{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T10:00:59Z","timestamp":1756461659384,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,25]],"date-time":"2020-10-25T00:00:00Z","timestamp":1603584000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","award":["JPMJCR1687"],"award-info":[{"award-number":["JPMJCR1687"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,25]]},"DOI":"10.1145\/3395035.3425639","type":"proceedings-article","created":{"date-parts":[[2020,12,28]],"date-time":"2020-12-28T05:36:27Z","timestamp":1609133787000},"page":"120-129","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep Video Understanding of Character Relationships in Movies"],"prefix":"10.1145","author":[{"given":"Yang","family":"Lu","sequence":"first","affiliation":[{"name":"Tokyo Institute of Technology, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Asri","family":"Rizki Yuliani","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keisuke","family":"Ishikawa","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ronaldo","family":"Prata Amorim","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roland","family":"Hartanto","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nakamasa","family":"Inoue","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kuniaki","family":"Uto","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Koichi","family":"Shinoda","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,12,27]]},"reference":[{"volume-title":"YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv preprint arXiv:2004.10934","year":"2020","author":"Bochkovskiy Alexey","key":"e_1_3_2_1_1_1"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"volume-title":"Moviescope: Large-scale analysis of movies using multiple modalities. arXiv preprint arXiv:1908.03180","year":"2019","author":"Cascante-Bonilla Paola","key":"e_1_3_2_1_3_1"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969304"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390742"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00198"},{"key":"e_1_3_2_1_8_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":"Devlin Jacob","year":"2019"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"volume-title":"End-to-end neural speaker diarization with selfattention. In 2019 IEEE Automatic Speech Recognition and UnderstandingWorkshop (ASRU)","author":"Fujita Yusuke","key":"e_1_3_2_1_10_1"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206828"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01144"},{"key":"e_1_3_2_1_14_1","unstructured":"Ken Harrenstien. 2009. Automatic captions in YouTube. In The Official Google Blog 11.  Ken Harrenstien. 2009. Automatic captions in YouTube. In The Official Google Blog 11."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2162"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00987"},{"volume-title":"Proceedings of the IEEE International Conference on Computer Vision. 2650--2659","year":"2017","author":"Li Junnan","key":"e_1_3_2_1_18_1"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01295-1"},{"volume-title":"Proceedings of ICLR'16","year":"2016","author":"Li Yujia","key":"e_1_3_2_1_20_1"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00368"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00190"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-73603-7_29"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2019EDP7104"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.10"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.556"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969250"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078610"},{"volume-title":"Hard: Some Experiences and Lessons Learned for the JHU Team in the Inaugural DIHARD Challenge.. In Interspeech. 2808--2812.","year":"2018","author":"Sell Gregory","key":"e_1_3_2_1_32_1"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1893"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_20"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.54"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00895"},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"33","author":"Wang Guangcong","year":"2019"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/3304415.3304560"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00841"},{"key":"e_1_3_2_1_44_1","unstructured":"Yuxin Wu Alexander Kirillov Francisco Massa Wan-Yen Lo and Ross Girshick. 2019. Detectron2. https:\/\/github.com\/facebookresearch\/detectron2.  Yuxin Wu Alexander Kirillov Francisco Massa Wan-Yen Lo and Ross Girshick. 2019. Detectron2. https:\/\/github.com\/facebookresearch\/detectron2."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299113"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953077"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.5555\/2919332.2919877"}],"event":{"name":"ICMI '20: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"],"location":"Virtual Event Netherlands","acronym":"ICMI '20"},"container-title":["Companion Publication of the 2020 International Conference on Multimodal Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3395035.3425639","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3395035.3425639","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3395035.3425639","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:02:47Z","timestamp":1750197767000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3395035.3425639"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,25]]},"references-count":47,"alternative-id":["10.1145\/3395035.3425639","10.1145\/3395035"],"URL":"https:\/\/doi.org\/10.1145\/3395035.3425639","relation":{},"subject":[],"published":{"date-parts":[[2020,10,25]]},"assertion":[{"value":"2020-12-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}