{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T17:46:47Z","timestamp":1787507207973,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":23,"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":["61572431"],"award-info":[{"award-number":["61572431"]}]},{"name":"National Natural Science Foundation of China","award":["61602405"],"award-info":[{"award-number":["61602405"]}]},{"name":"Fundamental Research Funds for the Central Universities","award":["2016QNA5015"],"award-info":[{"award-number":["2016QNA5015"]}]},{"name":"China Knowledge Centre for Engineering Sciences and Technology"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,8,7]]},"DOI":"10.1145\/3077136.3080655","type":"proceedings-article","created":{"date-parts":[[2017,7,28]],"date-time":"2017-07-28T15:35:01Z","timestamp":1501256101000},"page":"829-832","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":67,"title":["Video Question Answering via Attribute-Augmented Attention Network Learning"],"prefix":"10.1145","author":[{"given":"Yunan","family":"Ye","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yimeng","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Xiao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2017,8,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Vqa: Visual question answering. In ICCV. 2425--2433.","author":"Antol Stanislaw","year":"2015","unstructured":"Stanislaw Antol , Aishwarya Agrawal , Jiasen Lu , Margaret Mitchell , Dhruv Batra , C. Lawrence Zitnick , and Devi Parikh . 2015 . Vqa: Visual question answering. In ICCV. 2425--2433. Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv Batra, C. Lawrence Zitnick, and Devi Parikh. 2015. Vqa: Visual question answering. In ICCV. 2425--2433."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Sergio Guadarrama Niveda Krishnamoorthy Girish Malkarnenkar Subhashini Venugopalan Raymond Mooney Trevor Darrell and Kate Saenko. 2013. Youtube2text: Recognizing and describing arbitrary activities using semantic hierarchies and zero-shot recognition. In ICCV. 2712--2719. Sergio Guadarrama Niveda Krishnamoorthy Girish Malkarnenkar Subhashini Venugopalan Raymond Mooney Trevor Darrell and Kate Saenko. 2013. Youtube2text: Recognizing and describing arbitrary activities using semantic hierarchies and zero-shot recognition. In ICCV. 2712--2719.","DOI":"10.1109\/ICCV.2013.337"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/253769.253798"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2611584"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Xiangnan He Lizi Liao Hanwang Zhang Liqiang Nie Xia Hu and Tat-Seng Chua. 2017. Neural Collaborative Filtering. In WWW. 173--182. Xiangnan He Lizi Liao Hanwang Zhang Liqiang Nie Xia Hu and Tat-Seng Chua. 2017. Neural Collaborative Filtering. In WWW. 173--182.","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Xiangnan He Hanwang Zhang Min-Yen Kan and Tat-Seng Chua. 2016. Fast Matrix Factorization for Online Recommendation with Implicit Feedback SIGIR. 549--558. Xiangnan He Hanwang Zhang Min-Yen Kan and Tat-Seng Chua. 2016. Fast Matrix Factorization for Online Recommendation with Implicit Feedback SIGIR. 549--558.","DOI":"10.1145\/2911451.2911489"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Justin Johnson Andrej Karpathy and Li Fei-Fei. 2016. DenseCap: Fully Convolutional Localization Networks for Dense Captioning CVPR. Justin Johnson Andrej Karpathy and Li Fei-Fei. 2016. DenseCap: Fully Convolutional Localization Networks for Dense Captioning CVPR.","DOI":"10.1109\/CVPR.2016.494"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2495248"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2229971"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Liqiang Nie Meng Wang Zheng-Jun Zha Guangda Li and Tat-Seng Chua. 2011. Multimedia answering: enriching text QA with media information SIGIR. 695--704. Liqiang Nie Meng Wang Zheng-Jun Zha Guangda Li and Tat-Seng Chua. 2011. Multimedia answering: enriching text QA with media information SIGIR. 695--704.","DOI":"10.1145\/2009916.2010010"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Liqiang Nie Shuicheng Yan Meng Wang Richang Hong and Tat-Seng Chua. 2012. Harvesting visual concepts for image search with complex queries ACM MM. 59--68. Liqiang Nie Shuicheng Yan Meng Wang Richang Hong and Tat-Seng Chua. 2012. Harvesting visual concepts for image search with complex queries ACM MM. 59--68.","DOI":"10.1145\/2393347.2393363"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2185041"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2207397"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2015.2415497"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Zichao Yang Xiaodong He Jianfeng Gao Li Deng and Alex Smola. 2016. Stacked attention networks for image question answering CVPR. 21--29. Zichao Yang Xiaodong He Jianfeng Gao Li Deng and Alex Smola. 2016. Stacked attention networks for image question answering CVPR. 21--29.","DOI":"10.1109\/CVPR.2016.10"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2978656"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502093"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2015.2493537"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Zhou Zhao Hanqing Lu Vincent W. Zheng Deng Cai Xiaofei He and Yueting Zhuang. 2017. Community-Based Question Answering via Asymmetric Multi-Faceted Ranking Network Learning AAAI. 3532--3539. Zhou Zhao Hanqing Lu Vincent W. Zheng Deng Cai Xiaofei He and Yueting Zhuang. 2017. Community-Based Question Answering via Asymmetric Multi-Faceted Ranking Network Learning AAAI. 3532--3539.","DOI":"10.1609\/aaai.v31i1.10999"},{"key":"e_1_3_2_1_22_1","unstructured":"Zhou Zhao Qifan Yang Deng Cai Xiaofei He and Yueting Zhuang. 2016. Expert Finding for Community-Based Question Answering via Ranking Metric Network Learning. IJCAI. 3000--3006. Zhou Zhao Qifan Yang Deng Cai Xiaofei He and Yueting Zhuang. 2016. Expert Finding for Community-Based Question Answering via Ranking Metric Network Learning. IJCAI. 3000--3006."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2014.2356461"}],"event":{"name":"SIGIR '17: The 40th International ACM SIGIR conference on research and development in Information Retrieval","location":"Shinjuku Tokyo Japan","acronym":"SIGIR '17","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"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\/3077136.3080655","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3077136.3080655","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T14:42:23Z","timestamp":1750776143000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3077136.3080655"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,8,7]]},"references-count":23,"alternative-id":["10.1145\/3077136.3080655","10.1145\/3077136"],"URL":"https:\/\/doi.org\/10.1145\/3077136.3080655","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"}}]}}