{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:15:08Z","timestamp":1775578508541,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,8,24]],"date-time":"2021-08-24T00:00:00Z","timestamp":1629763200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972047"],"award-info":[{"award-number":["61972047"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFC0831500"],"award-info":[{"award-number":["2018YFC0831500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,8,24]]},"DOI":"10.1145\/3460426.3463634","type":"proceedings-article","created":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T22:50:28Z","timestamp":1630536628000},"page":"358-366","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Social Relation Analysis from Videos via Multi-entity Reasoning"],"prefix":"10.1145","author":[{"given":"Chenghao","family":"Yan","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"given":"Zihe","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"given":"Fangtao","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"given":"Chenyu","family":"Cao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"given":"Bin","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2021,9]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.365"},{"key":"e_1_3_2_1_3_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. 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. 2787--2795."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00415"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5646"},{"key":"e_1_3_2_1_7_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2018 . Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018). Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126306"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Yuan Fang Kingsley Kuan Jie Lin Cheston Tan and Vijay Chandrasekhar. 2017. Object detection meets knowledge graphs. (2017).  Yuan Fang Kingsley Kuan Jie Lin Cheston Tan and Vijay Chandrasekhar. 2017. Object detection meets knowledge graphs. (2017).","DOI":"10.24963\/ijcai.2017\/230"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00092"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01144"},{"key":"e_1_3_2_1_12_1","unstructured":"Roei Herzig Moshiko Raboh Gal Chechik Jonathan Berant and Amir Globerson. 2018. Mapping images to scene graphs with permutation-invariant structured prediction. In Advances in Neural Information Processing Systems. 7211--7221.  Roei Herzig Moshiko Raboh Gal Chechik Jonathan Berant and Amir Globerson. 2018. Mapping images to scene graphs with permutation-invariant structured prediction. In Advances in Neural Information Processing Systems. 7211--7221."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00106"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.564"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"e_1_3_2_1_16_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling . 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 ( 2016 ). Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00987"},{"key":"e_1_3_2_1_18_1","volume-title":"Frame Aggregation and Multi-Modal Fusion Framework for Video-Based Person Recognition. arXiv preprint arXiv:2010.09290","author":"Li Fangtao","year":"2020","unstructured":"Fangtao Li , Wenzhe Wang , Zihe Liu , Haoran Wang , Chenghao Yan , and Bin Wu. 2020. Frame Aggregation and Multi-Modal Fusion Framework for Video-Based Person Recognition. arXiv preprint arXiv:2010.09290 ( 2020 ). Fangtao Li, Wenzhe Wang, Zihe Liu, Haoran Wang, Chenghao Yan, and Bin Wu. 2020. Frame Aggregation and Multi-Modal Fusion Framework for Video-Based Person Recognition. arXiv preprint arXiv:2010.09290 (2020)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.289"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00368"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-73603-7_29"},{"key":"e_1_3_2_1_22_1","volume-title":"The more you know: Using knowledge graphs for image classification. arXiv preprint arXiv:1612.04844","author":"Marino Kenneth","year":"2016","unstructured":"Kenneth Marino , Ruslan Salakhutdinov , and Abhinav Gupta . 2016. The more you know: Using knowledge graphs for image classification. arXiv preprint arXiv:1612.04844 ( 2016 ). Kenneth Marino, Ruslan Salakhutdinov, and Abhinav Gupta. 2016. The more you know: Using knowledge graphs for image classification. arXiv preprint arXiv:1612.04844 (2016)."},{"key":"e_1_3_2_1_23_1","volume-title":"Learning attention-based embeddings for relation prediction in knowledge graphs. arXiv preprint arXiv:1906.01195","author":"Nathani Deepak","year":"2019","unstructured":"Deepak Nathani , Jatin Chauhan , Charu Sharma , and Manohar Kaul . 2019. Learning attention-based embeddings for relation prediction in knowledge graphs. arXiv preprint arXiv:1906.01195 ( 2019 ). Deepak Nathani, Jatin Chauhan, Charu Sharma, and Manohar Kaul. 2019. Learning attention-based embeddings for relation prediction in knowledge graphs. arXiv preprint arXiv:1906.01195 (2019)."},{"key":"e_1_3_2_1_24_1","volume-title":"Dat Quoc Nguyen, and Dinh Phung.","author":"Nguyen Dai Quoc","year":"2017","unstructured":"Dai Quoc Nguyen , Tu Dinh Nguyen , Dat Quoc Nguyen, and Dinh Phung. 2017 . A novel embedding model for knowledge base completion based on convolutional neural network. arXiv preprint arXiv:1712.02121 (2017). Dai Quoc Nguyen, Tu Dinh Nguyen, Dat Quoc Nguyen, and Dinh Phung. 2017. A novel embedding model for knowledge base completion based on convolutional neural network. arXiv preprint arXiv:1712.02121 (2017)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.332"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.320"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2826549"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0987-1"},{"key":"e_1_3_2_1_29_1","volume-title":"Vl-bert: Pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530","author":"Su Weijie","year":"2019","unstructured":"Weijie Su , Xizhou Zhu , Yue Cao , Bin Li , Lewei Lu , Furu Wei , and Jifeng Dai . 2019 . Vl-bert: Pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (2019). Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, and Jifeng Dai. 2019. Vl-bert: Pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (2019)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.54"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00513"},{"key":"e_1_3_2_1_33_1","volume-title":"Graph attention networks. arXiv preprint arXiv:1710.10903","author":"Cucurull Guillem","year":"2017","unstructured":"Guillem Cucurull , Arantxa Casanova , Adriana Romero , Pietro Lio , and Yoshua Bengio . 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 ( 2017 ). Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00895"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_37"},{"key":"e_1_3_2_1_37_1","volume-title":"Deep reasoning with knowledge graph for social relationship understanding. arXiv preprint arXiv:1807.00504","author":"Wang Zhouxia","year":"2018","unstructured":"Zhouxia Wang , Tianshui Chen , Jimmy Ren , Weihao Yu , Hui Cheng , and Liang Lin . 2018. Deep reasoning with knowledge graph for social relationship understanding. arXiv preprint arXiv:1807.00504 ( 2018 ). Zhouxia Wang, Tianshui Chen, Jimmy Ren, Weihao Yu, Hui Cheng, and Liang Lin. 2018. Deep reasoning with knowledge graph for social relationship understanding. arXiv preprint arXiv:1807.00504 (2018)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3001693"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206526"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01021"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.414"},{"key":"e_1_3_2_1_42_1","volume-title":"Asian Conference on Computer Vision. Springer, 35--50","author":"Zhong Yujie","year":"2018","unstructured":"Yujie Zhong , Relja Arandjelovi?, and Andrew Zisserman . 2018 . Ghostvlad for set-based face recognition . In Asian Conference on Computer Vision. Springer, 35--50 . Yujie Zhong, Relja Arandjelovi?, and Andrew Zisserman. 2018. Ghostvlad for set-based face recognition. In Asian Conference on Computer Vision. Springer, 35--50."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"}],"event":{"name":"ICMR '21: International Conference on Multimedia Retrieval","location":"Taipei Taiwan","acronym":"ICMR '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2021 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3460426.3463634","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3460426.3463634","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:17:03Z","timestamp":1750191423000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3460426.3463634"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,24]]},"references-count":43,"alternative-id":["10.1145\/3460426.3463634","10.1145\/3460426"],"URL":"https:\/\/doi.org\/10.1145\/3460426.3463634","relation":{},"subject":[],"published":{"date-parts":[[2021,8,24]]},"assertion":[{"value":"2021-09-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}