{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T23:45:23Z","timestamp":1784591123517,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":47,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China (NSFC)","award":["No.62201572, No.61831022, No.62276259, No.62322120, No.U21B2010"],"award-info":[{"award-number":["No.62201572, No.61831022, No.62276259, No.62322120, No.U21B2010"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3689092.3689959","type":"proceedings-article","created":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T18:33:17Z","timestamp":1729708397000},"page":"41-48","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":28,"title":["MER 2024: Semi-Supervised Learning, Noise Robustness, and Open-Vocabulary Multimodal Emotion Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9477-0599","authenticated-orcid":false,"given":"Zheng","family":"Lian","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences (CAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3485-3869","authenticated-orcid":false,"given":"Haiyang","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of Automation, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7944-3458","authenticated-orcid":false,"given":"Licai","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of Automation, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3444-5641","authenticated-orcid":false,"given":"Zhuofan","family":"Wen","sequence":"additional","affiliation":[{"name":"Institute of Automation, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9366-5970","authenticated-orcid":false,"given":"Siyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Automation, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0097-2654","authenticated-orcid":false,"given":"Shun","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Automation, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0204-2875","authenticated-orcid":false,"given":"Hao","family":"Gu","sequence":"additional","affiliation":[{"name":"Institute of Automation, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4839-8850","authenticated-orcid":false,"given":"Jinming","family":"Zhao","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0623-9114","authenticated-orcid":false,"given":"Ziyang","family":"Ma","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7423-617X","authenticated-orcid":false,"given":"Xie","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2422-4618","authenticated-orcid":false,"given":"Jiangyan","family":"Yi","sequence":"additional","affiliation":[{"name":"Institute of Automation, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4308-645X","authenticated-orcid":false,"given":"Rui","family":"Liu","sequence":"additional","affiliation":[{"name":"Inner Mongolia University, Inner Mongolia, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5997-5169","authenticated-orcid":false,"given":"Kele","family":"Xu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9852-0551","authenticated-orcid":false,"given":"Bin","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Automation, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3030-1280","authenticated-orcid":false,"given":"Erik","family":"Cambria","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3694-206X","authenticated-orcid":false,"given":"Guoying","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Oulu, Oulu, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6478-8699","authenticated-orcid":false,"given":"Bj\u00f6rn W.","family":"Schuller","sequence":"additional","affiliation":[{"name":"Imperial College London, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0477-587X","authenticated-orcid":false,"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Merbench: A unified evaluation benchmark for multimodal emotion recognition. arXiv preprint arXiv:2401.03429","author":"Lian Zheng","year":"2024","unstructured":"Zheng Lian, Licai Sun, Yong Ren, Hao Gu, Haiyang Sun, Lan Chen, Bin Liu, and Jianhua Tao. Merbench: A unified evaluation benchmark for multimodal emotion recognition. arXiv preprint arXiv:2401.03429, 2024."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612836"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.277"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.50"},{"key":"e_1_3_2_1_6_1","article-title":"Efficient multimodal transformer with dual-level feature restoration for robust multimodal sentiment analysis","author":"Sun Licai","year":"2023","unstructured":"Licai Sun, Zheng Lian, Bin Liu, and Jianhua Tao. Efficient multimodal transformer with dual-level feature restoration for robust multimodal sentiment analysis. IEEE Transactions on Affective Computing, 2023.","journal-title":"IEEE Transactions on Affective Computing"},{"issue":"07","key":"e_1_3_2_1_7_1","first-page":"8419","article-title":"Graph completion network for incomplete multimodal learning in conversation","volume":"45","author":"Lian Zheng","year":"2023","unstructured":"Zheng Lian, Lan Chen, Licai Sun, Bin Liu, and Jianhua Tao. Gcnet: Graph completion network for incomplete multimodal learning in conversation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(07):8419--8432, 2023.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_8_1","volume-title":"Musan: A music, speech, and noise corpus. arXiv preprint arXiv:1510.08484","author":"Snyder David","year":"2015","unstructured":"David Snyder, Guoguo Chen, and Daniel Povey. Musan: A music, speech, and noise corpus. arXiv preprint arXiv:1510.08484, 2015."