{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T17:10:10Z","timestamp":1750957810849,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,10,23]],"date-time":"2017-10-23T00:00:00Z","timestamp":1508716800000},"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":["61472281, 61622115"],"award-info":[{"award-number":["61472281, 61622115"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Program for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learnin","award":["GZ2015005"],"award-info":[{"award-number":["GZ2015005"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,10,23]]},"DOI":"10.1145\/3123266.3127895","type":"proceedings-article","created":{"date-parts":[[2017,10,20]],"date-time":"2017-10-20T13:04:26Z","timestamp":1508504666000},"page":"1871-1876","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Richer Semantic Visual and Language Representation for Video Captioning"],"prefix":"10.1145","author":[{"given":"Pengjie","family":"Tang","sequence":"first","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanli","family":"Wang","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanzhang","family":"Wang","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaisheng","family":"Xu","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2017,10,23]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments Association for Computational Linguistics Workshop. 65--72","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie . 2005 . METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments Association for Computational Linguistics Workshop. 65--72 . Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments Association for Computational Linguistics Workshop. 65--72."},{"key":"e_1_3_2_1_2_1","volume-title":"Long-Term Recurrent Convolutional Networks for Visual Recognition and Description IEEE Conference on Computer Vision and Pattern Recognition. 2625--2634","author":"Donahue Jeffrey","year":"2015","unstructured":"Jeffrey Donahue , Lisa Anne Hendricks , Sergio Guadarrama , Marcus Rohrbach , Subhashini Venugopalan , Kate Saenko , and Trevor Darrell . 2015 . Long-Term Recurrent Convolutional Networks for Visual Recognition and Description IEEE Conference on Computer Vision and Pattern Recognition. 2625--2634 . Jeffrey Donahue, Lisa Anne Hendricks, Sergio Guadarrama, Marcus Rohrbach, Subhashini Venugopalan, Kate Saenko, and Trevor Darrell. 2015. Long-Term Recurrent Convolutional Networks for Visual Recognition and Description IEEE Conference on Computer Vision and Pattern Recognition. 2625--2634."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984064"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"e_1_3_2_1_5_1","volume-title":"Deep Residual Learning for Image Recognition. In IEEE Conference on Computer Vision and Pattern Recognition. 770--778","author":"He Kaiming","year":"2016","unstructured":"Kaiming He , Xiangyu Zhang , Shaoqing Ren , and Jian Sun . 2016 . Deep Residual Learning for Image Recognition. In IEEE Conference on Computer Vision and Pattern Recognition. 770--778 . Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In IEEE Conference on Computer Vision and Pattern Recognition. 770--778."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_7_1","volume-title":"International Conference on Trustworthy Computing and Services. 163--169","author":"Huang Haiqi","year":"2012","unstructured":"Haiqi Huang , Yueming Lu , Fangwei Zhang , and Songlin Sun . 2012 . A Multi-Modal Clustering Method for Web Videos . In International Conference on Trustworthy Computing and Services. 163--169 . Haiqi Huang, Yueming Lu, Fangwei Zhang, and Songlin Sun. 2012. A Multi-Modal Clustering Method for Web Videos. In International Conference on Trustworthy Computing and Services. 163--169."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984065"},{"key":"e_1_3_2_1_9_1","volume-title":"Deep Visual-Semantic Alignments for Generating Image Descriptions IEEE Conference on Computer Vision and Pattern Recognition. 3128--3137","author":"Karpathy Andrej","year":"2015","unstructured":"Andrej Karpathy and Fei-Fei Li . 2015 . Deep Visual-Semantic Alignments for Generating Image Descriptions IEEE Conference on Computer Vision and Pattern Recognition. 