{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:08:56Z","timestamp":1750306136447,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":15,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,8,7]],"date-time":"2017-08-07T00:00:00Z","timestamp":1502064000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["61325009"],"award-info":[{"award-number":["61325009"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,8,7]]},"DOI":"10.1145\/3077136.3084144","type":"proceedings-article","created":{"date-parts":[[2017,7,28]],"date-time":"2017-07-28T19:35:01Z","timestamp":1501270501000},"page":"1341-1344","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Seeing Bot"],"prefix":"10.1145","author":[{"given":"Yingwei","family":"Pan","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaofan","family":"Qiu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Yao","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Mei","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2017,8,7]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Satanjeev Banerjee and Alon Lavie 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments ACL workshop.  Satanjeev Banerjee and Alon Lavie 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments ACL workshop."},{"volume-title":"Dolan","year":"2011","author":"Chen David L.","key":"e_1_3_2_1_2_1"},{"volume-title":"Sergio Guadarrama, Marcus Rohrbach, Subhashini Venugopalan, Kate Saenko, and Trevor Darrell.","year":"2015","author":"Donahue Jeffrey","key":"e_1_3_2_1_3_1"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"e_1_3_2_1_5_1","unstructured":"Andrea Frome Greg S. Corrado Jon Shlens Samy Bengio Jeff Dean Tomas Mikolov etal 2013. DeViSE: A Deep Visual-Semantic Embedding Model. NIPS.  Andrea Frome Greg S. Corrado Jon Shlens Samy Bengio Jeff Dean Tomas Mikolov et al. 2013. DeViSE: A Deep Visual-Semantic Embedding Model. NIPS."},{"key":"e_1_3_2_1_6_1","unstructured":"Yehao Li Ting Yao Tao Mei Hongyang Chao and Yong Rui 2016. Share-and-Chat: Achieving Human-Level Video Commenting by Search and Multi-View Embedding ACM MM.  Yehao Li Ting Yao Tao Mei Hongyang Chao and Yong Rui 2016. Share-and-Chat: Achieving Human-Level Video Commenting by Search and Multi-View Embedding ACM MM."},{"key":"e_1_3_2_1_7_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. ECCV.  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. ECCV."},{"key":"e_1_3_2_1_8_1","unstructured":"Yingwei Pan Tao Mei Ting Yao Houqiang Li and Yong Rui 2016. Jointly modeling embedding and translation to bridge video and language CVPR.  Yingwei Pan Tao Mei Ting Yao Houqiang Li and Yong Rui 2016. Jointly modeling embedding and translation to bridge video and language CVPR."},{"key":"e_1_3_2_1_9_1","unstructured":"Yingwei Pan Ting Yao Houqiang Li and Tao Mei. 2017. Video Captioning with Transferred Semantic Attributes CVPR.  Yingwei Pan Ting Yao Houqiang Li and Tao Mei. 2017. Video Captioning with Transferred Semantic Attributes CVPR."},{"key":"e_1_3_2_1_10_1","unstructured":"Yingwei Pan Ting Yao Tao Mei Houqiang Li Chong-Wah Ngo and Yong Rui. 2014. Click-through-based cross-view learning for image search SIGIR.  Yingwei Pan Ting Yao Tao Mei Houqiang Li Chong-Wah Ngo and Yong Rui. 2014. Click-through-based cross-view learning for image search SIGIR."},{"volume-title":"Le","year":"2014","author":"Sutskever Ilya","key":"e_1_3_2_1_11_1"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Subhashini Venugopalan Marcus Rohrbach Jeffrey Donahue Raymond Mooney Trevor Darrell and Kate Saenko 2015. Sequence to Sequence - Video to Text. In ICCV.  Subhashini Venugopalan Marcus Rohrbach Jeffrey Donahue Raymond Mooney Trevor Darrell and Kate Saenko 2015. Sequence to Sequence - Video to Text. In ICCV.","DOI":"10.1109\/ICCV.2015.515"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Oriol Vinyals Alexander Toshev Samy Bengio and Dumitru Erhan 2015. Show and Tell: A Neural Image Caption Generator. CVPR.  Oriol Vinyals Alexander Toshev Samy Bengio and Dumitru Erhan 2015. Show and Tell: A Neural Image Caption Generator. CVPR.","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Ting Yao Yingwei Pan Yehao Li and Tao Mei. 2017. Incorporating Copying Mechanism in Image Captioning for Learning Novel Objects CVPR.  Ting Yao Yingwei Pan Yehao Li and Tao Mei. 2017. Incorporating Copying Mechanism in Image Captioning for Learning Novel Objects CVPR.","DOI":"10.1109\/CVPR.2017.559"},{"volume-title":"Boosting image captioning with attributes. arXiv preprint arXiv:1611.01646","year":"2016","author":"Yao Ting","key":"e_1_3_2_1_15_1"}],"event":{"name":"SIGIR '17: The 40th International ACM SIGIR conference on research and development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Shinjuku Tokyo Japan","acronym":"SIGIR '17"},"container-title":["Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3077136.3084144","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3077136.3084144","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:37:19Z","timestamp":1750217839000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3077136.3084144"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,8,7]]},"references-count":15,"alternative-id":["10.1145\/3077136.3084144","10.1145\/3077136"],"URL":"https:\/\/doi.org\/10.1145\/3077136.3084144","relation":{},"subject":[],"published":{"date-parts":[[2017,8,7]]},"assertion":[{"value":"2017-08-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}