{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T16:44:32Z","timestamp":1793205872825,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":69,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Shenzhen Foundational Research Funding","award":["JCYJ20220818102415032"],"award-info":[{"award-number":["JCYJ20220818102415032"]}]},{"name":"The Major Key Project of PCL","award":["PCL2023A09"],"award-info":[{"award-number":["PCL2023A09"]}]},{"name":"Natural Science Foundation of Guangdong","award":["2023A1515012922"],"award-info":[{"award-number":["2023A1515012922"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176076"],"award-info":[{"award-number":["62176076"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies","award":["2022B1212010005k"],"award-info":[{"award-number":["2022B1212010005k"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681515","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T02:59:27Z","timestamp":1729911567000},"page":"9621-9630","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Multimodal Emotion Recognition Calibration in Conversations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8256-7049","authenticated-orcid":false,"given":"Geng","family":"Tu","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8316-5561","authenticated-orcid":false,"given":"Feng","family":"Xiong","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7234-1347","authenticated-orcid":false,"given":"Bin","family":"Liang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0499-727X","authenticated-orcid":false,"given":"Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0578-9328","authenticated-orcid":false,"given":"Xi","family":"Zeng","sequence":"additional","affiliation":[{"name":"The 30th Research Institute of China Electronics Technology Group Corporation, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4009-5679","authenticated-orcid":false,"given":"Ruifeng","family":"Xu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology & GD Prov. Key Lab. of Novel Security Intelligence Technologies, & Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"e_1_3_2_1_2_1","volume-title":"Electronic Conference on Foundations of Information Science: The nature of information: Conceptions, misconceptions, and paradoxes (FIS 2002","volume":"13","author":"Burgin M","year":"2002","unstructured":"M Burgin. 2002. The essence of information: Paradoxes, contradictions, and solutions. In Electronic Conference on Foundations of Information Science: The nature of information: Conceptions, misconceptions, and paradoxes (FIS 2002). Retrieved September, Vol. 13. Citeseer, 2013."},{"key":"e_1_3_2_1_3_1","first-page":"335","article-title":"IEMOCAP: Interactive emotional dyadic motion capture database","volume":"42","author":"Busso Carlos","year":"2008","unstructured":"Carlos Busso, Murtaza Bulut, Chi-Chun Lee, Abe Kazemzadeh, Emily Mower, Samuel Kim, Jeannette N Chang, Sungbok Lee, and Shrikanth S Narayanan. 2008. IEMOCAP: Interactive emotional dyadic motion capture database. LREC, Vol. 42, 4 (2008), 335--359.","journal-title":"LREC"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01036"},{"key":"e_1_3_2_1_5_1","unstructured":"Adam D Cobb and Brian Jalaian. 2021. Scaling Hamiltonian Monte Carlo inference for Bayesian neural networks with symmetric splitting. In Uncertainty in Artificial Intelligence. PMLR 675--685."},{"key":"e_1_3_2_1_6_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Corbi\u00e8re Charles","year":"2019","unstructured":"Charles Corbi\u00e8re, Nicolas Thome, Avner Bar-Hen, Matthieu Cord, and Patrick P\u00e9rez. 2019. Addressing failure prediction by learning model confidence. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_7_1","volume-title":"Transforming neural-net output levels to probability distributions. Advances in neural information processing systems","author":"Denker John","year":"1990","unstructured":"John Denker and Yann LeCun. 1990. Transforming neural-net output levels to probability distributions. Advances in neural information processing systems, Vol. 3 (1990)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"e_1_3_2_1_9_1","volume-title":"COSMIC: COmmonSense knowledge for eMotion identification in conversations. In Findings of EMNLP. 2470--2481.","author":"Ghosal Deepanway","year":"2020","unstructured":"Deepanway Ghosal, Navonil Majumder, Alexander Gelbukh, Rada Mihalcea, and Soujanya Poria. 