{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:09:24Z","timestamp":1765343364625,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","funder":[{"DOI":"10.13039\/100018919","name":"Peng Cheng Laboratory","doi-asserted-by":"publisher","award":["PCL2023A10-2"],"award-info":[{"award-number":["PCL2023A10-2"]}],"id":[{"id":"10.13039\/100018919","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Key Laboratory of next generation interactive media innovative technology","award":["ZDSYS20210623092001004"],"award-info":[{"award-number":["ZDSYS20210623092001004"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755164","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:37:21Z","timestamp":1761377841000},"page":"1404-1413","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Motion is Worth a Hybrid Sentence: Taming Language Model for Unified Motion Generation by Fine-grained Planning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7703-9315","authenticated-orcid":false,"given":"Ronghui","family":"Li","sequence":"first","affiliation":[{"name":"Tsinghua University, Shenzhen, China and Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1288-9656","authenticated-orcid":false,"given":"Lingxiao","family":"Han","sequence":"additional","affiliation":[{"name":"Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4881-8279","authenticated-orcid":false,"given":"Shi","family":"Shu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4298-2609","authenticated-orcid":false,"given":"Yueyao","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2469-5690","authenticated-orcid":false,"given":"Yukang","family":"Lin","sequence":"additional","affiliation":[{"name":"Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7477-5938","authenticated-orcid":false,"given":"Yue","family":"Ma","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7411-4751","authenticated-orcid":false,"given":"Jie","family":"Guo","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4220-5958","authenticated-orcid":false,"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0403-1923","authenticated-orcid":false,"given":"Xiu","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems 35 (2022) 23716-23736."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","unstructured":"Tenglong Ao Zeyi Zhang and Libin Liu. 2023. GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents. ACM Trans. Graph. (2023) 18 pages. doi:10.1145\/3592097","DOI":"10.1145\/3592097"},{"key":"e_1_3_2_1_3_1","volume-title":"SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation. ICCV","author":"Athanasiou Nikos","year":"2023","unstructured":"Nikos Athanasiou, Mathis Petrovich, Michael J. Black, and G\u00fcl Varol. 2023. SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation. ICCV (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls. arXiv preprint arXiv:2407.21136","author":"Bian Yuxuan","year":"2024","unstructured":"Yuxuan Bian, Ailing Zeng, Xuan Ju, Xian Liu, Zhaoyang Zhang, Wei Liu, and Qiang Xu. 2024. MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls. arXiv preprint arXiv:2407.21136 (2024)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680847"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680847"},{"key":"e_1_3_2_1_7_1","unstructured":"Ting Chen Mostafa Dehghani Vladimir Mirkes Aditya Ramesh Sean Welleck et al. 2022. PaLI: A Jointly-Scaled Multimodal Model of Language and Vision. arXiv preprint arXiv:2209.06794 (2022). https:\/\/arxiv.org\/abs\/2209.06794"},{"key":"e_1_3_2_1_8_1","volume-title":"Posescript: Linking 3d human poses and natural language","author":"Delmas Ginger","year":"2024","unstructured":"Ginger Delmas, Philippe Weinzaepfel, Thomas Lucas, Francesc Moreno-Noguer, and Gr\u00e9gory Rogez. 2024. Posescript: Linking 3d human poses and natural language. IEEE transactions on pattern analysis and machine intelligence (2024)."},{"key":"e_1_3_2_1_9_1","volume-title":"Corey Lynch, Aakanksha Chowdhery, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, Wenlong Huang, et al.","author":"Driess Danny","year":"2023","unstructured":"Danny Driess, Fei Xia, Mehdi SM Sajjadi, Corey Lynch, Aakanksha Chowdhery, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, Wenlong Huang, et al. 2023. Palm-e: An embodied multimodal language model. (2023)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00912"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"e_1_3_2_1_14_1","volume-title":"Semanticboost: Elevating motion generation with augmented textual cues. arXiv preprint arXiv:2310.20323","author":"He Xin","year":"2023","unstructured":"Xin He, Shaoli Huang, Xiaohang Zhan, Chao Weng, and Ying Shan. 2023. Semanticboost: Elevating motion generation with augmented textual cues. arXiv preprint arXiv:2310.20323 (2023)."