{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:41:30Z","timestamp":1776886890871,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206193, 62376178"],"award-info":[{"award-number":["62206193, 62376178"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Grants Council, Hong Kong","award":["15611021"],"award-info":[{"award-number":["15611021"]}]},{"DOI":"10.13039\/501100012246","name":"Priority Academic Program Development of Jiangsu Higher Education Institutions","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012246","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755655","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:27:39Z","timestamp":1761377259000},"page":"5775-5783","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Emotion across Modalities and Cultures: Multilingual Multimodal Emotion-Cause Analysis with Memory-inspired Framework"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0017-511X","authenticated-orcid":false,"given":"Dan","family":"Wu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6183-8096","authenticated-orcid":false,"given":"Xincheng","family":"Ju","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8948-2856","authenticated-orcid":false,"given":"Dong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1000-3278","authenticated-orcid":false,"given":"Shoushan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3030-1280","authenticated-orcid":false,"given":"Erik","family":"Cambria","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7887-5099","authenticated-orcid":false,"given":"Guodong","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"38586","article-title":"Massively multilingual corpus of sentiment datasets and multi-faceted sentiment classification benchmark","volume":"36","author":"Augustyniak Lukasz","year":"2023","unstructured":"Lukasz Augustyniak, Szymon Wo\u017aniak, Marcin Gruza, Piotr Gramacki, Krzysztof Rajda, Miko\u0142aj Morzy, and Tomasz Kajdanowicz. 2023. Massively multilingual corpus of sentiment datasets and multi-faceted sentiment classification benchmark. Advances in Neural Information Processing Systems, Vol. 36 (2023), 38586-38610.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.wassa-1.18"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.34097\/jeicom-3-1-june21-1"},{"key":"e_1_3_2_1_4_1","first-page":"108","article-title":"Sentic Blending","author":"Cambria Erik","year":"2013","unstructured":"Erik Cambria, Newton Howard, Jane Hsu, and Amir Hussain. 2013. Sentic Blending: Scalable Multimodal Fusion for Continuous Interpretation of Semantics and Sentics. In IEEE SSCI. 108-117.","journal-title":"In IEEE SSCI."},{"key":"e_1_3_2_1_5_1","series-title":"Lecture Notes in Computer Science","volume-title":"Biometric ID Management and Multimodal Communication","author":"Cambria Erik","unstructured":"Erik Cambria, Amir Hussain, Catherine Havasi, and Chris Eckl. 2009. Common Sense Computing: From the Society of Mind to Digital Intuition and Beyond. In Biometric ID Management and Multimodal Communication. Lecture Notes in Computer Science, Vol. 5707. Springer, Berlin Heidelberg, 252-259."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 29th international conference on computational linguistics. 6752-6761","author":"Chauhan Dushyant Singh","year":"2022","unstructured":"Dushyant Singh Chauhan, Gopendra Vikram Singh, Aseem Arora, Asif Ekbal, and Pushpak Bhattacharyya. 2022. A sentiment and emotion aware multimodal multiparty humor recognition in multilingual conversational setting. In Proceedings of the 29th international conference on computational linguistics. 6752-6761."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29732"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3518"},{"key":"e_1_3_2_1_9_1","volume-title":"A coefficient of agreement for nominal scales. Educational and psychological measurement","author":"Cohen Jacob","year":"1960","unstructured":"Jacob Cohen. 1960. A coefficient of agreement for nominal scales. Educational and psychological measurement, Vol. 20, 1 (1960), 37-46."},{"key":"e_1_3_2_1_10_1","volume-title":"Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca. arXiv preprint arXiv:2304.08177","author":"Cui Yiming","year":"2023","unstructured":"Yiming Cui, Ziqing Yang, and Xin Yao. 2023. Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca. arXiv preprint arXiv:2304.08177 (2023). https:\/\/arxiv.org\/abs\/2304.08177"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.wassa-1.40"},{"key":"e_1_3_2_1_12_1","volume-title":"Qlora: Efficient finetuning of quantized llms. Advances in neural information processing systems","author":"Dettmers Tim","year":"2023","unstructured":"Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. 2023. Qlora: Efficient finetuning of quantized llms. Advances in neural information processing systems, Vol. 36 (2023), 10088-10115."},{"key":"e_1_3_2_1_13_1","first-page":"4171","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","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 4171-4186."},{"key":"e_1_3_2_1_14_1","volume-title":"High-context and low-context communication styles. Studiengang Informationsberufe","author":"Gamsriegler Angela","year":"2005","unstructured":"Angela Gamsriegler. 