{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T04:42:46Z","timestamp":1774500166512,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62376255"],"award-info":[{"award-number":["62376255"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755522","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:44:48Z","timestamp":1761371088000},"page":"5735-5744","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["EmoDETective: Detecting, Exploring, and Thinking Emotional Cause in Videos"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6629-5129","authenticated-orcid":false,"given":"Xuandong","family":"Huang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7021-4145","authenticated-orcid":false,"given":"Yuzhe","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3626-5493","authenticated-orcid":false,"given":"Jiashu","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0838-7996","authenticated-orcid":false,"given":"Shiqian","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1164-9895","authenticated-orcid":false,"given":"Shangfei","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-04114-8_26"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2396531"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123352"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 24185-24198","author":"Chen Zhe","year":"2024","unstructured":"Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, et al., 2024. Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 24185-24198."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3518"},{"key":"e_1_3_2_1_6_1","unstructured":"Zesen Cheng Sicong Leng Hang Zhang Yifei Xin Xin Li Guanzheng Chen Yongxin Zhu Wenqi Zhang Ziyang Luo Deli Zhao et al. 2024c. Videollama 2: Advancing spatial-temporal modeling and audio understanding in video-llms. arXiv preprint arXiv:2406.07476 (2024)."},{"key":"e_1_3_2_1_7_1","volume-title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs. arXiv preprint arXiv:2406.07476","author":"Cheng Zesen","year":"2024","unstructured":"Zesen Cheng, Sicong Leng, Hang Zhang, Yifei Xin, Xin Li, Guanzheng Chen, Yongxin Zhu, Wenqi Zhang, Ziyang Luo, Deli Zhao, and Lidong Bing. 2024b. VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs. arXiv preprint arXiv:2406.07476 (2024). https:\/\/arxiv.org\/abs\/2406.07476"},{"key":"e_1_3_2_1_8_1","volume-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models. arXiv preprint arXiv:2311.07919","author":"Chu Yunfei","year":"2023","unstructured":"Yunfei Chu, Jin Xu, Xiaohuan Zhou, Qian Yang, Shiliang Zhang, Zhijie Yan, Chang Zhou, and Jingren Zhou. 2023. Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models. arXiv preprint arXiv:2311.07919 (2023)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8724"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2017.9"},{"key":"e_1_3_2_1_11_1","unstructured":"Rui Li Xiaohan Wang Yuhui Zhang Zeyu Wang and Serena Yeung-Levy. 2025. Temporal Preference Optimization for Long-Form Video Understanding. arXiv:2501.13919 [cs.CV] https:\/\/arxiv.org\/abs\/2501.13919"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681631"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612836"},{"key":"e_1_3_2_1_14_1","unstructured":"Zheng Lian Haiyang Sun Licai Sun Hao Gu Zhuofan Wen Siyuan Zhang Shun Chen Mingyu Xu Ke Xu Kang Chen et al. 2023b. Explainable Multimodal Emotion Recognition. arXiv preprint arXiv:2306.15401 (2023)."},{"key":"e_1_3_2_1_15_1","volume-title":"Explainable Multimodal Emotion Reasoning. arXiv preprint arXiv:2306.15401","author":"Lian Zheng","year":"2023","unstructured":"Zheng Lian, Licai Sun, Mingyu Xu, Haiyang Sun, Ke Xu, Zhuofan Wen, Shun Chen, Bin Liu, and Jianhua Tao. 2023c. Explainable Multimodal Emotion Reasoning. arXiv preprint arXiv:2306.15401 (2023)."},{"key":"e_1_3_2_1_16_1","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2023. Visual Instruction Tuning."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2012.24"},{"key":"e_1_3_2_1_18_1","volume-title":"Viral video ads: Emotional triggers and social media virality. Psychology & marketing","author":"Nikolinakou Angeliki","year":"2018","unstructured":"Angeliki Nikolinakou and Karen Whitehill King. 2018. Viral video ads: Emotional triggers and social media virality. Psychology & marketing, Vol. 35, 10 (2018), 715-726."},{"key":"e_1_3_2_1_19_1","volume-title":"Accessing movies based on emotional impact. Multimedia systems","author":"Oliveira Eva","year":"2013","unstructured":"Eva Oliveira, Pedro Martins, and Teresa Chambel. 2013. Accessing movies based on emotional impact. Multimedia systems, Vol. 19 (2013), 559-576."},{"key":"e_1_3_2_1_20_1","unstructured":"OpenAI. [n.d.]. Hello GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/"},{"key":"e_1_3_2_1_21_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_22_1","unstructured":"Long Ouyang Jeff Wu Xu Jiang Diogo Almeida Carroll L. Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray John Schulman Jacob Hilton Fraser Kelton Luke Miller Maddie Simens Amanda Askell Peter Welinder Paul Christiano Jan Leike and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. arXiv:2203.02155 [cs.CL] https:\/\/arxiv.org\/abs\/2203.02155"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548018"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3032373"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.learninstruc.2013.02.006"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1511\/2001.28.344"},{"key":"e_1_3_2_1_27_1","volume-title":"Meld: A multimodal multi-party dataset for emotion recognition in conversations. arXiv preprint arXiv:1810.02508","author":"Poria Soujanya","year":"2018","unstructured":"Soujanya Poria, Devamanyu Hazarika, Navonil Majumder, Gautam Naik, Erik Cambria, and Rada Mihalcea. 