{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T01:44:05Z","timestamp":1781487845820,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,10,19]],"date-time":"2017-10-19T00:00:00Z","timestamp":1508371200000},"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":[[2017,10,19]]},"DOI":"10.1145\/3123266.3123364","type":"proceedings-article","created":{"date-parts":[[2017,10,20]],"date-time":"2017-10-20T13:04:26Z","timestamp":1508504666000},"page":"1050-1058","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":35,"title":["Video Question Answering via Hierarchical Dual-Level Attention Network Learning"],"prefix":"10.1145","author":[{"given":"Zhou","family":"Zhao","sequence":"first","affiliation":[{"name":"Zhejiang University, Hang Zhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinghao","family":"Lin","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hang Zhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinghua","family":"Jiang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hang Zhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deng","family":"Cai","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hang Zhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofei","family":"He","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hang Zhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hang Zhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2017,10,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502215"},{"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","volume-title":"Delving deeper into convolutional networks for learning video representations. arXiv preprint arXiv:1511.06432","author":"Ballas N.","year":"2015"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654946"},{"key":"e_1_3_2_1_5_1","first-page":"3468","volume-title":"NIPS","author":"Feichtenhofer C.","year":"2016"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0893-6"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/253769.253798"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911489"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/1857999.1858085"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2011.53"},{"key":"e_1_3_2_1_14_1","volume-title":"Clevr: A diagnostic dataset for compositional language and elementary visual reasoning. arXiv preprint arXiv:1612.06890","author":"Johnson J.","year":"2016"},{"key":"e_1_3_2_1_15_1","volume-title":"NIPS","author":"Kim J.-H.","year":"2016"},{"key":"e_1_3_2_1_16_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma D.","year":"2014"},{"key":"e_1_3_2_1_17_1","first-page":"1097","volume-title":"NIPS","author":"Krizhevsky A.","year":"2012"},{"key":"e_1_3_2_1_18_1","first-page":"4655","volume-title":"NIPS","author":"Li R.","year":"2016"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.502"},{"key":"e_1_3_2_1_20_1","first-page":"289","volume-title":"NIPS","author":"Lu J.","year":"2016"},{"key":"e_1_3_2_1_21_1","first-page":"1682","volume-title":"NIPS","author":"Malinowski M.","year":"2014"},{"key":"e_1_3_2_1_22_1","volume-title":"Video fill in the blank with merging lstms. arXiv preprint arXiv:1610.04062","author":"Mazaheri A.","year":"2016"},{"key":"e_1_3_2_1_23_1","volume-title":"Visualization and thermodynamic encoding of single-molecule partition function projections. Nature communications, 6","author":"Palma C.-A.","year":"2015"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.117"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080767"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2699863"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"e_1_3_2_1_28_1","first-page":"568","volume-title":"NIPS","author":"Simonyan K.","year":"2014"},{"key":"e_1_3_2_1_29_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_30_1","first-page":"843","volume-title":"ICML","author":"Srivastava N.","year":"2015"},{"key":"e_1_3_2_1_31_1","first-page":"2440","volume-title":"NIPS","author":"Sukhbaatar S.","year":"2015"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"e_1_3_2_1_36_1","volume-title":"v. d. Hengel. Visual question answering: A survey of methods and datasets. arXiv preprint arXiv:1607.05910","author":"Wu Q.","year":"2016"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654931"},{"key":"e_1_3_2_1_38_1","first-page":"1603","article-title":"Dynamic memory networks for visual and textual question answering","author":"Xiong C.","year":"2016","journal-title":"ICML"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655069"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298789"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2602938"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080655"},{"key":"e_1_3_2_1_45_1","volume-title":"Leveraging video descriptions to learn video question answering. arXiv preprint arXiv:1611.04021","author":"Zeng K.-H.","year":"2016"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.331"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964308"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502093"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2015.2493537"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967201"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/492"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2014.2356461"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1033-7"}],"event":{"name":"MM '17: ACM Multimedia Conference","location":"Mountain View California USA","acronym":"MM '17","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 25th ACM international conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3123266.3123364","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3123266.3123364","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:14:03Z","timestamp":1750212843000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3123266.3123364"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10,19]]},"references-count":53,"alternative-id":["10.1145\/3123266.3123364","10.1145\/3123266"],"URL":"https:\/\/doi.org\/10.1145\/3123266.3123364","relation":{},"subject":[],"published":{"date-parts":[[2017,10,19]]},"assertion":[{"value":"2017-10-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}