{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:55:35Z","timestamp":1777568135957,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":64,"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":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62006166,62376178,62076175"],"award-info":[{"award-number":["62006166,62376178,62076175"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012246","name":"Priority Academic Program Development of Jiangsu Higher Education Institutions","doi-asserted-by":"publisher","id":[{"id":"10.13039\/https:\/\/doi.org\/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":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681407","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"592-601","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Hawkeye: Discovering and Grounding Implicit Anomalous Sentiment in Recon-videos via Scene-enhanced Video Large Language Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5386-3013","authenticated-orcid":false,"given":"Jianing","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3619-1525","authenticated-orcid":false,"given":"Jingjing","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4832-6902","authenticated-orcid":false,"given":"Yujie","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2144-6921","authenticated-orcid":false,"given":"Jiamin","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, China"}],"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, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Coefficient of variation. Encyclopedia of research design","author":"Abdi Herv\u00e9","year":"2010","unstructured":"Herv\u00e9 Abdi. 2010. Coefficient of variation. Encyclopedia of research design, Vol. 1, 5 (2010)."},{"key":"e_1_3_2_1_2_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer normalization. arXiv preprint arXiv:1607.06450 (2016)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612504"},{"key":"e_1_3_2_1_5_1","volume-title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning. CoRR","author":"Chen Jun","year":"2023","unstructured":"Jun Chen, Deyao Zhu, Xiaoqian Shen, Xiang Li, Zechun Liu, Pengchuan Zhang, Raghuraman Krishnamoorthi, Vikas Chandra, Yunyang Xiong, and Mohamed Elhoseiny. 2023. MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning. CoRR, Vol. abs\/2310.09478 (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic. CoRR","author":"Chen Keqin","year":"2023","unstructured":"Keqin Chen, Zhao Zhang, Weili Zeng, Richong Zhang, Feng Zhu, and Rui Zhao. 2023. Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic. CoRR, Vol. abs\/2306.15195 (2023)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.189"},{"key":"e_1_3_2_1_9_1","volume-title":"Xing","author":"Chiang Wei-Lin","year":"2023","unstructured":"Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, and Eric P. Xing. 2023. Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality. https:\/\/lmsys.org\/blog\/2023-03--30-vicuna\/"},{"key":"e_1_3_2_1_10_1","volume-title":"Michael Ying Yang, and Bodo Rosenhahn","author":"Cong Yuren","year":"2023","unstructured":"Yuren Cong, Michael Ying Yang, and Bodo Rosenhahn. 2023. Reltr: Relation transformer for scene graph generation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_2_1_11_1","volume-title":"LoRAMoE: Revolutionizing Mixture of Experts for Maintaining World Knowledge in Language Model Alignment. CoRR","author":"Dou Shihan","year":"2023","unstructured":"Shihan Dou, Enyu Zhou, Yan Liu, Songyang Gao, Jun Zhao, Wei Shen, Yuhao Zhou, Zhiheng Xi, Xiao Wang, Xiaoran Fan, Shiliang Pu, Jiang Zhu, Rui Zheng, Tao Gui, Qi Zhang, and Xuanjing Huang. 2023. LoRAMoE: Revolutionizing Mixture of Experts for Maintaining World Knowledge in Language Model Alignment. CoRR, Vol. abs\/2312.09979 (2023)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.101"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"e_1_3_2_1_15_1","volume-title":"OneLLM: One Framework to Align All Modalities with Language. CoRR","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. 2023. OneLLM: One Framework to Align All Modalities with Language. CoRR, Vol. abs\/2312.03700 (2023)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of ICLR","author":"Hu Edward J.","year":"2022","unstructured":"Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In Proceedings of ICLR 2022."