3128--3137 . Andrej Karpathy and Fei-Fei Li. 2015. Deep Visual-Semantic Alignments for Generating Image Descriptions IEEE Conference on Computer Vision and Pattern Recognition. 3128--3137."},{"key":"e_1_3_2_1_10_1","volume-title":"Multimodal Neural Language Models. In International Conference on Machine Learning. 595--603","author":"Kiros Ryan","year":"2014","unstructured":"Ryan Kiros , Ruslan Salakhutdinov , and Rich Zemel . 2014 . Multimodal Neural Language Models. In International Conference on Machine Learning. 595--603 . Ryan Kiros, Ruslan Salakhutdinov, and Rich Zemel. 2014. Multimodal Neural Language Models. In International Conference on Machine Learning. 595--603."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Niveda Krishnamoorthy Girish Malkarnenkar Raymond Mooney Kate Saenko and Sergio Guadarrama. 2013. Generating Natural-Language Video Descriptions Using Text-Mined Knowledge The Association for the Advancement of Artificial Intelligence. Niveda Krishnamoorthy Girish Malkarnenkar Raymond Mooney Kate Saenko and Sergio Guadarrama. 2013. Generating Natural-Language Video Descriptions Using Text-Mined Knowledge The Association for the Advancement of Artificial Intelligence.","DOI":"10.1609\/aaai.v27i1.8679"},{"volume-title":"Automatic Evaluation of Machine Translation Quality Using Longest Common Subsequence and Skip-Bigram Statistics","author":"Lin Chin-Yew","key":"e_1_3_2_1_12_1","unstructured":"Chin-Yew Lin and Franz Josef Och . 2004. Automatic Evaluation of Machine Translation Quality Using Longest Common Subsequence and Skip-Bigram Statistics . In Association for Computational Linguistics . 21--26. Chin-Yew Lin and Franz Josef Och. 2004. Automatic Evaluation of Machine Translation Quality Using Longest Common Subsequence and Skip-Bigram Statistics. In Association for Computational Linguistics. 21--26."},{"volume-title":"Microsoft COCO: Common Objects in Context. In European Conference on Computer Vision. 740--755","author":"Lin Tsung-Yi","key":"e_1_3_2_1_13_1","unstructured":"Tsung-Yi Lin , Michael Maire , Serge Belongie , James Hays , Pietro Perona , Deva Ramanan , Piotr Doll\u00e1r , and C. Lawrence Zitnick . 2014 . Microsoft COCO: Common Objects in Context. In European Conference on Computer Vision. 740--755 . Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C. Lawrence Zitnick. 2014. Microsoft COCO: Common Objects in Context. In European Conference on Computer Vision. 740--755."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Pingbo Pan Zhongwen Xu Yi Yang Fei Wu and Yueting Zhuang. 2016 b. Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning IEEE Conference on Computer Vision and Pattern Recognition. 1029--1038. Pingbo Pan Zhongwen Xu Yi Yang Fei Wu and Yueting Zhuang. 2016 b. Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning IEEE Conference on Computer Vision and Pattern Recognition. 1029--1038.","DOI":"10.1109\/CVPR.2016.117"},{"key":"e_1_3_2_1_15_1","unstructured":"Yingwei Pan Tao Mei Ting Yao Houqiang Li and Yong Rui. 2016 a. Jointly Modeling Embedding and Translation to Bridge Video and Language IEEE Conference on Computer Vision and Pattern Recognition. 4594--4602. Yingwei Pan Tao Mei Ting Yao Houqiang Li and Yong Rui. 2016 a. Jointly Modeling Embedding and Translation to Bridge Video and Language IEEE Conference on Computer Vision and Pattern Recognition. 4594--4602."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_1_17_1","volume-title":"Zhe Gan, and Lawrence Carin.","author":"Pu Yunchen","year":"2016","unstructured":"Yunchen Pu , Martin Renqiang Min , Zhe Gan, and Lawrence Carin. 2016 . Adaptive Feature Abstraction for Translating Video to Language . arXiv preprint arXiv:1611.07837 (2016). Yunchen Pu, Martin Renqiang Min, Zhe Gan, and Lawrence Carin. 2016. Adaptive Feature Abstraction for Translating Video to Language. arXiv preprint arXiv:1611.07837 (2016)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984066"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_20_1","volume-title":"Weakly Supervised Dense Video Captioning. arXiv preprint arXiv:1704.01502","author":"Shen Zhiqiang","year":"2017","unstructured":"Zhiqiang Shen , Jianguo Li , Zhou Su , Minjun Li , Yurong Chen , Yu-Gang Jiang , and Xiangyang Xue . 