2020. COSMIC: COmmonSense knowledge for eMotion identification in conversations. In Findings of EMNLP. 2470--2481."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Deepanway Ghosal Navonil Majumder Soujanya Poria Niyati Chhaya and Alexander Gelbukh. 2020. DialogueGCN: A graph convolutional neural network for emotion recognition in conversation. In EMNLP-IJCNLP.","DOI":"10.18653\/v1\/D19-1015"},{"key":"e_1_3_2_1_11_1","volume-title":"International conference on machine learning. PMLR, 1321--1330","author":"Guo Chuan","year":"2017","unstructured":"Chuan Guo, Geoff Pleiss, Yu Sun, and Kilian Q Weinberger. 2017. On calibration of modern neural networks. In International conference on machine learning. PMLR, 1321--1330."},{"key":"e_1_3_2_1_12_1","volume-title":"International Conference on Learning Representations.","author":"Gupta Kartik","year":"2020","unstructured":"Kartik Gupta, Amir Rahimi, Thalaiyasingam Ajanthan, Thomas Mensink, Cristian Sminchisescu, and Richard Hartley. 2020. Calibration of Neural Networks using Splines. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_13_1","unstructured":"Danijar Hafner Dustin Tran Timothy Lillicrap Alex Irpan and James Davidson. 2020. Noise contrastive priors for functional uncertainty. In Uncertainty in Artificial Intelligence. PMLR 905--914."},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on Learning Representations.","author":"Havasi Marton","year":"2020","unstructured":"Marton Havasi, Rodolphe Jenatton, Stanislav Fort, Jeremiah Zhe Liu, Jasper Snoek, Balaji Lakshminarayanan, Andrew Mingbo Dai, and Dustin Tran. 2020. Training independent subnetworks for robust prediction. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1280"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01561"},{"key":"e_1_3_2_1_17_1","volume-title":"International Conference on Learning Representations.","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_18_1","volume-title":"MM-DFN: Multimodal Dynamic Fusion Network for Emotion Recognition in Conversations","author":"Hu Dou","unstructured":"Dou Hu, Xiaolong Hou, Lingwei Wei, Lianxin Jiang, and Yang Mo. 2022. MM-DFN: Multimodal Dynamic Fusion Network for Emotion Recognition in Conversations. In ICASSP. IEEE, 7037--7041."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.547"},{"key":"e_1_3_2_1_20_1","volume-title":"MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation. In ACL. 5666--5675.","author":"Hu Jingwen","year":"2021","unstructured":"Jingwen Hu, Yuchen Liu, Jinming Zhao, and Qin Jin. 2021. MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation. In ACL. 5666--5675."},{"key":"e_1_3_2_1_21_1","volume-title":"Laurens Van Der Maaten, and Kilian Q Weinberger","author":"Huang Gao","year":"2017","unstructured":"Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q Weinberger. 2017. Densely connected convolutional networks. In CVPR. 4700--4708."},{"key":"e_1_3_2_1_22_1","volume-title":"AutoML-Emo: Automatic Knowledge Selection using Congruent Effect for Emotion Identification in Conversations","author":"Jiang Dazhi","year":"2022","unstructured":"Dazhi Jiang, Runguo Wei, Jintao Wen, Geng Tu, and Erik Cambria. 2022. AutoML-Emo: Automatic Knowledge Selection using Congruent Effect for Emotion Identification in Conversations. IEEE Transactions on Affective Computing (2022)."},{"key":"e_1_3_2_1_23_1","first-page":"17141","article-title":"Hierarchical gaussian process priors for bayesian neural network weights","volume":"33","author":"Karaletsos Theofanis","year":"2020","unstructured":"Theofanis Karaletsos and Thang D Bui. 2020. Hierarchical gaussian process priors for bayesian neural network weights. Advances in Neural Information Processing Systems, Vol. 33 (2020), 17141--17152.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_24_1","volume-title":"What uncertainties do we need in bayesian deep learning for computer vision? Advances in neural information processing systems","author":"Kendall Alex","year":"2017","unstructured":"Alex Kendall and Yarin Gal. 2017. What uncertainties do we need in bayesian deep learning for computer vision? Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_25_1","volume-title":"Telmo Silva Filho, and Peter Flach","author":"Kull Meelis","year":"2017","unstructured":"Meelis Kull, Telmo Silva Filho, and Peter Flach. 