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.534"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2867718"},{"key":"e_1_3_2_1_21_1","volume-title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding. CoRR","author":"Jin Peng","year":"2023","unstructured":"Peng Jin, Ryuichi Takanobu, Caiwan Zhang, Xiaochun Cao, and Li Yuan. 2023. Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding. CoRR, Vol. abs\/2311.08046 (2023)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of ACCV 2018 (Lecture Notes in Computer Science","author":"Khoreva Anna","year":"2018","unstructured":"Anna Khoreva, Anna Rohrbach, and Bernt Schiele. 2018. Video Object Segmentation with Language Referring Expressions. In Proceedings of ACCV 2018 (Lecture Notes in Computer Science, Vol. 11364)."},{"key":"e_1_3_2_1_24_1","volume-title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning. CoRR","author":"Li Bo","year":"2023","unstructured":"Bo Li, Yuanhan Zhang, Liangyu Chen, Jinghao Wang, Jingkang Yang, and Ziwei Liu. 2023. Otter: A Multi-Modal Model with In-Context Instruction Tuning. CoRR, Vol. abs\/2305.03726 (2023)."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of ICML","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven C. H. Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. In Proceedings of ICML 2023."},{"key":"e_1_3_2_1_26_1","volume-title":"VideoChat: Chat-Centric Video Understanding. CoRR","author":"Li Kunchang","year":"2023","unstructured":"Kunchang Li, Yinan He, Yi Wang, Yizhuo Li, Wenhai Wang, Ping Luo, Yali Wang, Limin Wang, and Yu Qiao. 2023. VideoChat: Chat-Centric Video Understanding. CoRR, Vol. abs\/2305.06355 (2023)."},{"key":"e_1_3_2_1_27_1","volume-title":"3DMIT: 3D Multi-modal Instruction Tuning for Scene Understanding. CoRR","author":"Li Zeju","year":"2024","unstructured":"Zeju Li, Chao Zhang, Xiaoyan Wang, Ruilong Ren, Yifan Xu, Ruifei Ma, and Xiangde Liu. 2024. 3DMIT: 3D Multi-modal Instruction Tuning for Scene Understanding. CoRR, Vol. abs\/2401.03201 (2024)."},{"key":"e_1_3_2_1_28_1","volume-title":"Moe-llava: Mixture of experts for large vision-language models. arXiv preprint arXiv:2401.15947","author":"Lin Bin","year":"2024","unstructured":"Bin Lin, Zhenyu Tang, Yang Ye, Jiaxi Cui, Bin Zhu, Peng Jin, Junwu Zhang, Munan Ning, and Li Yuan. 2024. Moe-llava: Mixture of experts for large vision-language models. arXiv preprint arXiv:2401.15947 (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection. CoRR","author":"Lin Bin","year":"2023","unstructured":"Bin Lin, Yang Ye, Bin Zhu, Jiaxi Cui, Munan Ning, Peng Jin, and Li Yuan. 2023. Video-LLaVA: Learning United Visual Representation by Alignment Before Projection. CoRR, Vol. abs\/2311.10122 (2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02212"},{"key":"e_1_3_2_1_31_1","volume-title":"Visual Instruction Tuning. CoRR","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual Instruction Tuning. CoRR, Vol. abs\/2304.08485 (2023)."},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of ICLR","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In Proceedings of ICLR 2019."},{"key":"e_1_3_2_1_33_1","volume-title":"Valley: Video Assistant with Large Language model Enhanced abilitY. CoRR","author":"Luo Ruipu","year":"2023","unstructured":"Ruipu Luo, Ziwang Zhao, Min Yang, Junwei Dong, Minghui Qiu, Pengcheng Lu, Tao Wang, and Zhongyu Wei. 2023. Valley: Video Assistant with Large Language model Enhanced abilitY. CoRR, Vol. abs\/2306.07207 (2023)."},{"key":"e_1_3_2_1_34_1","volume-title":"Salman H. Khan, and Fahad Shahbaz Khan.","author":"Maaz Muhammad","year":"2023","unstructured":"Muhammad Maaz, Hanoona Abdul Rasheed, Salman H. Khan, and Fahad Shahbaz Khan. 2023. Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models. CoRR, Vol. abs\/2306.05424 (2023)."},{"key":"e_1_3_2_1_35_1","volume-title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models. CoRR","author":"Mitra Chancharik","year":"2023","unstructured":"Chancharik Mitra, Brandon Huang, Trevor Darrell, and Roei Herzig. 2023. Compositional Chain-of-Thought Prompting for Large Multimodal Models. CoRR, Vol. abs\/2311.17076 (2023)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00150"},{"key":"e_1_3_2_1_37_1","volume-title":"Towards Harmful Erotic Content Detection through Coreference-Driven Contextual Analysis. CoRR","author":"Okulska Inez","year":"2023","unstructured":"Inez Okulska and Emilia Wisnios. 