{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T04:27:25Z","timestamp":1765254445443,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":77,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,3]]},"DOI":"10.1145\/3680528.3687571","type":"proceedings-article","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T08:14:37Z","timestamp":1733213677000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["TALK-Act: Enhance Textural-Awareness for 2D Speaking Avatar Reenactment with Diffusion Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5219-1097","authenticated-orcid":false,"given":"Jiazhi","family":"Guan","sequence":"first","affiliation":[{"name":"DCST, BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3997-0031","authenticated-orcid":false,"given":"Quanwei","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2120-8383","authenticated-orcid":false,"given":"Kaisiyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2616-923X","authenticated-orcid":false,"given":"Hang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0077-4105","authenticated-orcid":false,"given":"Shengyi","family":"He","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4682-9442","authenticated-orcid":false,"given":"Zhiliang","family":"Xu","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7567-3053","authenticated-orcid":false,"given":"Haocheng","family":"Feng","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1867-5378","authenticated-orcid":false,"given":"Errui","family":"Ding","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4888-4445","authenticated-orcid":false,"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0163-9434","authenticated-orcid":false,"given":"Hongtao","family":"Xie","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9841-1796","authenticated-orcid":false,"given":"Youjian","family":"Zhao","sequence":"additional","affiliation":[{"name":"DCST, BNRist, Tsinghua University, Beijing, China and Zhongguancun Laboratory, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4220-5958","authenticated-orcid":false,"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore, Singapore"}]}],"member":"320","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"e_1_3_3_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.170"},{"key":"e_1_3_3_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_15"},{"key":"e_1_3_3_1_4_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/276"},{"key":"e_1_3_3_1_5_1","doi-asserted-by":"crossref","unstructured":"Guha Balakrishnan Amy Zhao Adrian\u00a0V. Dalca Fr\u00e9do Durand and John\u00a0V. Guttag. 2018. Synthesizing Images of Humans in Unseen Poses. CoRR abs\/1804.07739 (2018). arXiv:https:\/\/arXiv.org\/abs\/1804.07739http:\/\/arxiv.org\/abs\/1804.07739","DOI":"10.1109\/CVPR.2018.00870"},{"key":"e_1_3_3_1_6_1","first-page":"5968","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Bhunia Ankan\u00a0Kumar","year":"2023","unstructured":"Ankan\u00a0Kumar Bhunia, Salman Khan, Hisham Cholakkal, Rao\u00a0Muhammad Anwer, Jorma Laaksonen, Mubarak Shah, and Fahad\u00a0Shahbaz Khan. 2023. Person image synthesis via denoising diffusion model. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5968\u20135976."},{"key":"e_1_3_3_1_7_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts Varun Jampani and Robin Rombach. 2023. Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets. arxiv:https:\/\/arXiv.org\/abs\/2311.15127\u00a0[cs.CV]"},{"key":"e_1_3_3_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01380"},{"key":"e_1_3_3_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_3_3_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"e_1_3_3_1_11_1","volume-title":"Forty-first International Conference on Machine Learning","author":"Chang Di","year":"2023","unstructured":"Di Chang, Yichun Shi, Quankai Gao, Hongyi Xu, Jessica Fu, Guoxian Song, Qing Yan, Yizhe Zhu, Xiao Yang, and Mohammad Soleymani. 2023. MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_3_1_12_1","unstructured":"Lele Chen Guofeng Cui Ziyi Kou Haitian Zheng and Chenliang Xu. 2020. What comprises a good talking-head video generation?: A survey and benchmark. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2005.03201 (2020)."},{"key":"e_1_3_3_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"e_1_3_3_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"e_1_3_3_1_15_1","doi-asserted-by":"crossref","unstructured":"Kun Cheng Xiaodong Cun Yong Zhang Menghan Xia Fei Yin Mingrui Zhu Xuan Wang Jue Wang and Nannan Wang. 2022. VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild. arxiv:https:\/\/arXiv.org\/abs\/2211.14758\u00a0[cs.CV]","DOI":"10.1145\/3550469.3555399"},{"key":"e_1_3_3_1_16_1","volume-title":"ACCV","author":"Chung Joon\u00a0Son","year":"2016","unstructured":"Joon\u00a0Son Chung and Andrew Zisserman. 2016. Out of time: automated lip sync in the wild. In ACCV."