2017. Beta calibration: a well-founded and easily implemented improvement on logistic calibration for binary classifiers. In Artificial intelligence and statistics. PMLR, 623--631."},{"key":"e_1_3_2_1_26_1","volume-title":"Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in neural information processing systems","author":"Lakshminarayanan Balaji","year":"2017","unstructured":"Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell. 2017. Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.09.057"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00276"},{"key":"e_1_3_2_1_29_1","volume-title":"GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation","author":"Lian Zheng","year":"2023","unstructured":"Zheng Lian, Lan Chen, Licai Sun, Bin Liu, and Jianhua Tao. 2023. GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3049898"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00018"},{"key":"e_1_3_2_1_32_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_33_1","volume-title":"International Conference on Machine Learning. PMLR, 23429--23450","author":"Ma Huan","year":"2023","unstructured":"Huan Ma, Qingyang Zhang, Changqing Zhang, Bingzhe Wu, Huazhu Fu, Joey Tianyi Zhou, and Qinghua Hu. 2023. Calibrating multimodal learning. In International Conference on Machine Learning. PMLR, 23429--23450."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"e_1_3_2_1_35_1","first-page":"15682","article-title":"Revisiting the calibration of modern neural networks","volume":"34","author":"Minderer Matthias","year":"2021","unstructured":"Matthias Minderer, Josip Djolonga, Rob Romijnders, Frances Hubis, Xiaohua Zhai, Neil Houlsby, Dustin Tran, and Mario Lucic. 2021. Revisiting the calibration of modern neural networks. Advances in Neural Information Processing Systems, Vol. 34 (2021), 15682--15694.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_36_1","volume-title":"International conference on machine learning. PMLR, 2498--2507","author":"Molchanov Dmitry","year":"2017","unstructured":"Dmitry Molchanov, Arsenii Ashukha, and Dmitry Vetrov. 2017. Variational dropout sparsifies deep neural networks. In International conference on machine learning. PMLR, 2498--2507."},{"key":"e_1_3_2_1_37_1","volume-title":"international conference on machine learning. PMLR, 7034--7044","author":"Moon Jooyoung","year":"2020","unstructured":"Jooyoung Moon, Jihyo Kim, Younghak Shin, and Sangheum Hwang. 2020. Confidence-aware learning for deep neural networks. In international conference on machine learning. PMLR, 7034--7044."},{"key":"e_1_3_2_1_38_1","first-page":"15288","article-title":"Calibrating deep neural networks using focal loss","volume":"33","author":"Mukhoti Jishnu","year":"2020","unstructured":"Jishnu Mukhoti, Viveka Kulharia, Amartya Sanyal, Stuart Golodetz, Philip Torr, and Puneet Dokania. 2020. Calibrating deep neural networks using focal loss. Advances in Neural Information Processing Systems, Vol. 33 (2020), 15288--15299.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_39_1","volume-title":"When does label smoothing help? Advances in neural information processing systems","author":"M\u00fcller Rafael","year":"2019","unstructured":"Rafael M\u00fcller, Simon Kornblith, and Geoffrey E Hinton. 2019. When does label smoothing help? Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.937"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_42_1","volume-title":"International Conference on Learning Representations.","author":"Patel Kanil","year":"2020","unstructured":"Kanil Patel, William H Beluch, Bin Yang, Michael Pfeiffer, and Dan Zhang. 2020. Multi-Class Uncertainty Calibration via Mutual Information Maximization-based Binning. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_43_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_44_1","first-page":"13456","article-title":"Intra order-preserving functions for calibration of multi-class neural networks","volume":"33","author":"Rahimi Amir","year":"2020","unstructured":"Amir Rahimi, Amirreza Shaban, Ching-An Cheng, Richard Hartley, and Byron Boots. 2020. Intra order-preserving functions for calibration of multi-class neural networks. Advances in Neural Information Processing Systems, Vol. 33 (2020), 13456--13467.