2023. Towards Harmful Erotic Content Detection through Coreference-Driven Contextual Analysis. CoRR, Vol. abs\/2310.14325 (2023)."},{"key":"e_1_3_2_1_39_1","volume-title":"From sparse to soft mixtures of experts. arXiv preprint arXiv:2308.00951","author":"Puigcerver Joan","year":"2023","unstructured":"Joan Puigcerver, Carlos Riquelme, Basil Mustafa, and Neil Houlsby. 2023. From sparse to soft mixtures of experts. arXiv preprint arXiv:2308.00951 (2023)."},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of ICML","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. 2021. Learning transferable visual models from natural language supervision. In Proceedings of ICML 2021."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00156"},{"key":"e_1_3_2_1_43_1","volume-title":"PandaGPT: One Model To Instruction-Follow Them All. CoRR","author":"Su Yixuan","year":"2023","unstructured":"Yixuan Su, Tian Lan, Huayang Li, Jialu Xu, Yan Wang, and Deng Cai. 2023. PandaGPT: One Model To Instruction-Follow Them All. CoRR, Vol. abs\/2305.16355 (2023)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"e_1_3_2_1_45_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings of ACL","volume":"2019","author":"Hubert Tsai Yao-Hung","year":"2019","unstructured":"Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, J Zico Kolter, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2019. Multimodal transformer for unaligned multimodal language sequences. In Proceedings of ACL 2019, Vol. 2019."},{"key":"e_1_3_2_1_47_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6455"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20163"},{"key":"e_1_3_2_1_50_1","volume-title":"Video-GroundingDINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding. CoRR","author":"Wasim Syed Talal","year":"2024","unstructured":"Syed Talal Wasim, Muzammal Naseer, Salman Khan, Ming-Hsuan Yang, and Fahad Shahbaz Khan. 2024. Video-GroundingDINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding. CoRR, Vol. abs\/2401.00901 (2024)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"e_1_3_2_1_52_1","volume-title":"UniRef: Segment Every Reference Object in Spatial and Temporal Spaces. arXiv preprint arXiv:2312.15715","author":"Wu Jiannan","year":"2023","unstructured":"Jiannan Wu, Yi Jiang, Bin Yan, Huchuan Lu, Zehuan Yuan, and Ping Luo. 2023. UniRef: Segment Every Reference Object in Spatial and Temporal Spaces. arXiv preprint arXiv:2312.15715 (2023)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28423"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01595"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.421"},{"key":"e_1_3_2_1_56_1","volume-title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality. CoRR","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, Chenliang Li, Yuanhong Xu, Hehong Chen, Junfeng Tian, Qian Qi, Ji Zhang, and Fei Huang. 2023. mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality. CoRR, Vol. abs\/2304.14178 (2023)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"e_1_3_2_1_58_1","volume-title":"Graph transformer networks. Advances in neural information processing systems","author":"Yun Seongjun","year":"2019","unstructured":"Seongjun Yun, Minbyul Jeong, Raehyun Kim, Jaewoo Kang, and Hyunwoo J Kim. 2019. Graph transformer networks. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01421"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548007"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/149"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.551"},{"key":"e_1_3_2_1_64_1","volume-title":"Zhifeng Li, Wei Liu, and Li Yuan.","author":"Zhu Bin","year":"2023","unstructured":"Bin Zhu, Bin Lin, Munan Ning, Yang Yan, Jiaxi Cui, Wang HongFa, Yatian Pang, Wenhao Jiang, Junwu Zhang, Zongwei Li, Cai Wan Zhang, Zhifeng Li, Wei Liu, and Li Yuan. 2023. LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment. arxiv: 2310.01852 [cs.CV]"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3160060"}],"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\/3664647.3681407","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:46Z","timestamp":1750294666000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681407"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":64,"alternative-id":["10.1145\/3664647.3681407","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681407","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"}}]}}