{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:40:49Z","timestamp":1765546849770,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2018B030312002"],"award-info":[{"award-number":["2018B030312002"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["NSFCU1811461"],"award-info":[{"award-number":["NSFCU1811461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Program of Guangdong Basic and Applied Research","award":["2019B030302002"],"award-info":[{"award-number":["2019B030302002"]}]},{"name":"National Key Research and Development Project","award":["2020AAA0106600"],"award-info":[{"award-number":["2020AAA0106600"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475638","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T06:21:10Z","timestamp":1634538070000},"page":"5213-5221","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Hybrid Reasoning Network for Video-based Commonsense Captioning"],"prefix":"10.1145","author":[{"given":"Weijiang","family":"Yu","sequence":"first","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Liang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Ji","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuejian","family":"Fang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nong","family":"Xiao","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nan","family":"Duan","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"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","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157196"},{"key":"e_1_3_2_2_3_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_4_1","volume-title":"Chaitanya Malaviya, Keisuke Sakaguchi, Ari Holtzman, Hannah Rashkin, Doug Downey, Wen-tau Yih, and Yejin Choi.","author":"Bhagavatula Chandra","year":"2020","unstructured":"Chandra Bhagavatula , Ronan Le Bras , Chaitanya Malaviya, Keisuke Sakaguchi, Ari Holtzman, Hannah Rashkin, Doug Downey, Wen-tau Yih, and Yejin Choi. 2020 . Abductive Commonsense Reasoning.. In ICLR. Chandra Bhagavatula, Ronan Le Bras, Chaitanya Malaviya, Keisuke Sakaguchi, Ari Holtzman, Hannah Rashkin, Doug Downey, Wen-tau Yih, and Yejin Choi. 2020. Abductive Commonsense Reasoning.. In ICLR."},{"key":"e_1_3_2_2_5_1","volume-title":"PIQA: Reasoning about Physical Commonsense in Natural Language.. In AAAI. 7432--7439.","author":"Bisk Yonatan","year":"2020","unstructured":"Yonatan Bisk , Rowan Zellers , Ronan LeBras , Jianfeng Gao , and Yejin Choi . 2020 . PIQA: Reasoning about Physical Commonsense in Natural Language.. In AAAI. 7432--7439. Yonatan Bisk, Rowan Zellers, Ronan LeBras, Jianfeng Gao, and Yejin Choi. 2020. PIQA: Reasoning about Physical Commonsense in Natural Language.. In AAAI. 7432--7439."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002497"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00479"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.61"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206492"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_2_16_1","volume-title":"Jeff Da, Keisuke Sakaguchi, Antoine Bosselut, and Yejin Choi.","author":"Hwang Jena D","year":"2020","unstructured":"Jena D Hwang , Chandra Bhagavatula , Ronan Le Bras , Jeff Da, Keisuke Sakaguchi, Antoine Bosselut, and Yejin Choi. 2020 . Comet-atomic 2020: On symbolic and neural commonsense knowledge graphs. arXiv preprint arXiv:2010.05953 (2020). Jena D Hwang, Chandra Bhagavatula, Ronan Le Bras, Jeff Da, Keisuke Sakaguchi, Antoine Bosselut, and Yejin Choi. 2020. Comet-atomic 2020: On symbolic and neural commonsense knowledge graphs. arXiv preprint arXiv:2010.05953 (2020)."},{"key":"e_1_3_2_2_17_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_18_1","volume-title":"TVQA: Spatio-temporal grounding for video question answering. In ACL.","author":"Lei Jie","year":"2019","unstructured":"Jie Lei , Licheng Yu , Tamara L Berg , and Mohit Bansal . 2019 . TVQA: Spatio-temporal grounding for video question answering. In ACL. Jie Lei, Licheng Yu, Tamara L Berg, and Mohit Bansal. 2019. TVQA: Spatio-temporal grounding for video question answering. In ACL."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.448"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.502"},{"key":"e_1_3_2_2_22_1","volume-title":"Rouge: A package for automatic evaluation of summaries. In 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 Text summarization branches out. 74--81. Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74--81."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.117"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_2_25_1","volume-title":"Automatic Differentiation in PyTorch. In NIPS 2017 Workshop on Autodiff","author":"Paszke Adam","year":"2017","unstructured":"Adam Paszke , Sam Gross , Soumith Chintala , Gregory Chanan , Edward Yang , Zachary DeVito , Zeming Lin , Alban Desmaison , Luca Antiga , and Adam Lerer . 2017 . Automatic Differentiation in PyTorch. In NIPS 2017 Workshop on Autodiff ( Long Beach, California, USA). https:\/\/openreview.net\/forum?id=BJJsrmfCZ Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic Differentiation in PyTorch. In NIPS 2017 Workshop on Autodiff (Long Beach, California, USA). https:\/\/openreview.net\/forum?id=BJJsrmfCZ"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.21236\/ADA612444"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11752-2_15"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"e_1_3_2_2_31_1","volume-title":"Atomic: An atlas of machine commonsense for if-then reasoning. In AAAI.","author":"Sap Maarten","year":"2018","unstructured":"Maarten Sap , Ronan LeBras , Emily Allaway , Chandra Bhagavatula , Nicholas Lourie , Hannah Rashkin , Brendan Roof , Noah A Smith , and Yejin Choi . 2018 . Atomic: An atlas of machine commonsense for if-then reasoning. In AAAI. Maarten Sap, Ronan LeBras, Emily Allaway, Chandra Bhagavatula, Nicholas Lourie, Hannah Rashkin, Brendan Roof, Noah A Smith, and Yejin Choi. 2018. Atomic: An atlas of machine commonsense for if-then reasoning. In AAAI."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1454"},{"key":"e_1_3_2_2_33_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Talmor Alon","year":"2019","unstructured":"Alon Talmor , Jonathan Herzig , Nicholas Lourie , and Jonathan Berant . 2019 . CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge . In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies , Volume 1 (Long and Short Papers). 4149--4158. Alon Talmor, Jonathan Herzig, Nicholas Lourie, and Jonathan Berant. 2019. CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 4149--4158."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_2_36_1","volume-title":"CIDEr: Consensus-based image description evaluation","author":"Vedantam Ramakrishna","year":"2015","unstructured":"Ramakrishna Vedantam , C. Lawrence Zitnick , and Devi Parikh . 2015. CIDEr: Consensus-based image description evaluation .. In CVPR. IEEE Computer Society , 4566--4575. http:\/\/dblp.uni-trier.de\/db\/conf\/cvpr\/cvpr 2015 .html#VedantamZP15 Ramakrishna Vedantam, C. Lawrence Zitnick, and Devi Parikh. 2015. CIDEr: Consensus-based image description evaluation.. In CVPR. IEEE Computer Society, 4566--4575. http:\/\/dblp.uni-trier.de\/db\/conf\/cvpr\/cvpr2015.html#VedantamZP15"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.327"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01077"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.597"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454536"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"}],"event":{"name":"MM '21: ACM Multimedia Conference","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Virtual Event China","acronym":"MM '21"},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475638","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475638","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:24Z","timestamp":1750193304000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475638"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":46,"alternative-id":["10.1145\/3474085.3475638","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475638","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}