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17625"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.123"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127550"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.824"},{"key":"e_1_3_2_1_51_1","volume-title":"SSLCL: An Efficient Model-Agnostic Supervised Contrastive Learning Framework for Emotion Recognition in Conversations. arXiv preprint arXiv:2310.16676","author":"Shi Tao","year":"2023","unstructured":"Tao Shi, Xiao Liang, Yaoyuan Liang, Xinyi Tong, and Shao-Lun Huang. 2023. SSLCL: An Efficient Model-Agnostic Supervised Contrastive Learning Framework for Emotion Recognition in Conversations. arXiv preprint arXiv:2310.16676 (2023)."},{"key":"e_1_3_2_1_52_1","volume-title":"Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics. 751--759","author":"Spitkovsky Valentin I","year":"2010","unstructured":"Valentin I Spitkovsky, Hiyan Alshawi, and Dan Jurafsky. 2010. From baby steps to leapfrog: How ?less is more? in unsupervised dependency parsing. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics. 751--759."},{"key":"e_1_3_2_1_53_1","volume-title":"On mixup training: Improved calibration and predictive uncertainty for deep neural networks. Advances in neural information processing systems","author":"Thulasidasan Sunil","year":"2019","unstructured":"Sunil Thulasidasan, Gopinath Chennupati, Jeff A Bilmes, Tanmoy Bhattacharya, and Sarah Michalak. 2019. On mixup training: Improved calibration and predictive uncertainty for deep neural networks. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_54_1","volume-title":"Sentiment-Emotion-and Context-guided Knowledge Selection Framework for Emotion Recognition in Conversations","author":"Tu Geng","year":"2022","unstructured":"Geng Tu, Bin Liang, Dazhi Jiang, and Ruifeng Xu. 2022. Sentiment-Emotion-and Context-guided Knowledge Selection Framework for Emotion Recognition in Conversations. IEEE Transactions on Affective Computing (2022)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230537"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107598"},{"key":"e_1_3_2_1_57_1","first-page":"4555","article-title":"A survey on curriculum learning","volume":"44","author":"Wang Xin","year":"2021","unstructured":"Xin Wang, Yudong Chen, and Wenwu Zhu. 2021. A survey on curriculum learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, 9 (2021), 4555--4576.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.10.009"},{"key":"e_1_3_2_1_60_1","volume-title":"Combining Ensembles and Data Augmentation Can Harm Your Calibration. In International Conference on Learning Representations.","author":"Wen Yeming","year":"2020","unstructured":"Yeming Wen, Ghassen Jerfel, Rafael Muller, Michael W Dusenberry, Jasper Snoek, Balaji Lakshminarayanan, and Dustin Tran. 2020. Combining Ensembles and Data Augmentation Can Harm Your Calibration. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.417"},{"key":"e_1_3_2_1_62_1","volume-title":"International Conference on Learning Representations.","author":"Xing Chen","year":"2019","unstructured":"Chen Xing, Sercan Arik, Zizhao Zhang, and Tomas Pfister. 2019. Distance-Based Learning from Errors for Confidence Calibration. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"crossref","unstructured":"Haozhe Yang Xianqiang Gao Jianlong Wu Tian Gan Ning Ding Feijun Jiang and Liqiang Nie. 2023. Self-adaptive Context and Modal-interaction Modeling For Multimodal Emotion Recognition. In Findings of ACL. 6267--6281.","DOI":"10.18653\/v1\/2023.findings-acl.390"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01389"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413949"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.732"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.861"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01622"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_30"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681515","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681515","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T20:57:48Z","timestamp":1750280268000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681515"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":69,"alternative-id":["10.1145\/3664647.3681515","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681515","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}