{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:35:08Z","timestamp":1761060908213,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":47,"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\/3343031.3351060","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"818-826","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":24,"title":["Watch It Twice"],"prefix":"10.1145","author":[{"given":"Xiangxi","family":"Shi","sequence":"first","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}]},{"given":"Jianfei","family":"Cai","sequence":"additional","affiliation":[{"name":"Nanyang Technological University &amp; Monash University, Singapore, Singapore"}]},{"given":"Shafiq","family":"Joty","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}]},{"given":"Jiuxiang","family":"Gu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}]}],"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\/CVPR.2017.339"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967258"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002497"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"volume-title":"Thirty-Second AAAI Conference on Artificial Intelligence .","year":"2018","author":"Gu Jiuxiang","key":"e_1_3_2_1_8_1"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_31"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01042"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00207"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"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\/ICASSP.2017.7952132"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/2891460.2891535"},{"key":"e_1_3_2_1_17_1","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105.  Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00042"},{"volume-title":"Rouge: A package for automatic evaluation of summaries. In Text summarization branches out . 74--81.","year":"2004","author":"Lin Chin-Yew","key":"e_1_3_2_1_19_1"},{"volume-title":"Yu Mo, and Yoshua Bengio.","year":"2017","author":"Lin Zhouhan","key":"e_1_3_2_1_20_1"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2879642"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240667"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00013"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"volume-title":"Proceedings of the 40th annual meeting on association for computational linguistics. Association for Computational Linguistics, 311--318","year":"2002","author":"Papineni Kishore","key":"e_1_3_2_1_25_1"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1103"},{"volume-title":"Yusuke Miyao, and Shin'ichi Satoh.","year":"2017","author":"Phan Sang","key":"e_1_3_2_1_27_1"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.548"},{"volume-title":"Video Captioning with Boundary-aware Hierarchical Language Decoding and Joint Video Prediction. arXiv preprint arXiv:1807.03658","year":"2018","author":"Shi Xiangxi","key":"e_1_3_2_1_30_1"},{"volume-title":"International Conference on Learning Representations","year":"2014","author":"Simonyan Karen","key":"e_1_3_2_1_31_1"},{"volume-title":"Hierarchical lstm with adjusted temporal attention for video captioning. arXiv preprint arXiv:1706.01231","year":"2017","author":"Song Jingkuan","key":"e_1_3_2_1_32_1"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"volume-title":"Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers . 1218--1227","year":"2014","author":"Thomason Jesse","key":"e_1_3_2_1_34_1"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Ramakrishna Vedantam C. Lawrence Zitnick and Devi Parikh. 2015. CIDEr: Consensus-based image description evaluation. In Computer Vision and Pattern Recognition .  Ramakrishna Vedantam C. Lawrence Zitnick and Devi Parikh. 2015. CIDEr: Consensus-based image description evaluation. In Computer Vision and Pattern Recognition .","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"volume-title":"Translating videos to natural language using deep recurrent neural networks. arXiv preprint arXiv:1412.4729","year":"2014","author":"Venugopalan Subhashini","key":"e_1_3_2_1_38_1"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00784"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00443"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2125"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00714"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/164"}],"event":{"name":"MM '19: The 27th ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Nice France","acronym":"MM '19"},"container-title":["Proceedings of the 27th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351060","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3351060","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\/3343031.3351060"}},"subtitle":["Video Captioning with a Refocused Video Encoder"],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":47,"alternative-id":["10.1145\/3343031.3351060","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3351060","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"}}]}}