["10.1145\/3343031.3350971","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3350971","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"}}]}}