{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T05:23:36Z","timestamp":1755926616222,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T00:00:00Z","timestamp":1635206400000},"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":[[2021,10,26]]},"DOI":"10.1145\/3459637.3482018","type":"proceedings-article","created":{"date-parts":[[2021,10,30]],"date-time":"2021-10-30T18:34:11Z","timestamp":1635618851000},"page":"4594-4603","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["TrUMAn: Trope Understanding in Movies and Animations"],"prefix":"10.1145","author":[{"given":"Hung-Ting","family":"Su","sequence":"first","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Po-Wei","family":"Shen","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing-Chen","family":"Tsai","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen-Feng","family":"Cheng","sequence":"additional","affiliation":[{"name":"National Taiwan University & Microsoft, Taipei, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke-Jyun","family":"Wang","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Winston H.","family":"Hsu","sequence":"additional","affiliation":[{"name":"National Taiwan University & Mobile Drive Technology, Taipei, Taiwan Roc"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,30]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Humam Alwassel Dhruv Mahajan Bruno Korbar Lorenzo Torresani Bernard Ghanem and Du Tran. 2020. Self-Supervised Learning by Cross-Modal Audio-Video Clustering. In NeurIPS.  Humam Alwassel Dhruv Mahajan Bruno Korbar Lorenzo Torresani Bernard Ghanem and Du Tran. 2020. Self-Supervised Learning by Cross-Modal Audio-Video Clustering. In NeurIPS."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157196"},{"volume-title":"ICCV Workshops.","author":"Jasani R. Girdhar B.","key":"e_1_3_2_1_3_1"},{"volume-title":"From System 1 Deep Learning to System 2 Deep Learning. NeuripS","year":"2019","author":"Bengio Yoshua","key":"e_1_3_2_1_4_1"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449806"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002497"},{"volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.","year":"2019","author":"Devlin Jacob","key":"e_1_3_2_1_7_1"},{"key":"e_1_3_2_1_8_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep Residual Learning for Image Recognition.  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep Residual Learning for Image Recognition."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/1857999.1858085"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Deng Huang Peihao Chen Runhao Zeng Qing Du Mingkui Tan and Chuang Gan. 2020. Location-aware Graph Convolutional Networks for Video Question Answering. In AAAI.  Deng Huang Peihao Chen Runhao Zeng Qing Du Mingkui Tan and Chuang Gan. 2020. Location-aware Graph Convolutional Networks for Video Question Answering. In AAAI.","DOI":"10.1609\/aaai.v34i07.6737"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/3172077.3172168"},{"volume-title":"TVQA: Localized, Compositional Video Question Answering. In EMNLP.","year":"2018","author":"Lei Jie","key":"e_1_3_2_1_12_1"},{"volume-title":"Violin: A large-scale dataset for video-and-language inference. In CVPR.","year":"2020","author":"Liu Jingzhou","key":"e_1_3_2_1_13_1"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969250"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3127906"},{"volume-title":"MovieQA: Understanding Stories in Movies through Question-Answering","author":"Tapaswi Makarand","key":"e_1_3_2_1_16_1"},{"key":"e_1_3_2_1_17_1","unstructured":"Thomas Winterbottom Sarah Xiao Alistair McLean and Noura Al Moubayed. 2020. On Modality Bias in the TVQA Dataset. In BMVC.  Thomas Winterbottom Sarah Xiao Alistair McLean and Noura Al Moubayed. 2020. On Modality Bias in the TVQA Dataset. In BMVC."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Jun Xu Tao Mei Ting Yao and Yong Rui. 2016. MSR-VTT: A Large Video Description Dataset for Bridging Video and Language. In CVPR.  Jun Xu Tao Mei Ting Yao and Yong Rui. 2016. MSR-VTT: A Large Video Description Dataset for Bridging Video and Language. In CVPR.","DOI":"10.1109\/CVPR.2016.571"},{"volume-title":"Question Answering Bias Analysis on Video QA Datasets. In Human Multimodal Language Workshop.","year":"2020","author":"Yang Jianing","key":"e_1_3_2_1_21_1"},{"key":"e_1_3_2_1_22_1","unstructured":"Zhou Yu Dejing Xu Jun Yu Ting Yu Zhou Zhao Yueting Zhuang and Dacheng Tao. 2019. ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering. In AAAI.  Zhou Yu Dejing Xu Jun Yu Ting Yu Zhou Zhao Yueting Zhuang and Dacheng Tao. 2019. ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering. In AAAI."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298196"}],"event":{"name":"CIKM '21: The 30th ACM International Conference on Information and Knowledge Management","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Virtual Event Queensland Australia","acronym":"CIKM '21"},"container-title":["Proceedings of the 30th ACM International Conference on Information & Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3459637.3482018","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3459637.3482018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:11Z","timestamp":1750188611000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3459637.3482018"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,26]]},"references-count":23,"alternative-id":["10.1145\/3459637.3482018","10.1145\/3459637"],"URL":"https:\/\/doi.org\/10.1145\/3459637.3482018","relation":{},"subject":[],"published":{"date-parts":[[2021,10,26]]},"assertion":[{"value":"2021-10-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}