{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:36:13Z","timestamp":1773804973210,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,7,19]],"date-time":"2018-07-19T00:00:00Z","timestamp":1531958400000},"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":["61532010, 61702190"],"award-info":[{"award-number":["61532010, 61702190"]}]},{"name":"National Basic Research Program of China","award":["2014CB340505"],"award-info":[{"award-number":["2014CB340505"]}]},{"name":"Shanghai Sailing Program","award":["17YF1404500"],"award-info":[{"award-number":["17YF1404500"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,7,19]]},"DOI":"10.1145\/3219819.3220036","type":"proceedings-article","created":{"date-parts":[[2018,7,19]],"date-time":"2018-07-19T13:05:12Z","timestamp":1532005512000},"page":"1880-1889","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":55,"title":["R-VQA"],"prefix":"10.1145","author":[{"given":"Pan","family":"Lu","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Lei","family":"Ji","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia &Institute of Computing Technology, CAS, Beijing, China"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}]},{"given":"Nan","family":"Duan","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia &Microsoft Corporation, Beijing, China"}]},{"given":"Ming","family":"Zhou","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia &Microsoft Corporation, Beijing, China"}]},{"given":"Jianyong","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2018,7,19]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_2_2_1","volume-title":"Dbpedia: A nucleus for a web of open data. In The semantic web","author":"Auer S\u00f6ren","year":"2007"},{"key":"e_1_3_2_2_3_1","volume-title":"International Conference on Learning Representations (ICLR '14)","author":"Bahdanau Dzmitry","year":"2014"},{"key":"e_1_3_2_2_4_1","volume-title":"MUTAN: Multimodal Tucker Fusion for Visual Question Answering. In International Conference on Computer Vision (ICCV '17)","author":"Ben-Younes Hedi","year":"2017"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376746"},{"key":"e_1_3_2_2_6_1","unstructured":"Antoine Bordes Nicolas Usunier Alberto Garcia-Duran Jason Weston and Oksana Yakhnenko. 2013. Translating embeddings for modeling multi-relational data. In Advances in neural information processing systems (NIPS '13). 2787--2795.   Antoine Bordes Nicolas Usunier Alberto Garcia-Duran Jason Weston and Oksana Yakhnenko. 2013. Translating embeddings for modeling multi-relational data. In Advances in neural information processing systems (NIPS '13). 2787--2795."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_2_8_1","volume-title":"Daylen Yang, Anna Rohrbach, Trevor Darrell, and Marcus Rohrbach.","author":"Fukui Akira","year":"2016"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_2_11_1","volume-title":"A focused dynamic attention model for visual question answering. arXiv preprint arXiv:1604.01485","author":"Ilievski Ilija","year":"2016"},{"key":"e_1_3_2_2_12_1","volume-title":"Advances In Neural Information Processing Systems (NIPS '16)","author":"Kim Jin-Hwa","year":"2016"},{"key":"e_1_3_2_2_13_1","volume-title":"International Conference on Learning Representations (ICLR '17)","author":"Kim Jin-Hwa","year":"2017"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_2_15_1","volume-title":"Incorporating External Knowledge to Answer Open-Domain Visual Questions with Dynamic Memory Networks. arXiv preprint arXiv:1712.00733","author":"Li Guohao","year":"2017"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098115"},{"key":"e_1_3_2_2_17_1","volume-title":"Advances In Neural Information Processing Systems (NIPS '16)","author":"Li Ruiyu","year":"2016"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.766"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.469"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.02.005"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1048"},{"key":"e_1_3_2_2_22_1","volume-title":"Visual Relationship Detection with Language Priors. In European Conference on Computer Vision (ECCV '16)","author":"Lu Cewu","year":"2016"},{"key":"e_1_3_2_2_23_1","volume-title":"The AAAI Conference on Artificial Intelligence (AAAI'18)","author":"Lu Pan","year":"2018"},{"key":"e_1_3_2_2_24_1","volume-title":"The AAAI Conference on Artificial Intelligence (AAAI '16)","author":"Ma Lin","year":"2016"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.11"},{"key":"e_1_3_2_2_26_1","volume-title":"Advances In Neural Information Processing Systems (NIPS '16)","author":"Ren Mengye","year":"2015"},{"key":"e_1_3_2_2_27_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014"},{"key":"e_1_3_2_2_28_1","unstructured":"Richard Socher Danqi Chen Christopher D Manning and Andrew Ng. 2013. Reasoning with neural tensor networks for knowledge base completion. In Advances in neural information processing systems (NIPS '13). 926--934.   Richard Socher Danqi Chen Christopher D Manning and Andrew Ng. 2013. Reasoning with neural tensor networks for knowledge base completion. In Advances in neural information processing systems (NIPS '13). 926--934."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098096"},{"key":"e_1_3_2_2_30_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR '16)","author":"Wu Qi"},{"key":"e_1_3_2_2_31_1","volume-title":"Image Captioning and Visual Question Answering Based on Attributes and External Knowledge","author":"Wu Qi","year":"2017"},{"key":"e_1_3_2_2_32_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR '16)","author":"Wu Qi"},{"key":"e_1_3_2_2_33_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR '15)","author":"Xiao Tianjun","year":"2015"},{"key":"e_1_3_2_2_34_1","volume-title":"International Conference on Machine Learning (ICML '16)","author":"Xiong Caiming","year":"2016"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"e_1_3_2_2_36_1","volume-title":"International Conference on Machine Learning (ICML '15)","author":"Xu Kelvin","year":"2015"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1049"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"e_1_3_2_2_39_1","volume-title":"The 16th Annual Conference of the North American","author":"Yang Zichao"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.446"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939759"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186026"}],"event":{"name":"KDD '18: The 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","location":"London United Kingdom","acronym":"KDD '18","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3219819.3220036","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3219819.3220036","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:07:28Z","timestamp":1750212448000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3219819.3220036"}},"subtitle":["Learning Visual Relation Facts with Semantic Attention for Visual Question Answering"],"short-title":[],"issued":{"date-parts":[[2018,7,19]]},"references-count":43,"alternative-id":["10.1145\/3219819.3220036","10.1145\/3219819"],"URL":"https:\/\/doi.org\/10.1145\/3219819.3220036","relation":{},"subject":[],"published":{"date-parts":[[2018,7,19]]},"assertion":[{"value":"2018-07-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}