{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T18:04:19Z","timestamp":1779991459919,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,29]]},"DOI":"10.1145\/3774905.3794682","type":"proceedings-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T17:14:56Z","timestamp":1779988496000},"page":"1301-1311","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Better Evaluation Metrics for Text-to-Motion Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1966-6059","authenticated-orcid":false,"given":"Wenshuo","family":"Chen","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1676-1547","authenticated-orcid":false,"given":"Haozhe","family":"Jia","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3134-4208","authenticated-orcid":false,"given":"Kuimou","family":"Yu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3132-9414","authenticated-orcid":false,"given":"Songning","family":"Lai","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8600-7099","authenticated-orcid":false,"given":"Lei","family":"Wang","sequence":"additional","affiliation":[{"name":"Griffith University, Brisbane, Australia and Data61\/CSIRO, Canberra, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4532-0924","authenticated-orcid":false,"given":"Yutao","family":"Yue","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China and JITRI, Institute of Deep Perception Technology, Wuxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,5,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Chaitanya Ahuja and Louis-Philippe Morency. 2019. Language2Pose: Natural Language Grounded Pose Forecasting. arXiv:1907.01108 [cs.CV] https:\/\/arxiv.org\/abs\/1907.01108","DOI":"10.1109\/3DV.2019.00084"},{"key":"e_1_3_2_1_2_1","volume-title":"TEACH: Temporal Action Composition for 3D Humans. arXiv:2209.04066 [cs.CV] https:\/\/arxiv.org\/abs\/2209.04066","author":"Athanasiou Nikos","year":"2022","unstructured":"Nikos Athanasiou, Mathis Petrovich, Michael J. Black, and G\u00fcl Varol. 2022. TEACH: Temporal Action Composition for 3D Humans. arXiv:2209.04066 [cs.CV] https:\/\/arxiv.org\/abs\/2209.04066"},{"key":"e_1_3_2_1_3_1","unstructured":"Ling-Hao Chen Shunlin Lu Wenxun Dai Zhiyang Dou Xuan Ju Jingbo Wang Taku Komura and Lei Zhang. 2025b. Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editing. arXiv:2410.18977 [cs.CV] https:\/\/arxiv.org\/abs\/2410.18977"},{"key":"e_1_3_2_1_4_1","unstructured":"Ling-Hao Chen Shunlin Lu Ailing Zeng Hao Zhang Benyou Wang Ruimao Zhang and Lei Zhang. 2024. MotionLLM: Understanding Human Behaviors from Human Motions and Videos. arXiv:2405.20340 [cs.CV] https:\/\/arxiv.org\/abs\/2405.20340"},{"key":"e_1_3_2_1_5_1","unstructured":"Wenshuo Chen Haozhe Jia Songning Lai Keming Wu Hongru Xiao Lijie Hu and Yutao Yue. 2025a. Free-T2M: Frequency Enhanced Text-to-Motion Diffusion Model With Consistency Loss. arXiv:2501.18232 [cs.CV] https:\/\/arxiv.org\/abs\/2501.18232"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Xin Chen Biao Jiang Wen Liu Zilong Huang Bin Fu Tao Chen Jingyi Yu and Gang Yu. 2023. Executing your Commands via Motion Diffusion in Latent Space. arXiv:2212.04048 [cs.CV] https:\/\/arxiv.org\/abs\/2212.04048","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"e_1_3_2_1_7_1","unstructured":"Jungbin Cho Junwan Kim Jisoo Kim Minseo Kim Mingu Kang Sungeun Hong Tae-Hyun Oh and Youngjae Yu. 2024. DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding. arXiv:2411.19527 [cs.CV] https:\/\/arxiv.org\/abs\/2411.19527"},{"key":"e_1_3_2_1_8_1","unstructured":"Xiao Cui Yulei Qin Yuting Gao Enwei Zhang Zihan Xu Tong Wu Ke Li Xing Sun Wengang Zhou and Houqiang Li. 2024. Sinkhorn Distance Minimization for Knowledge Distillation. arXiv:2402.17110 [cs.LG] https:\/\/arxiv.org\/abs\/2402.17110"},{"key":"e_1_3_2_1_9_1","volume-title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances. arXiv:1306.0895 [stat.ML] https:\/\/arxiv.org\/abs\/1306.0895","author":"Cuturi Marco","year":"2013","unstructured":"Marco Cuturi. 