{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,27]],"date-time":"2025-12-27T10:05:52Z","timestamp":1766829952652,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0102000"],"award-info":[{"award-number":["2018AAA0102000"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62022083, U21B2038, 61931008 and 62102133"],"award-info":[{"award-number":["62022083, U21B2038, 61931008 and 62102133"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3548055","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:42:46Z","timestamp":1665416566000},"page":"4164-4174","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Inferential Visual Question Generation"],"prefix":"10.1145","author":[{"given":"Chao","family":"Bi","sequence":"first","affiliation":[{"name":"University of the Chinese Academy of Sciences; Institute of Computing Technology, Chinese Academy of Sciences, Beijing; Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuhui","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences; Peng Cheng Laboratory, Beijing; Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Xue","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengbo","family":"Chen","sequence":"additional","affiliation":[{"name":"Henan University, Kaifeng, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"University of the Chinese Academy of Sciences; Institute of Computing Technology, Chinese Academy of Sciences, Beijing; Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1203"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_2_5_1","volume-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization. 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 . In Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization. 65--72 . Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization. 65--72."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2831447"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_42"},{"key":"e_1_3_2_2_8_1","first-page":"1112","article-title":"Hierarchical LSTMs with adaptive attention for visual captioning","volume":"42","author":"Gao Lianli","year":"2019","unstructured":"Lianli Gao , Xiangpeng Li , Jingkuan Song , and Heng Tao Shen . 2019 . Hierarchical LSTMs with adaptive attention for visual captioning . IEEE Transactions on Pattern Analysis and Machine Intelligence , Vol. 42 , 5 (2019), 1112 -- 1131 . Lianli Gao, Xiangpeng Li, Jingkuan Song, and Heng Tao Shen. 2019. Hierarchical LSTMs with adaptive attention for visual captioning. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 42, 5 (2019), 1112--1131.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00161"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_32"},{"key":"e_1_3_2_2_12_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Hudson Drew A","year":"2018","unstructured":"Drew A Hudson and Christopher D Manning . 2018 . Compositional Attention Networks for Machine Reasoning . In Proceedings of the International Conference on Learning Representations. Drew A Hudson and Christopher D Manning. 2018. Compositional Attention Networks for Machine Reasoning. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.575"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"e_1_3_2_2_16_1","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Kai Shen","year":"2021","unstructured":"Shen Kai , Lingfei Wu , Siliang Tang , Yueting Zhuang , Zhuoye Ding , Yun Xiao , Bo Long , 2021 . Learning to Generate Visual Questions with Noisy Supervision . Advances in Neural Information Processing Systems , Vol. 34 (2021). Shen Kai, Lingfei Wu, Siliang Tang, Yueting Zhuang, Zhuoye Ding, Yun Xiao, Bo Long, et al. 2021. Learning to Generate Visual Questions with Noisy Supervision. Advances in Neural Information Processing Systems , Vol. 34 (2021)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00211"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30793-6_22"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00640"},{"key":"e_1_3_2_2_21_1","volume-title":"Proceedings of the ACL Workshop on Text Summarization Branches Out. 74--81","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin . 2004 . Rouge: A package for automatic evaluation of summaries . In Proceedings of the ACL Workshop on Text Summarization Branches Out. 74--81 . Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Proceedings of the ACL Workshop on Text Summarization Branches Out. 74--81."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2880185"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00898"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413924"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"e_1_3_2_2_26_1","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume":"29","author":"Lu Jiasen","year":"2016","unstructured":"Jiasen Lu , Jianwei Yang , Dhruv Batra , and Devi Parikh . 2016 b. Hierarchical question-image co-attention for visual question answering . Advances in Neural Information Processing Systems , Vol. 29 (2016), 289 -- 297 . Jiasen Lu, Jianwei Yang, Dhruv Batra, and Devi Parikh. 2016b. Hierarchical question-image co-attention for visual question answering. Advances in Neural Information Processing Systems , Vol. 29 (2016), 289--297.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1170"},{"key":"e_1_3_2_2_29_1","first-page":"2172","article-title":"Pixels to graphs by associative embedding","volume":"2017","author":"Newell Alejandro","year":"2017","unstructured":"Alejandro Newell and Jia Deng . 2017 . Pixels to graphs by associative embedding . Advances in Neural Information Processing Systems , Vol. 2017 (2017), 2172 -- 2181 . Alejandro Newell and Jia Deng. 2017. Pixels to graphs by associative embedding. Advances in Neural Information Processing Systems , Vol. 2017 (2017), 2172--2181.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.469"},{"key":"e_1_3_2_2_31_1","volume-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics. 311--318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni , Salim Roukos , Todd Ward , and Wei-Jing Zhu . 2002 . Bleu: a method for automatic evaluation of machine translation . In Proceedings of the Annual Meeting of the Association for Computational Linguistics. 311--318 . Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the Annual Meeting of the Association for Computational Linguistics. 311--318."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059923"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00681"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2851077"},{"key":"e_1_3_2_2_36_1","unstructured":"Kaihua Tang. 2020. A Scene Graph Generation Codebase in PyTorch. https:\/\/github.com\/KaihuaTang\/Scene-Graph-Benchmark.pytorch.  Kaihua Tang. 2020. A Scene Graph Generation Codebase in PyTorch. https:\/\/github.com\/KaihuaTang\/Scene-Graph-Benchmark.pytorch."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475390"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.05.001"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.500"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00403"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3476969"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486475"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2986029"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413761"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.03.005"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/592"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.5555\/2919332.2919877"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Lisboa Portugal","acronym":"MM '22"},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548055","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3548055","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:29Z","timestamp":1750186949000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548055"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":53,"alternative-id":["10.1145\/3503161.3548055","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3548055","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}