{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:35:16Z","timestamp":1750221316141,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,11,6]],"date-time":"2017-11-06T00:00:00Z","timestamp":1509926400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672133, 61502081, 61502080, 61632007"],"award-info":[{"award-number":["61672133, 61502081, 61502080, 61632007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental Research Funds for the Central Universities","award":["ZYGX2015J058, ZYGX2014Z007"],"award-info":[{"award-number":["ZYGX2015J058, ZYGX2014Z007"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,11,6]]},"DOI":"10.1145\/3132847.3132922","type":"proceedings-article","created":{"date-parts":[[2017,11,6]],"date-time":"2017-11-06T13:30:29Z","timestamp":1509975029000},"page":"1039-1048","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Movie Fill in the Blank with Adaptive Temporal Attention and Description Update"],"prefix":"10.1145","author":[{"given":"Jie","family":"Chen","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Shao","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fumin","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengkun","family":"He","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lianli","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2017,11,6]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"volume-title":"CVPR","year":"2015","author":"Chen Xinlei","key":"e_1_3_2_1_2_1"},{"volume-title":"Courville","year":"2016","author":"Cooijmans Tim","key":"e_1_3_2_1_3_1"},{"volume-title":"CVPR","year":"2015","author":"Donahue Jeff","key":"e_1_3_2_1_4_1"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"volume-title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding Conference on Empirical Methods in Natural Language Processing, EMNLP","year":"2016","author":"Fukui Akira","key":"e_1_3_2_1_6_1"},{"volume-title":"CVPR","year":"2015","author":"Gan Chuang","key":"e_1_3_2_1_7_1"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"volume-title":"Deep Residual Learning for Image Recognition. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR","year":"2016","author":"He Kaiming","key":"e_1_3_2_1_9_1"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"volume-title":"Compositional Memory for Visual Question Answering. CoRR","year":"2015","author":"Jiang Aiwen","key":"e_1_3_2_1_11_1"},{"volume-title":"Deep Fragment Embeddings for Bidirectional Image Sentence Mapping Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014. 1889","year":"2014","author":"Karpathy Andrej","key":"e_1_3_2_1_12_1"},{"volume-title":"Multimodal Residual Learning for Visual QA. In Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems","year":"2016","author":"Kim Jin-Hwa","key":"e_1_3_2_1_13_1"},{"volume-title":"CVPR","year":"2017","author":"Lu Jiasen","key":"e_1_3_2_1_14_1"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Lin Ma Zhengdong Lu and Hang Li. 2016. Learning to Answer Questions from Image Using Convolutional Neural Network Thirtieth AAAI Conference on Artificial Intelligence. 3567--3573.   Lin Ma Zhengdong Lu and Hang Li. 2016. Learning to Answer Questions from Image Using Convolutional Neural Network Thirtieth AAAI Conference on Artificial Intelligence. 3567--3573.","DOI":"10.1609\/aaai.v30i1.10442"},{"volume-title":"A dataset and exploration of models for understanding video data through fill-in-the-blank question-answering. CoRR","year":"2016","author":"Maharaj Tegan","key":"e_1_3_2_1_16_1"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"volume-title":"Video Fill in the Blank with Merging LSTMs. CoRR","year":"2016","author":"Mazaheri Amir","key":"e_1_3_2_1_18_1"},{"volume-title":"Efficient Estimation of Word Representations in Vector Space. CoRR","year":"2013","author":"Mikolov Tomas","key":"e_1_3_2_1_19_1"},{"volume-title":"Image Question Answering Using Convolutional Neural Network with Dynamic Parameter Prediction IEEE Conference on Computer Vision and Pattern Recognition, CVPR","year":"2016","author":"Noh Hyeonwoo","key":"e_1_3_2_1_20_1"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.117"},{"volume-title":"GCPR 2014, Proceedings. 184--195","year":"2014","author":"Rohrbach Anna","key":"e_1_3_2_1_22_1"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.61"},{"volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR","year":"2014","author":"Simonyan Karen","key":"e_1_3_2_1_24_1"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983771"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.335"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"volume-title":"The 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 1494--1504","year":"2015","author":"Venugopalan Subhashini","key":"e_1_3_2_1_28_1"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"e_1_3_2_1_30_1","series-title":"ACL","volume-title":"Short Papers. 707--712.","author":"Wang Di","year":"2015"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983777"},{"volume-title":"Dynamic Memory Networks for Visual and Textual Question Answering International Conference on Machine Learning, ICML","year":"2016","author":"Xiong Caiming","key":"e_1_3_2_1_32_1"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.31193\/ssap.01.9787509791011"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"volume-title":"Video Captioning and Retrieval Models with Semantic Attention. CoRR","year":"2016","author":"Yu Youngjae","key":"e_1_3_2_1_35_1"},{"volume-title":"Juan Carlos Niebles, and Min Sun","year":"2017","author":"Zeng Kuo-Hao","key":"e_1_3_2_1_36_1"},{"volume-title":"Simple Baseline for Visual Question Answering. CoRR","year":"2015","author":"Zhou Bolei","key":"e_1_3_2_1_37_1"},{"volume-title":"Hauptmann","year":"2015","author":"Zhu Linchao","key":"e_1_3_2_1_38_1"}],"event":{"name":"CIKM '17: ACM Conference on Information and Knowledge Management","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Singapore Singapore","acronym":"CIKM '17"},"container-title":["Proceedings of the 2017 ACM on Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3132847.3132922","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3132847.3132922","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:13:45Z","timestamp":1750212825000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3132847.3132922"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11,6]]},"references-count":38,"alternative-id":["10.1145\/3132847.3132922","10.1145\/3132847"],"URL":"https:\/\/doi.org\/10.1145\/3132847.3132922","relation":{},"subject":[],"published":{"date-parts":[[2017,11,6]]},"assertion":[{"value":"2017-11-06","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}