{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:48:41Z","timestamp":1775580521466,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":66,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475493","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T22:11:38Z","timestamp":1634595098000},"page":"3380-3389","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and Benchmark"],"prefix":"10.1145","author":[{"given":"Xun","family":"Gao","sequence":"first","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longjun","family":"Cai","sequence":"additional","affiliation":[{"name":"Alibaba Group, 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","unstructured":"[n.d.]. https:\/\/pyscenedetect.readthedocs.io\/en\/latest\/.  [n.d.]. https:\/\/pyscenedetect.readthedocs.io\/en\/latest\/."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2009.08.002"},{"key":"e_1_3_2_2_3_1","volume-title":"Deep Residual Learning for Image Recognition. In IEEE Conference on Computer Vision & Pattern Recognition."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/2906831.2906979"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01248"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-010-0182-0"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2396531"},{"key":"e_1_3_2_2_8_1","volume-title":"The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Benitez-Quiroz C. F."},{"key":"e_1_3_2_2_9_1","volume-title":"Acquisition of the Algorithms of Social Life: A Domain-Based Approach. Psychological Bulletin","author":"Blunt Bugental","year":"2000"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85099-1_8"},{"key":"e_1_3_2_2_11_1","unstructured":"Roddy Cowie Ellen Douglas-Cowie Susie Savvidou* Edelle McMahon Martin Sawey and Marc Schr\u00f6der. 2000. 'FEELTRACE': An instrument for recording perceived emotion in real time. In ISCA tutorial and research workshop (ITRW) on speech and emotion.  Roddy Cowie Ellen Douglas-Cowie Susie Savvidou* Edelle McMahon Martin Sawey and Marc Schr\u00f6der. 2000. 'FEELTRACE': An instrument for recording perceived emotion in real time. In ISCA tutorial and research workshop (ITRW) on speech and emotion."},{"key":"e_1_3_2_2_12_1","volume-title":"Emotional Intimacy: Overlooked Requirement for Survival","author":"Dahms Alan M.","year":"1972","edition":"1"},{"key":"e_1_3_2_2_13_1","volume-title":"A preliminary draft of this","author":"Rivera Joseph De","year":"1991"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"e_1_3_2_2_15_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2397456"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997638"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2522848.2531739"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130508"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2012.26"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37444-9_48"},{"key":"e_1_3_2_2_23_1","volume-title":"IEEE International Conference Workshops on Automatic Face and Gesture Recognition.","author":"Dhall A."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3264993"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2682899"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74889-2_43"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMARTCOMP.2017.7946996"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"A. C. Gallagher and T. Chen. 2009. Understanding images of groups of people. IEEE (2009).  A. C. Gallagher and T. Chen. 2009. Understanding images of groups of people. IEEE (2009).","DOI":"10.1109\/CVPR.2009.5206828"},{"key":"e_1_3_2_2_29_1","volume-title":"Calculation. https:\/\/www.statisticshowto.com\/inter-rater-reliability\/ Retrieved","author":"Glen Stephanie","year":"2006"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01144"},{"key":"e_1_3_2_2_31_1","volume-title":"Fahad Shahbaz Khan, and Mubarak Shah.","author":"Khan Salman","year":"2021"},{"key":"e_1_3_2_2_32_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01158-4"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/3143567.3143655"},{"key":"e_1_3_2_2_35_1","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Kukleva A."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01024"},{"key":"e_1_3_2_2_37_1","volume-title":"Parameter Efficient Multimodal Transformers for Video Representation Learning. arXiv preprint arXiv:2012.04124","author":"Lee Sangho","year":"2020"},{"key":"e_1_3_2_2_38_1","volume-title":"Soviet physics doklady","author":"Levenshtein Vladimir I"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.289"},{"key":"e_1_3_2_2_40_1","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Liu X.","year":"2019"},{"key":"e_1_3_2_2_41_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. arXiv preprint arXiv:1908.02265","author":"Lu Jiasen","year":"2019"},{"key":"e_1_3_2_2_42_1","volume-title":"Computer Vision Pattern Recognition Workshops.","author":"Lucey P."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-73603-7_29"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.5555\/520809.796143"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2013.130"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"crossref","unstructured":"T. Mittal P. Guhan U. Bhattacharya R. Chandra A. Bera and D. Manocha. 2020. EmotiCon: Context-Aware Multimodal Emotion Recognition using Frege's Principle.  T. Mittal P. Guhan U. Bhattacharya R. Chandra A. Bera and D. Manocha. 2020. EmotiCon: Context-Aware Multimodal Emotion Recognition using Frege's Principle.","DOI":"10.1109\/CVPR42600.2020.01424"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.188"},{"key":"e_1_3_2_2_49_1","volume-title":"Robust correlated and individual component analysis","author":"Panagakis Yannis","year":"2015"},{"key":"e_1_3_2_2_50_1","volume-title":"Proc IEEE International Conference on Multimedia & Expo.","author":"Pantic M."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2009.5349530"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACIIW.2019.8925231"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.54"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.111"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359996.3364268"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_4"},{"key":"e_1_3_2_2_60_1","volume-title":"Attention is all you need. arXiv preprint arXiv:1706.03762","author":"Vaswani Ashish","year":"2017"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00895"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01020"},{"key":"e_1_3_2_2_64_1","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).","author":"Zafeiriou S."},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"crossref","unstructured":"N. Zhang M. Paluri Y. Taigman R. Fergus and L. Bourdev. 2015. Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues. IEEE Computer Society (2015) 4804--4813.  N. Zhang M. Paluri Y. Taigman R. Fergus and L. Bourdev. 2015. Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues. IEEE Computer Society (2015) 4804--4813.","DOI":"10.1109\/CVPR.2015.7299113"},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"}],"event":{"name":"MM '21: ACM Multimedia Conference","location":"Virtual Event China","acronym":"MM '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475493","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475493","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:49:09Z","timestamp":1750193349000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475493"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":66,"alternative-id":["10.1145\/3474085.3475493","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475493","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"}}]}}