},{"key":"e_1_3_2_1_9_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. Explainable multimodal emotion reasoning. arXiv preprint arXiv:2306.15401, 2023."},{"key":"e_1_3_2_1_10_1","first-page":"10078","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Tong Zhan","year":"2022","unstructured":"Zhan Tong, Yibing Song, Jue Wang, and Limin Wang. Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. In Proceedings of the Advances in Neural Information Processing Systems, pages 10078--10093, 2022."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-015-0195-2"},{"key":"e_1_3_2_1_12_1","volume-title":"Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193","author":"Oquab Maxime","year":"2023","unstructured":"Maxime Oquab, Timoth\u00e9e Darcet, Th\u00e9o Moutakanni, Huy Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El-Nouby, et al. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193, 2023."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3093397"},{"key":"e_1_3_2_1_16_1","volume-title":"Eva-02: A visual representation for neon genesis. arXiv preprint arXiv:2303.11331","author":"Fang Yuxin","year":"2023","unstructured":"Yuxin Fang, Quan Sun, Xinggang Wang, Tiejun Huang, Xinlong Wang, and Yue Cao. Eva-02: A visual representation for neon genesis. arXiv preprint arXiv:2303.11331, 2023."},{"key":"e_1_3_2_1_17_1","first-page":"8748","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. Learning transferable visual models from natural language supervision. In Proceedings of the International Conference on Machine Learning, pages 8748--8763. PMLR, 2021."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"e_1_3_2_1_20_1","first-page":"28492","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. Robust speech recognition via large-scale weak supervision. In Proceedings of the International Conference on Machine Learning, pages 28492-- 28518. PMLR, 2023."},{"key":"e_1_3_2_1_21_1","volume-title":"emotion2vec: Self-supervised pre-training for speech emotion representation. arXiv preprint arXiv:2312.15185","author":"Ma Ziyang","year":"2023","unstructured":"Ziyang Ma, Zhisheng Zheng, Jiaxin Ye, Jinchao Li, Zhifu Gao, Shiliang Zhang, and Xie Chen. emotion2vec: Self-supervised pre-training for speech emotion representation. arXiv preprint arXiv:2312.15185, 2023."},{"key":"e_1_3_2_1_22_1","first-page":"12449","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. wav2vec 2.0: A framework for self-supervised learning of speech representations. In Proceedings of the Advances in Neural Information Processing Systems, pages 12449--12460, 2020."},{"key":"e_1_3_2_1_23_1","volume-title":"Hubert: Self-supervised speech representation learning by masked prediction of hidden units","author":"Hsu Wei-Ning","year":"2021","unstructured":"Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai, Kushal Lakhotia, Ruslan Salakhutdinov, and Abdelrahman Mohamed. Hubert: Self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 29:3451--3460, 2021."},{"key":"e_1_3_2_1_24_1","first-page":"5754","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Yang Zhilin","year":"2019","unstructured":"Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Russ R Salakhutdinov, and Quoc V Le. Xlnet: Generalized autoregressive pretraining for language understanding. Proceedings of the Advances in Neural Information Processing Systems, pages 5754--5764, 2019."},{"key":"e_1_3_2_1_25_1","first-page":"1","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Clark Kevin","year":"2020","unstructured":"Kevin Clark, Minh-Thang Luong, Quoc V Le, and Christopher D Manning. Electra: Pre-training text encoders as discriminators rather than generators. In Proceedings of the International Conference on Learning Representations, pages 1--18, 2020."},{"key":"e_1_3_2_1_26_1","volume-title":"Pert: pre-training bert with permuted language model. arXiv preprint arXiv:2203.06906","author":"Cui Yiming","year":"2022","unstructured":"Yiming Cui, Ziqing Yang, and Ting Liu. Pert: pre-training bert with permuted language model. arXiv preprint arXiv:2203.06906, 2022."},{"key":"e_1_3_2_1_27_1","volume-title":"Lert: A linguisticallymotivated pre-trained language model. arXiv preprint arXiv:2211.05344","author":"Cui Yiming","year":"2022","unstructured":"Yiming Cui, Wanxiang Che, Shijin Wang, and Ting Liu. Lert: A linguisticallymotivated pre-trained language model. arXiv preprint arXiv:2211.05344, 2022."},{"key":"e_1_3_2_1_28_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. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692, 2019."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.58"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"e_1_3_2_1_31_1","unstructured":"BigScience Workshop Teven Le Scao Angela Fan Christopher Akiki Ellie Pavlick Suzana Ili? Daniel Hesslow Roman Castagn\u00e9 Alexandra Sasha Luccioni Fran\u00e7ois Yvon et al. Bloom: A 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100 2022."},{"key":"e_1_3_2_1_32_1","volume-title":"Baichuan 2: Open large-scale language models. arXiv preprint arXiv:2309.10305","author":"Yang Aiyuan","year":"2023","unstructured":"Aiyuan Yang, Bin Xiao, Bingning Wang, Borong Zhang, Ce Bian, Chao Yin, Chenxu Lv, Da Pan, Dian Wang, Dong Yan, et al. Baichuan 2: Open large-scale language models. arXiv preprint arXiv:2309.10305, 2023."