2013. Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances. arXiv:1306.0895 [stat.ML] https:\/\/arxiv.org\/abs\/1306.0895"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Wenxun Dai Ling-Hao Chen Jingbo Wang Jinpeng Liu Bo Dai and Yansong Tang. 2024. MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model. arXiv:2404.19759 [cs.CV] https:\/\/arxiv.org\/abs\/2404.19759","DOI":"10.1007\/978-3-031-72640-8_22"},{"key":"e_1_3_2_1_11_1","volume-title":"Sen Wang, and Li Cheng.","author":"Guo Chuan","year":"2023","unstructured":"Chuan Guo, Yuxuan Mu, Muhammad Gohar Javed, Sen Wang, and Li Cheng. 2023. MoMask: Generative Masked Modeling of 3D Human Motions. arXiv:2312.00063 [cs.CV] https:\/\/arxiv.org\/abs\/2312.00063"},{"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":"10.1109\/CVPR52688.2022.00509"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Chuan Guo Xinxin Zuo Sen Wang and Li Cheng. 2022 d. TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts. arXiv:2207.01696 [cs.CV] https:\/\/arxiv.org\/abs\/2207.01696","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"e_1_3_2_1_17_1","unstructured":"Martin Heusel Hubert Ramsauer Thomas Unterthiner Bernhard Nessler and Sepp Hochreiter. 2018. GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. arXiv:1706.08500 [cs.LG] https:\/\/arxiv.org\/abs\/1706.08500"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Yiheng Huang Hui Yang Chuanchen Luo Yuxi Wang Shibiao Xu Zhaoxiang Zhang Man Zhang and Junran Peng. 2024. StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Framework. arXiv:2405.05691 [cs.CV] https:\/\/arxiv.org\/abs\/2405.05691","DOI":"10.1145\/3664647.3681657"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Sadeep Jayasumana Srikumar Ramalingam Andreas Veit Daniel Glasner Ayan Chakrabarti and Sanjiv Kumar. 2024. Rethinking FID: Towards a Better Evaluation Metric for Image Generation. arXiv:2401.09603 [cs.CV] https:\/\/arxiv.org\/abs\/2401.09603","DOI":"10.1109\/CVPR52733.2024.00889"},{"key":"e_1_3_2_1_20_1","unstructured":"Biao Jiang Xin Chen Wen Liu Jingyi Yu Gang Yu and Tao Chen. 2023. MotionGPT: Human Motion as a Foreign Language. arXiv:2306.14795 [cs.CV] https:\/\/arxiv.org\/abs\/2306.14795"},{"key":"e_1_3_2_1_21_1","unstructured":"Yihao Liao Yiyu Fu Ziming Cheng and Jiangfeiyang Wang. 2024. AnimationGPT:An AIGC tool for generating game combat motion assets. https:\/\/github.com\/fyyakaxyy\/AnimationGPT."},{"key":"e_1_3_2_1_22_1","volume-title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset. Advances in Neural Information Processing Systems","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 (2023)."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV).","author":"Mahmood Naureen","unstructured":"Naureen Mahmood, Nima Ghorbani, Nikolaus F. Troje, Gerard Pons-Moll, and Michael J. Black. 2019. AMASS: Archive of Motion Capture As Surface Shapes. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_2_1_24_1","volume-title":"TEMOS: Generating diverse human motions from textual descriptions. arXiv:2204.14109 [cs.CV] https:\/\/arxiv.org\/abs\/2204.14109","author":"Petrovich Mathis","year":"2022","unstructured":"Mathis Petrovich, Michael J. Black, and G\u00fcl Varol. 2022. TEMOS: Generating diverse human motions from textual descriptions. arXiv:2204.14109 [cs.CV] https:\/\/arxiv.org\/abs\/2204.14109"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Gabriel Peyr\u00e9 and Marco Cuturi. 2020. Computational Optimal Transport. arXiv:1803.00567 [stat.ML] https:\/\/arxiv.org\/abs\/1803.00567","DOI":"10.1561\/9781680835519"},{"key":"e_1_3_2_1_26_1","volume-title":"Korrawe Karunratanakul, Pu Wang, Hongfei Xue, Chen Chen, Chuan Guo, Junli Cao, Jian Ren, and Sergey Tulyakov.","author":"Pinyoanuntapong Ekkasit","year":"2024","unstructured":"Ekkasit Pinyoanuntapong, Muhammad Usama Saleem, Korrawe Karunratanakul, Pu Wang, Hongfei Xue, Chen Chen, Chuan Guo, Junli Cao, Jian Ren, and Sergey Tulyakov. 