2017. Weakly Supervised Dense Video Captioning. arXiv preprint arXiv:1704.01502 ( 2017 ). Zhiqiang Shen, Jianguo Li, Zhou Su, Minjun Li, Yurong Chen, Yu-Gang Jiang, and Xiangyang Xue. 2017. Weakly Supervised Dense Video Captioning. arXiv preprint arXiv:1704.01502 (2017)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984062"},{"key":"e_1_3_2_1_22_1","volume-title":"Going Deeper with Convolutions. In IEEE Conference on Computer Vision and Pattern Recognition. 1--9.","author":"Szegedy Christian","year":"2015","unstructured":"Christian Szegedy , Wei Liu , Yangqing Jia , Pierre Sermanet , Scott Reed , Dragomir Anguelov , Dumitru Erhan , Vincent Vanhoucke , and Andrew Rabinovich . 2015 . Going Deeper with Convolutions. In IEEE Conference on Computer Vision and Pattern Recognition. 1--9. Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. 2015. Going Deeper with Convolutions. In IEEE Conference on Computer Vision and Pattern Recognition. 1--9."},{"key":"e_1_3_2_1_23_1","volume-title":"CIDEr: Consensus-Based Image Description Evaluation IEEE Conference on Computer Vision and Pattern Recognition. 4566--4575","author":"Vedantam Ramakrishna","year":"2015","unstructured":"Ramakrishna Vedantam , C. Lawrence Zitnick , and Devi Parikh . 2015 . CIDEr: Consensus-Based Image Description Evaluation IEEE Conference on Computer Vision and Pattern Recognition. 4566--4575 . Ramakrishna Vedantam, C. Lawrence Zitnick, and Devi Parikh. 2015. CIDEr: Consensus-Based Image Description Evaluation IEEE Conference on Computer Vision and Pattern Recognition. 4566--4575."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"e_1_3_2_1_25_1","volume-title":"Show and Tell: A Neural Image Caption Generator. IEEE Conference on Computer Vision and Pattern Recognition. 3156--3164","author":"Vinyals Oriol","year":"2015","unstructured":"Oriol Vinyals , Alexander Toshev , Samy Bengio , and Dumitru Erhan . 2015 . Show and Tell: A Neural Image Caption Generator. IEEE Conference on Computer Vision and Pattern Recognition. 3156--3164 . Oriol Vinyals, Alexander Toshev, Samy Bengio, and Dumitru Erhan. 2015. Show and Tell: A Neural Image Caption Generator. IEEE Conference on Computer Vision and Pattern Recognition. 3156--3164."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.145"},{"key":"e_1_3_2_1_27_1","volume-title":"MSR-VTT: A Large Video Description Dataset for Bridging Video and Language IEEE Conference on Computer Vision and Pattern Recognition. 5288--5296","author":"Xu Jun","year":"2016","unstructured":"Jun Xu , Tao Mei , Ting Yao , and Yong Rui . 2016 . MSR-VTT: A Large Video Description Dataset for Bridging Video and Language IEEE Conference on Computer Vision and Pattern Recognition. 5288--5296 . Jun Xu, Tao Mei, Ting Yao, and Yong Rui. 2016. MSR-VTT: A Large Video Description Dataset for Bridging Video and Language IEEE Conference on Computer Vision and Pattern Recognition. 5288--5296."},{"key":"e_1_3_2_1_28_1","volume-title":"Image Captioning with Deep LSTM Based on Sequential Residual IEEE International Conference on Multimedia & Expo. 361--366","author":"Xu Kaisheng","year":"2017","unstructured":"Kaisheng Xu , Hanli Wang , and Pengjie Tang . 2017 . Image Captioning with Deep LSTM Based on Sequential Residual IEEE International Conference on Multimedia & Expo. 361--366 . Kaisheng Xu, Hanli Wang, and Pengjie Tang. 2017. Image Captioning with Deep LSTM Based on Sequential Residual IEEE International Conference on Multimedia & Expo. 361--366."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"}],"event":{"name":"MM '17: ACM Multimedia Conference","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Mountain View California USA","acronym":"MM '17"},"container-title":["Proceedings of the 25th ACM international conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3123266.3127895","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3123266.3127895","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T16:45:45Z","timestamp":1750956345000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3123266.3127895"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10,23]]},"references-count":29,"alternative-id":["10.1145\/3123266.3127895","10.1145\/3123266"],"URL":"https:\/\/doi.org\/10.1145\/3123266.3127895","relation":{},"subject":[],"published":{"date-parts":[[2017,10,23]]},"assertion":[{"value":"2017-10-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}