},{"key":"e_1_3_2_1_33_1","volume-title":"Ctnet: Conversational transformer network for emotion recognition","author":"Lian Zheng","year":"2021","unstructured":"Zheng Lian, Bin Liu, and Jianhua Tao. Ctnet: Conversational transformer network for emotion recognition. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 29:985--1000, 2021."},{"key":"e_1_3_2_1_34_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. 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_35_1","volume-title":"Onellm: One framework to align all modalities with language. arXiv preprint arXiv:2312.03700","author":"Han Jiaming","year":"2023","unstructured":"Jiaming Han, Kaixiong Gong, Yiyuan Zhang, Jiaqi Wang, Kaipeng Zhang, Dahua Lin, Yu Qiao, Peng Gao, and Xiangyu Yue. Onellm: One framework to align all modalities with language. arXiv preprint arXiv:2312.03700, 2023."},{"key":"e_1_3_2_1_36_1","volume-title":"Otter: A multi-modal model with in-context instruction tuning. arXiv preprint arXiv:2305.03726","author":"Li Bo","year":"2023","unstructured":"Bo Li, Yuanhan Zhang, Liangyu Chen, Jinghao Wang, Jingkang Yang, and Ziwei Liu. Otter: A multi-modal model with in-context instruction tuning. arXiv preprint arXiv:2305.03726, 2023."},{"key":"e_1_3_2_1_37_1","volume-title":"Video-llama: An instruction-tuned audiovisual language model for video understanding. arXiv preprint arXiv:2306.02858","author":"Zhang Hang","year":"2023","unstructured":"Hang Zhang, Xin Li, and Lidong Bing. Video-llama: An instruction-tuned audiovisual language model for video understanding. arXiv preprint arXiv:2306.02858, 2023."},{"key":"e_1_3_2_1_38_1","volume-title":"Videochat: Chat-centric video understanding. arXiv preprint arXiv:2305.06355","author":"Li KunChang","year":"2023","unstructured":"KunChang Li, Yinan He, YiWang, Yizhuo Li,WenhaiWang, Ping Luo, YaliWang, Limin Wang, and Yu Qiao. Videochat: Chat-centric video understanding. arXiv preprint arXiv:2305.06355, 2023."},{"key":"e_1_3_2_1_39_1","first-page":"11","volume-title":"Proceedings of the 1st Workshop on Taming Large Language Models: Controllability in the era of Interactive Assistants","author":"Su Yixuan","year":"2023","unstructured":"Yixuan Su, Tian Lan, Huayang Li, Jialu Xu, Yan Wang, and Deng Cai. Pandagpt: One model to instruction-follow them all. In Proceedings of the 1st Workshop on Taming Large Language Models: Controllability in the era of Interactive Assistants, pages 11--23, 2023."},{"key":"e_1_3_2_1_40_1","volume-title":"Video-llava: Learning united visual representation by alignment before projection. arXiv preprint arXiv:2311.10122","author":"Lin Bin","year":"2023","unstructured":"Bin Lin, Bin Zhu, Yang Ye, Munan Ning, Peng Jin, and Li Yuan. Video-llava: Learning united visual representation by alignment before projection. arXiv preprint arXiv:2311.10122, 2023."},{"key":"e_1_3_2_1_41_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Tang Changli","year":"2023","unstructured":"Changli Tang,Wenyi Yu, Guangzhi Sun, Xianzhao Chen, Tian Tan,Wei Li, Lu Lu, MA Zejun, and Chao Zhang. Salmonn: Towards generic hearing abilities for large language models. In The Twelfth International Conference on Learning Representations, 2023."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"e_1_3_2_1_43_1","volume-title":"Video-chatgpt: Towards detailed video understanding via large vision and language models. arXiv preprint arXiv:2306.05424","author":"Maaz Muhammad","year":"2023","unstructured":"Muhammad Maaz, Hanoona Rasheed, Salman Khan, and Fahad Shahbaz Khan. Video-chatgpt: Towards detailed video understanding via large vision and language models. arXiv preprint arXiv:2306.05424, 2023."},{"key":"e_1_3_2_1_44_1","volume-title":"Llama-vid: An image is worth 2 tokens in large language models. arXiv preprint arXiv:2311.17043","author":"Li Yanwei","year":"2023","unstructured":"Yanwei Li, ChengyaoWang, and Jiaya Jia. Llama-vid: An image is worth 2 tokens in large language models. arXiv preprint arXiv:2311.17043, 2023."},{"key":"e_1_3_2_1_45_1","volume-title":"mplug-owl: Modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178","author":"Ye Qinghao","year":"2023","unstructured":"Qinghao Ye, Haiyang Xu, Guohai Xu, Jiabo Ye, Ming Yan, Yiyang Zhou, Junyang Wang, Anwen Hu, Pengcheng Shi, Yaya Shi, et al. mplug-owl: Modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178, 2023."},{"key":"e_1_3_2_1_46_1","volume-title":"Chatunivi: Unified visual representation empowers large language models with image and video understanding. arXiv preprint arXiv:2311.08046","author":"Jin Peng","year":"2023","unstructured":"Peng Jin, Ryuichi Takanobu, Caiwan Zhang, Xiaochun Cao, and Li Yuan. Chatunivi: Unified visual representation empowers large language models with image and video understanding. arXiv preprint arXiv:2311.08046, 2023."},{"key":"e_1_3_2_1_47_1","unstructured":"OpenAI. Gpt-4v(ision) system card 2023."}],"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 2nd International Workshop on Multimodal and Responsible Affective Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689092.3689959","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3689092.3689959","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:59:00Z","timestamp":1755914340000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689092.3689959"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":47,"alternative-id":["10.1145\/3689092.3689959","10.1145\/3689092"],"URL":"https:\/\/doi.org\/10.1145\/3689092.3689959","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"}}]}}