},{"key":"e_1_3_2_1_15_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2022. Lora: Low-rank adaptation of large language models. ICLR 1, 2 (2022), 3.","journal-title":"ICLR"},{"key":"e_1_3_2_1_16_1","unstructured":"Puxin Huang Noah Shinn Zhenhai Zhang Yujia Xiao Aniruddha Sharma Xuezhi Han Xiaohua Zhan Xinlei Li Jianwei Zhang Kai-Wei Chang et al. 2023. Language Is Not All You Need: Aligning Perception with Language Models. arXiv preprint arXiv:2302.14045 (2023). https:\/\/arxiv.org\/abs\/2302.14045"},{"key":"e_1_3_2_1_17_1","unstructured":"Shengpeng Ji Ziyue Jiang Wen Wang Yifu Chen Minghui Fang Jialong Zuo Qian Yang Xize Cheng Zehan Wang Ruiqi Li et al. 2024. Wavtokenizer: an efficient acoustic discrete codec tokenizer for audio language modeling. arXiv preprint arXiv:2408.16532 (2024)."},{"key":"e_1_3_2_1_18_1","first-page":"20067","article-title":"Motiongpt: Human motion as a foreign language","volume":"36","author":"Jiang Biao","year":"2023","unstructured":"Biao Jiang, Xin Chen, Wen Liu, Jingyi Yu, Gang Yu, and Tao Chen. 2023. Motiongpt: Human motion as a foreign language. Advances in Neural Information Processing Systems 36 (2023), 20067-20079.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_19_1","unstructured":"Yinhan Jiang Maud Bibi Naman Patel Sharan Mathur et al. 2023. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Sai Shashank Kalakonda Shubh Maheshwari and Ravi Kiran Sarvadevabhatla. 2023. Action-GPT: Leveraging Large-scale Language Models for Improved and Generalized Action Generation. arXiv:2211.15603 [cs.CV] https:\/\/arxiv.org\/abs\/2211.15603","DOI":"10.1109\/ICME55011.2023.00014"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00348"},{"key":"e_1_3_2_1_23_1","unstructured":"Diederik P Kingma Max Welling et al. 2013. Auto-encoding variational bayes."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01360"},{"key":"e_1_3_2_1_25_1","volume-title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. arXiv preprint arXiv:2301.12597","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. arXiv preprint arXiv:2301.12597 (2023). https:\/\/arxiv.org\/abs\/2301.12597"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00151"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00939"},{"key":"e_1_3_2_1_29_1","first-page":"25268","article-title":"Motion-x: A large-scale 3d expressive whole-body human motion dataset","volume":"36","author":"Lin Jing","year":"2023","unstructured":"Jing Lin, Ailing Zeng, Shunlin Lu, Yuanhao Cai, Ruimao Zhang, Haoqian Wang, and Lei Zhang. 2023. Motion-x: A large-scale 3d expressive whole-body human motion dataset. Advances in Neural Information Processing Systems 36 (2023), 25268-25280.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_30_1","volume-title":"MotionLLaMA: A Unified Framework for Motion Synthesis and Comprehension. arXiv preprint arXiv:2411.17335","author":"Ling Zeyu","year":"2024","unstructured":"Zeyu Ling, Bo Han, Shiyang Li, Hongdeng Shen, Jikang Cheng, and Changqing Zou. 2024. MotionLLaMA: A Unified Framework for Motion Synthesis and Comprehension. arXiv preprint arXiv:2411.17335 (2024)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548400"},{"key":"e_1_3_2_1_32_1","volume-title":"Visual Instruction Tuning. arXiv preprint arXiv:2304.08485","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Zhang, Yinan Du, and Jason Wang. 2023. Visual Instruction Tuning. arXiv preprint arXiv:2304.08485 (2023). https:\/\/arxiv.org\/abs\/2304. 08485"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00115"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01021"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00155"},{"key":"e_1_3_2_1_37_1","volume-title":"HumanTOMATO: Text-aligned Whole-body Motion Generation. arxiv:2310.12978","author":"Lu Shunlin","year":"2023","unstructured":"Shunlin Lu, Ling-Hao Chen, Ailing Zeng, Jing Lin, Ruimao Zhang, Lei Zhang, and Heung-Yeung Shum. 2023. HumanTOMATO: Text-aligned Whole-body Motion Generation. arxiv:2310.12978 (2023)."},{"key":"e_1_3_2_1_38_1","volume-title":"European Conference on Computer Vision (ECCV).","author":"Thomas","year":"2022","unstructured":"Thomas Lucas*, Fabien Baradel*, Philippe Weinzaepfel, and Gr\u00e9gory Rogez. 2022. PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_1_39_1","volume-title":"Multitask Framework for Motion Comprehension and Generation. arXiv preprint arXiv:2405.16273","author":"Luo Mingshuang","year":"2024","unstructured":"Mingshuang Luo, Ruibing Hou, Zhuo Li, Hong Chang, Zimo Liu, Yaowei Wang, and Shiguang Shan. 2024. M3GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation. arXiv preprint arXiv:2405.16273 (2024)."},{"key":"e_1_3_2_1_40_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. https:\/\/arxiv.org\/abs\/2303.08774. arXiv:2303.08774."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00153"},{"key":"e_1_3_2_1_43_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever et al. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_1_44_1","volume-title":"Generating Fine-Grained Human Motions Using ChatGPT-Refined Descriptions. arXiv preprint arXiv:2312.02772","author":"Shi Xu","year":"2023","unstructured":"Xu Shi, Chuanchen Luo, Junran Peng, Hongwen Zhang, and Yunlian Sun. 2023. Generating Fine-Grained Human Motions Using ChatGPT-Refined Descriptions. arXiv preprint arXiv:2312.02772 (2023)."