2024a. ControlMM: Controllable Masked Motion Generation. arXiv:2410.10780 [cs.CV] https:\/\/arxiv.org\/abs\/2410.10780"},{"key":"e_1_3_2_1_27_1","volume-title":"Pu Wang, Minwoo Lee, Srijan Das, and Chen Chen.","author":"Pinyoanuntapong Ekkasit","year":"2024","unstructured":"Ekkasit Pinyoanuntapong, Muhammad Usama Saleem, Pu Wang, Minwoo Lee, Srijan Das, and Chen Chen. 2024b. BAMM: Bidirectional Autoregressive Motion Model. arXiv:2403.19435 [cs.CV] https:\/\/arxiv.org\/abs\/2403.19435"},{"key":"e_1_3_2_1_28_1","volume-title":"MMM: Generative Masked Motion Model. arXiv:2312.03596 [cs.CV] https:\/\/arxiv.org\/abs\/2312.03596","author":"Pinyoanuntapong Ekkasit","year":"2024","unstructured":"Ekkasit Pinyoanuntapong, Pu Wang, Minwoo Lee, and Chen Chen. 2024c. MMM: Generative Masked Motion Model. arXiv:2312.03596 [cs.CV] https:\/\/arxiv.org\/abs\/2312.03596"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Guy Tevet Brian Gordon Amir Hertz Amit H. Bermano and Daniel Cohen-Or. 2022a. MotionCLIP: Exposing Human Motion Generation to CLIP Space. arXiv:2203.08063 [cs.CV] https:\/\/arxiv.org\/abs\/2203.08063","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"e_1_3_2_1_31_1","volume-title":"Human motion diffusion model. arXiv preprint arXiv:2209.14916","author":"Tevet Guy","year":"2022","unstructured":"Guy Tevet, Sigal Raab, Brian Gordon, Yonatan Shafir, Daniel Cohen-Or, and Amit H Bermano. 2022b. Human motion diffusion model. arXiv preprint arXiv:2209.14916 (2022)."},{"key":"e_1_3_2_1_32_1","volume-title":"Bermano","author":"Tevet Guy","year":"2022","unstructured":"Guy Tevet, Sigal Raab, Brian Gordon, Yonatan Shafir, Daniel Cohen-Or, and Amit H. Bermano. 2022c. Human Motion Diffusion Model. arXiv:2209.14916 [cs.CV] https:\/\/arxiv.org\/abs\/2209.14916"},{"key":"e_1_3_2_1_33_1","volume-title":"So Kweon, and Junmo Kim.","author":"Zhang Chenshuang","year":"2024","unstructured":"Chenshuang Zhang, Chaoning Zhang, Mengchun Zhang, In So Kweon, and Junmo Kim. 2024b. Text-to-image Diffusion Models in Generative AI: A Survey. arXiv:2303.07909 [cs.CV] https:\/\/arxiv.org\/abs\/2303.07909"},{"key":"e_1_3_2_1_34_1","unstructured":"Jianrong Zhang Yangsong Zhang Xiaodong Cun Shaoli Huang Yong Zhang Hongwei Zhao Hongtao Lu and Xi Shen. 2023b. T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations. arXiv:2301.06052 [cs.CV] https:\/\/arxiv.org\/abs\/2301.06052"},{"key":"e_1_3_2_1_35_1","volume-title":"Motiondiffuse: Text-driven human motion generation with diffusion model","author":"Zhang Mingyuan","year":"2024","unstructured":"Mingyuan Zhang, Zhongang Cai, Liang Pan, Fangzhou Hong, Xinying Guo, Lei Yang, and Ziwei Liu. 2024a. Motiondiffuse: Text-driven human motion generation with diffusion model. IEEE transactions on pattern analysis and machine intelligence, Vol. 46, 6 (2024), 4115-4128."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"e_1_3_2_1_37_1","volume-title":"Motion-X: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset. arXiv preprint arXiv:2501.05098","author":"Zhang Yuhong","year":"2025","unstructured":"Yuhong Zhang, Jing Lin, Ailing Zeng, Guanlin Wu, Shunlin Lu, Yurong Fu, Yuanhao Cai, Ruimao Zhang, Haoqian Wang, and Lei Zhang. 2025. Motion-X: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset. arXiv preprint arXiv:2501.05098 (2025)."}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774905.3794682","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T17:23:08Z","timestamp":1779988988000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774905.3794682"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,28]]},"references-count":37,"alternative-id":["10.1145\/3774905.3794682","10.1145\/3774905"],"URL":"https:\/\/doi.org\/10.1145\/3774905.3794682","relation":{},"subject":[],"published":{"date-parts":[[2026,5,28]]},"assertion":[{"value":"2026-05-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}