2005. High-context and low-context communication styles. Studiengang Informationsberufe; Information & Knowledge (2005)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-011-9101-8"},{"key":"e_1_3_2_1_16_1","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Alex Vaughan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_17_1","first-page":"13504","volume-title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024","author":"He Bo","year":"2024","unstructured":"Bo He, Hengduo Li, Young Kyun Jang, Menglin Jia, Xuefei Cao, Ashish Shah, Abhinav Shrivastava, and Ser-Nam Lim. 2024. MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, June 16-22, 2024. 13504-13514."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3525957"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3391854"},{"key":"e_1_3_2_1_20_1","volume-title":"UniMEEC: Towards Unified Multimodal Emotion Recognition and Emotion Cause. In Findings of the Association for Computational Linguistics: EMNLP","author":"Hu Guimin","year":"2024","unstructured":"Guimin Hu, Zhihong Zhu, Daniel Hershcovich, Lijie Hu, Hasti Seifi, and Jiayuan Xie. 2024b. UniMEEC: Towards Unified Multimodal Emotion Recognition and Emotion Cause. In Findings of the Association for Computational Linguistics: EMNLP 2024, Yaser Al-Onaizan, Mohit Bansal, and Yun-Nung Chen (Eds.). 5248-5261."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.240"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3543080"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681413"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1520-6793(199809)15:6<507::AID-MAR2>3.0.CO;2-A"},{"key":"e_1_3_2_1_25_1","volume-title":"Multimodal emotion-cause pair extraction with holistic interaction and label constraint. ACM Transactions on Multimedia Computing, Communications and Applications","author":"Li Bobo","year":"2024","unstructured":"Bobo Li, Hao Fei, Fei Li, Tat-seng Chua, and Donghong Ji. 2024a. Multimodal emotion-cause pair extraction with holistic interaction and label constraint. ACM Transactions on Multimedia Computing, Communications and Applications (2024)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.semeval-1.44"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.semeval-1.226"},{"key":"e_1_3_2_1_28_1","volume-title":"From extraction to generation: multimodal emotion-cause pair generation in conversations","author":"Ma Heqing","year":"2024","unstructured":"Heqing Ma, Jianfei Yu, Fanfan Wang, Hanyu Cao, and Rui Xia. 2024. From extraction to generation: multimodal emotion-cause pair generation in conversations. IEEE Transactions on Affective Computing (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"XED: A multilingual dataset for sentiment analysis and emotion detection. arXiv preprint arXiv:2011.01612","author":"\u00d6hman Emily","year":"2020","unstructured":"Emily \u00d6hman, Marc P\u00e0mies, Kaisla Kajava, and J\u00f6rg Tiedemann. 2020. XED: A multilingual dataset for sentiment analysis and emotion detection. arXiv preprint arXiv:2011.01612 (2020)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.632"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3226559"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681601"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.semeval-1.277"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.wassa-1.45"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-08328-z"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.semeval-1.53"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1083-6101.2006.tb00313.x"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.105"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350987"},{"key":"e_1_3_2_1_41_1","volume-title":"Video-llama: An instruction-tuned audio-visual language model for video understanding. arXiv preprint arXiv:2306.02858","author":"Zhang Hang","year":"2023","unstructured":"Hang Zhang, Xin Li, and Lidong Bing. 2023. Video-llama: An instruction-tuned audio-visual language model for video understanding. arXiv preprint arXiv:2306.02858 (2023)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3354382"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10651409"},{"key":"e_1_3_2_1_44_1","volume-title":"Exploring Interpretability in Deep Learning for Affective Computing: A Comprehensive Review. ACM Transactions on Multimedia Computing, Communications and Applications","author":"Zhang Xinjie","year":"2025","unstructured":"Xinjie Zhang, Tenggan Zhang, Lei Sun, Jinming Zhao, and Qin Jin. 2025. Exploring Interpretability in Deep Learning for Affective Computing: A Comprehensive Review. ACM Transactions on Multimedia Computing, Communications and Applications (2025)."}],"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\/3746027.3755655","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:57:24Z","timestamp":1765342644000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755655"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":44,"alternative-id":["10.1145\/3746027.3755655","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755655","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"}}]}}