},{"key":"e_1_3_3_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"e_1_3_3_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"e_1_3_3_1_19_1","volume-title":"ECCV","author":"Guan Jiazhi","year":"2024","unstructured":"Jiazhi Guan, Zhiliang Xu, Hang Zhou, Kaisiyuan Wang, Shengyi He, Zhanwang Zhang, Borong Liang, Haocheng Feng, Errui Ding, Jingtuo Liu, Jingdong Wang, Youjian Zhao, and Ziwei Liu. 2024. Resyncer: Rewiring Style-based Generator for Unified Audio-Visually Synced Facial Performer. In ECCV."},{"key":"e_1_3_3_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00151"},{"key":"e_1_3_3_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"e_1_3_3_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"e_1_3_3_1_23_1","unstructured":"Yuwei Guo Ceyuan Yang Anyi Rao Yaohui Wang Yu Qiao Dahua Lin and Bo Dai. 2023. Animatediff: Animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.04725 (2023)."},{"key":"e_1_3_3_1_24_1","unstructured":"Martin Heusel Hubert Ramsauer Thomas Unterthiner Bernhard Nessler and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_1_25_1","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020) 6840\u20136851."},{"key":"e_1_3_3_1_26_1","unstructured":"Li Hu Xin Gao Peng Zhang Ke Sun Bang Zhang and Liefeng Bo. 2023. Animate anyone: Consistent and controllable image-to-video synthesis for character animation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.17117 (2023)."},{"key":"e_1_3_3_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00668"},{"key":"e_1_3_3_1_28_1","unstructured":"Xinya Ji Hang Zhou Kaisiyuan Wang Qianyi Wu Wayne Wu Feng Xu and Xun Cao. 2022. EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Model. SIGGRAPH (2022)."},{"key":"e_1_3_3_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"e_1_3_3_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_24"},{"key":"e_1_3_3_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00159"},{"key":"e_1_3_3_1_32_1","first-page":"22680","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Karras Johanna","year":"2023","unstructured":"Johanna Karras, Aleksander Holynski, Ting-Chun Wang, and Ira Kemelmacher-Shlizerman. 2023. Dreampose: Fashion video synthesis with stable diffusion. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 22680\u201322690."},{"key":"e_1_3_3_1_33_1","doi-asserted-by":"crossref","unstructured":"Hyeongwoo Kim Pablo Garrido Ayush Tewari Weipeng Xu Justus Thies Matthias Niessner Patrick P\u00e9rez Christian Richardt Michael Zollh\u00f6fer and Christian Theobalt. 2018. Deep video portraits. ACM Transactions on Graphics (TOG) 37 4 (2018) 1\u201314.","DOI":"10.1145\/3197517.3201283"},{"key":"e_1_3_3_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_11"},{"key":"e_1_3_3_1_35_1","doi-asserted-by":"crossref","unstructured":"Fangjian Liao Xingxing Zou and Waikeung Wong. 2024. Appearance and Pose-guided Human Generation: A Survey. Comput. Surveys 56 5 (2024) 1\u201335.","DOI":"10.1145\/3637060"},{"key":"e_1_3_3_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00600"},{"key":"e_1_3_3_1_37_1","doi-asserted-by":"crossref","unstructured":"Xian Liu Yinghao Xu Qianyi Wu Hang Zhou Wayne Wu and Bolei Zhou. 2022. Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation. ECCV (2022).","DOI":"10.1007\/978-3-031-19836-6_7"},{"key":"e_1_3_3_1_38_1","doi-asserted-by":"crossref","unstructured":"Matthew Loper Naureen Mahmood Javier Romero Gerard Pons-Moll and Michael\u00a0J. Black. 2015. SMPL: A Skinned Multi-Person Linear Model. ACM Trans. Graphics (Proc. SIGGRAPH Asia) 34 6 (Oct. 2015) 248:1\u2013248:16.","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_3_3_1_39_1","doi-asserted-by":"crossref","unstructured":"Yuanxun Lu Jinxiang Chai and Xun Cao. 2021. Live speech portraits: real-time photorealistic talking-head animation. ACM Transactions on Graphics (TOG) 40 6 (2021) 1\u201317.","DOI":"10.1145\/3478513.3480484"},{"key":"e_1_3_3_1_40_1","unstructured":"Yifeng Ma Suzhen Wang Yu Ding Bowen Ma Tangjie Lv Changjie Fan Zhipeng Hu Zhidong Deng and Xin Yu. 2023a. TalkCLIP: Talking Head Generation with Text-Guided Expressive Speaking Styles. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.00334 (2023)."},{"key":"e_1_3_3_1_41_1","unstructured":"Yifeng Ma Suzhen Wang Zhipeng Hu Changjie Fan Tangjie Lv Yu Ding Zhidong Deng and Xin Yu. 2023b. StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles. AAAI (2023)."},{"key":"e_1_3_3_1_42_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"e_1_3_3_1_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20102"},{"key":"e_1_3_3_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"e_1_3_3_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"e_1_3_3_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"e_1_3_3_1_47_1","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748\u20138763."