},{"key":"e_1_3_2_1_45_1","volume-title":"FG-MDM: Towards Zero-Shot Human Motion Generation via Fine-Grained Descriptions. arXiv preprint arXiv:2312.02772","author":"Shi Xu","year":"2023","unstructured":"Xu Shi,Wei Yao, Chuanchen Luo, Junran Peng, Hongwen Zhang, and Yunlian Sun. 2023. FG-MDM: Towards Zero-Shot Human Motion Generation via Fine-Grained Descriptions. arXiv preprint arXiv:2312.02772 (2023)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-2070(03)00003-7"},{"key":"e_1_3_2_1_48_1","volume-title":"Human Motion Diffusion Model. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SJ1kSyO2jwu","author":"Tevet Guy","year":"2023","unstructured":"Guy Tevet, Sigal Raab, Brian Gordon, Yoni Shafir, Daniel Cohen-or, and Amit Haim Bermano. 2023. Human Motion Diffusion Model. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SJ1kSyO2jwu"},{"key":"e_1_3_2_1_49_1","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Baptiste Rozi\u00e8re Naman Goyal Olivier Sim\u00e9oni Thomas Massart Ludovic Denoyer et al. 2023. LLaMA: Open and Efficient Foundation Language Models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_50_1","volume-title":"EDGE: Editable Dance Generation From Music. arXiv preprint arXiv:2211.10658","author":"Tseng Jonathan","year":"2022","unstructured":"Jonathan Tseng, Rodrigo Castellon, and C Karen Liu. 2022. EDGE: Editable Dance Generation From Music. arXiv preprint arXiv:2211.10658 (2022)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"e_1_3_2_1_52_1","unstructured":"Aaron Van Den Oord Oriol Vinyals et al. 2017. Neural discrete representation learning. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_53_1","volume-title":"European Conference on Computer Vision. Springer, 37-54","author":"Wan Weilin","year":"2024","unstructured":"Weilin Wan, Zhiyang Dou, Taku Komura, Wenping Wang, Dinesh Jayaraman, and Lingjie Liu. 2024. Tlcontrol: Trajectory and language control for human motion synthesis. In European Conference on Computer Vision. Springer, 37-54."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"YinWang Mu Li Jiapeng Liu Zhiying Leng FrederickW. B. Li Ziyao Zhang and Xiaohui Liang. 2025. Fg-T2M: LLMs-Augmented Fine-Grained Text Driven Human Motion Generation. arXiv:2502.05534 [cs.CV] https:\/\/arxiv.org\/abs\/2502.05534","DOI":"10.1007\/s11263-025-02392-9"},{"key":"e_1_3_2_1_55_1","volume-title":"Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs. arXiv preprint arXiv:2405.17013","author":"Wu Qi","year":"2024","unstructured":"Qi Wu, Yubo Zhao, Yifan Wang, Xinhang Liu, Yu-Wing Tai, and Chi-Keung Tang. 2024. Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs. arXiv preprint arXiv:2405.17013 (2024)."},{"key":"e_1_3_2_1_56_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Xie Yiming","year":"2024","unstructured":"Yiming Xie, Varun Jampani, Lei Zhong, Deqing Sun, and Huaizu Jiang. 2024. OmniControl: Control Any Joint at Any Time for Human Motion Generation. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_57_1","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems.","author":"Xu Zunnan","year":"2024","unstructured":"Zunnan Xu, Yukang Lin, Haonan Han, Sicheng Yang, Ronghui Li, Yachao Zhang, and Xiu Li. 2024. Mambatalk: Efficient holistic gesture synthesis with selective state space models. In The Thirty-eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"e_1_3_2_1_60_1","volume-title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model. arXiv preprint arXiv:2208.15001","author":"Zhang Mingyuan","year":"2022","unstructured":"Mingyuan Zhang, Zhongang Cai, Liang Pan, Fangzhou Hong, Xinying Guo, Lei Yang, and Ziwei Liu. 2022. MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model. arXiv preprint arXiv:2208.15001 (2022)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"e_1_3_2_1_62_1","volume-title":"FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing. NeurIPS","author":"Zhang Mingyuan","year":"2023","unstructured":"Mingyuan Zhang, Huirong Li, Zhongang Cai, Jiawei Ren, Lei Yang, and Ziwei Liu. 2023. FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing. NeurIPS (2023)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28567"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00545"},{"key":"e_1_3_2_1_65_1","volume-title":"ParCo: Part-Coordinating Text-to-Motion Synthesis. arXiv preprint arXiv:2403.18512","author":"Zou Qiran","year":"2024","unstructured":"Qiran Zou, Shangyuan Yuan, Shian Du, Yu Wang, Chang Liu, Yi Xu, Jie Chen, and Xiangyang Ji. 2024. ParCo: Part-Coordinating Text-to-Motion Synthesis. arXiv preprint arXiv:2403.18512 (2024)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755164","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:04:52Z","timestamp":1765343092000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755164"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":65,"alternative-id":["10.1145\/3746027.3755164","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755164","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"}}]}}