2018. Meld: A multimodal multi-party dataset for emotion recognition in conversations. arXiv preprint arXiv:1810.02508 (2018)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/icme46284.2020.9102808"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.326"},{"key":"e_1_3_2_1_30_1","volume-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300","author":"Shao Zhihong","year":"2024","unstructured":"Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Y Wu, et al., 2024. Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2522848.2531741"},{"key":"e_1_3_2_1_32_1","volume-title":"Film structure and the emotion system","author":"Smith Greg M","unstructured":"Greg M Smith. 2003. Film structure and the emotion system. Cambridge University Press."},{"key":"e_1_3_2_1_33_1","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar Aurelien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. arXiv:2302.13971 [cs.CL] https:\/\/arxiv.org\/abs\/2302.13971"},{"key":"e_1_3_2_1_34_1","volume-title":"CMMR 2015","author":"Trochidis Konstantinos","year":"2016","unstructured":"Konstantinos Trochidis and Simon Lui. 2016. Modeling affective responses to music using audio signal analysis and physiology. In Music, Mind, and Embodiment: 11th International Symposium, CMMR 2015, Plymouth, UK, June 16-19, 2015, Revised Selected Papers 11. Springer, 346-357."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1037\/0096-3445.123.4.394"},{"key":"e_1_3_2_1_36_1","volume-title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. arXiv preprint arXiv:2409.12191","author":"Wang Peng","year":"2024","unstructured":"Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, and Junyang Lin. 2024a. Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_37_1","volume-title":"VAD: A Video Affective Dataset with Danmu","author":"Wang Shangfei","year":"2024","unstructured":"Shangfei Wang, Xin Li, Feiyi Zheng, Jicai Pan, Xuewei Li, Yanan Chang, Qiong Li, Jiahe Wang, Yufei Xiao, et al., 2024b. VAD: A Video Affective Dataset with Danmu. IEEE Transactions on Affective Computing (2024)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2912377"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-10203-1"},{"key":"e_1_3_2_1_40_1","volume-title":"On the acoustics of emotion in audio: what speech, music, and sound have in common. Frontiers in psychology","author":"Weninger Felix","year":"2013","unstructured":"Felix Weninger, Florian Eyben, Bj\u00f6rn W Schuller, Marcello Mortillaro, and Klaus R Scherer. 2013. On the acoustics of emotion in audio: what speech, music, and sound have in common. Frontiers in psychology, Vol. 4 (2013), 292."},{"key":"e_1_3_2_1_41_1","volume-title":"Color and emotion: effects of hue, saturation, and brightness. Psychological research","author":"Wilms Lisa","year":"2018","unstructured":"Lisa Wilms and Daniel Oberfeld. 2018. Color and emotion: effects of hue, saturation, and brightness. Psychological research, Vol. 82, 5 (2018), 896-914."},{"key":"e_1_3_2_1_42_1","volume-title":"Research on the application of deep learning-based BERT model in sentiment analysis. arXiv preprint arXiv:2403.08217","author":"Wu Yichao","year":"2024","unstructured":"Yichao Wu, Zhengyu Jin, Chenxi Shi, Penghao Liang, and Tong Zhan. 2024. Research on the application of deep learning-based BERT model in sentiment analysis. arXiv preprint arXiv:2403.08217 (2024)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2622690"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521500"},{"key":"e_1_3_2_1_45_1","volume-title":"arXiv preprint arXiv:2412.15115","author":"Yang An","year":"2024","unstructured":"An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, Keming Lu, Keqin Bao, Kexin Yang, Le Yu, Mei Li, Mingfeng Xue, Pei Zhang, Qin Zhu, Rui Men, Runji Lin, Tianhao Li, Tingyu Xia, Xingzhang Ren, Xuancheng Ren, Yang Fan, Yang Su, Yichang Zhang, Yu Wan, Yuqiong Liu, Zeyu Cui, Zhenru Zhang, and Zihan Qiu. 2024. Qwen2.5 Technical Report. arXiv preprint arXiv:2412.15115 (2024)."},{"key":"e_1_3_2_1_46_1","volume-title":"Rlaif-v: Aligning mllms through open-source ai feedback for super gpt-4v trustworthiness. arXiv preprint arXiv:2405.17220","author":"Yu Tianyu","year":"2024","unstructured":"Tianyu Yu, Haoye Zhang, Yuan Yao, Yunkai Dang, Da Chen, Xiaoman Lu, Ganqu Cui, Taiwen He, Zhiyuan Liu, Tat-Seng Chua, et al., 2024. Rlaif-v: Aligning mllms through open-source ai feedback for super gpt-4v trustworthiness. arXiv preprint arXiv:2405.17220 (2024)."},{"key":"e_1_3_2_1_47_1","unstructured":"Boqiang Zhang Kehan Li Zesen Cheng Zhiqiang Hu Yuqian Yuan Guanzheng Chen Sicong Leng Yuming Jiang Hang Zhang Xin Li et al. 2025. VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding. arXiv preprint arXiv:2501.13106 (2025)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3134167"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01811"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5364"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3363560"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755522","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:14:20Z","timestamp":1765307660000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755522"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":51,"alternative-id":["10.1145\/3746027.3755522","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755522","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}