},{"key":"e_1_3_3_1_48_1","doi-asserted-by":"crossref","unstructured":"Yurui Ren Ge Li Shan Liu and Thomas\u00a0H Li. 2020. Deep spatial transformation for pose-guided person image generation and animation. IEEE Transactions on Image Processing 29 (2020) 8622\u20138635.","DOI":"10.1109\/TIP.2020.3018224"},{"key":"e_1_3_3_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_3_1_51_1","unstructured":"Aliaksandr Siarohin St\u00e9phane Lathuili\u00e8re Sergey Tulyakov Elisa Ricci and Nicu Sebe. 2019. First order motion model for image animation. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00452"},{"key":"e_1_3_3_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"e_1_3_3_1_54_1","unstructured":"Jiaming Song Chenlin Meng and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.02502 (2020)."},{"key":"e_1_3_3_1_55_1","unstructured":"Yang Song Jingwen Zhu Dawei Li Xiaolong Wang and Hairong Qi. 2018. Talking face generation by conditional recurrent adversarial network. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1804.04786 (2018)."},{"key":"e_1_3_3_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555393"},{"key":"e_1_3_3_1_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"e_1_3_3_1_58_1","unstructured":"Thomas Unterthiner Sjoerd Van\u00a0Steenkiste Karol Kurach Raphael Marinier Marcin Michalski and Sylvain Gelly. 2018. Towards accurate generative models of video: A new metric & challenges. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1812.01717 (2018)."},{"key":"e_1_3_3_1_59_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_1_60_1","doi-asserted-by":"crossref","unstructured":"Duomin Wang Yu Deng Zixin Yin Heung-Yeung Shum and Baoyuan Wang. 2023. Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis. CVPR (2023).","DOI":"10.1109\/CVPR52729.2023.01724"},{"key":"e_1_3_3_1_61_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"e_1_3_3_1_62_1","doi-asserted-by":"crossref","unstructured":"Suzhen Wang Lincheng Li Yu Ding Changjie Fan and Xin Yu. 2021. Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2107.09293 (2021).","DOI":"10.24963\/ijcai.2021\/152"},{"key":"e_1_3_3_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00891"},{"key":"e_1_3_3_1_64_1","unstructured":"Yaohui Wang Di Yang Francois Bremond and Antitza Dantcheva. 2022. Latent image animator: Learning to animate images via latent space navigation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2203.09043 (2022)."},{"key":"e_1_3_3_1_65_1","doi-asserted-by":"crossref","unstructured":"Zhou Wang Alan\u00a0C Bovik Hamid\u00a0R Sheikh and Eero\u00a0P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13 4 (2004) 600\u2013612.","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_3_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02026"},{"key":"e_1_3_3_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"e_1_3_3_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"e_1_3_3_1_69_1","unstructured":"Zhentao Yu Zixin Yin Deyu Zhou Duomin Wang Finn Wong and Baoyuan Wang. 2023. Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors. ICCV (2023)."},{"key":"e_1_3_3_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_3_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"e_1_3_3_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"e_1_3_3_1_74_1","first-page":"13545","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zheng Yufeng","year":"2022","unstructured":"Yufeng Zheng, Victoria\u00a0Fern\u00e1ndez Abrevaya, Marcel\u00a0C B\u00fchler, Xu Chen, Michael\u00a0J Black, and Otmar Hilliges. 2022. Im avatar: Implicit morphable head avatars from videos. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 13545\u201313555."},{"key":"e_1_3_3_1_75_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"e_1_3_3_1_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"e_1_3_3_1_77_1","unstructured":"Shenhao Zhu Junming\u00a0Leo Chen Zuozhuo Dai Yinghui Xu Xun Cao Yao Yao Hao Zhu and Siyu Zhu. 2024. Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.14781 (2024)."},{"key":"e_1_3_3_1_78_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zielonka Wojciech","year":"2023","unstructured":"Wojciech Zielonka, Timo Bolkart, and Justus Thies. 2023. INSTA: Instant Volumetric Head Avatars. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."}],"event":{"name":"SA '24: SIGGRAPH Asia 2024 Conference Papers","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"],"location":"Tokyo Japan","acronym":"SA '24"},"container-title":["SIGGRAPH Asia 2024 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3680528.3687571","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3680528.3687571","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:26Z","timestamp":1750294706000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3680528.3687571"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":77,"alternative-id":["10.1145\/3680528.3687571","10.1145\/3680528"],"URL":"https:\/\/doi.org\/10.1145\/3680528.3687571","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"2024-12-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}