{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T00:25:04Z","timestamp":1778372704134,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758216","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:37:21Z","timestamp":1761377841000},"page":"12761-12768","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Language-Driven 3D Human Pose Estimation in Multi-Person Scenarios: A New Dataset and Approach"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6847-2608","authenticated-orcid":false,"given":"Tingrui","family":"Shen","sequence":"first","affiliation":[{"name":"South China University of Technology, GuangZhou, China and Singapore Management University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6621-0594","authenticated-orcid":false,"given":"Bangzhen","family":"Liu","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China and Singapore Management University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2337-1706","authenticated-orcid":false,"given":"Zhirun","family":"Fan","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8362-5011","authenticated-orcid":false,"given":"Shiting","family":"Zhang","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6055-2185","authenticated-orcid":false,"given":"Weifeng","family":"Pan","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4069-4529","authenticated-orcid":false,"given":"Fan","family":"Sun","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7909-4765","authenticated-orcid":false,"given":"Dan","family":"Cao","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3802-4644","authenticated-orcid":false,"given":"Shengfeng","family":"He","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00304"},{"key":"e_1_3_2_1_3_1","volume-title":"SCJD: Sparse Correlation and Joint Distillation for Efficient 3D Human Pose Estimation.","author":"Chen Weihong","year":"2025","unstructured":"Weihong Chen, Xuemiao Xu, Haoxin Yang, Yi Xie, Peng Xiao, Cheng Xu, Huaidong Zhang, and Pheng-Ann Heng. 2025. SCJD: Sparse Correlation and Joint Distillation for Efficient 3D Human Pose Estimation. (2025)."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 20186-20196","author":"Ha Myoung Hoon","year":"2022","unstructured":"Hyung-gun Chi, Myoung Hoon Ha, Seunggeun Chi, Sang Wan Lee, Qixing Huang, and Karthik Ramani. 2022. Infogcn: Representation learning for human skeleton-based action recognition. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 20186-20196."},{"key":"e_1_3_2_1_5_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. 2024a. PoseScript: Linking 3D Human Poses and Natural Language. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_1_6_1","volume-title":"Semantic-Aware Human Pose Representation. In European Conference on Computer Vision. Springer, 55-73","author":"Delmas Ginger","year":"2024","unstructured":"Ginger Delmas, Philippe Weinzaepfel, Francesc Moreno-Noguer, and Gr\u00e9gory Rogez. 2024b. PoseEmbroider: Towards a 3D, Visual, Semantic-Aware Human Pose Representation. In European Conference on Computer Vision. Springer, 55-73."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2557779"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00204"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.381"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_14_1","volume-title":"ChatHuman: Language-driven 3D Human Understanding with Retrieval-Augmented Tool Reasoning. arXiv preprint arXiv:2405.04533","author":"Lin Jing","year":"2024","unstructured":"Jing Lin, Yao Feng, Weiyang Liu, and Michael J Black. 2024. ChatHuman: Language-driven 3D Human Understanding with Retrieval-Augmented Tool Reasoning. arXiv preprint arXiv:2405.04533 (2024)."},{"key":"e_1_3_2_1_15_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, Vol. 36 (2023), 25268-25280.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_16_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. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"e_1_3_2_1_18_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Luo Zhuoyan","year":"2024","unstructured":"Zhuoyan Luo, Yicheng Xiao, Yong Liu, Shuyan Li, Yitong Wang, Yansong Tang, Xiu Li, and Yujiu Yang. 2024. Soc: Semantic-assisted object cluster for referring video object segmentation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108487"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.139"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00794"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0273-6"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_4"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.284"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01289"},{"key":"e_1_3_2_1_27_1","volume-title":"European Conference on Computer Vision. Springer, 309-325","author":"Sun Ziming","year":"2024","unstructured":"Ziming Sun, Yuan Liang, Zejun Ma, Tianle Zhang, Linchao Bao, Guiqing Li, and Shengfeng He. 2024. Repose: 3d human pose estimation via spatio-temporal depth relational consistency. In European Conference on Computer Vision. Springer, 309-325."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.14"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_12"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01281"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"e_1_3_2_1_34_1","unstructured":"Yuxin Wu Alexander Kirillov Francisco Massa Wan-Yen Lo and Ross Girshick. 2019. Detectron2."},{"key":"e_1_3_2_1_35_1","volume-title":"European Conference on Computer Vision. Springer, 402-419","author":"Xiao Peng","year":"2024","unstructured":"Peng Xiao, Yi Xie, Xuemiao Xu, Weihong Chen, and Huaidong Zhang. 2024. Multi-person pose forecasting with individual interaction perceptron and prior learning. In European Conference on Computer Vision. Springer, 402-419."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3554739"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/IECON43393.2020.9255211"},{"key":"e_1_3_2_1_38_1","volume-title":"StarPose: 3D Human Pose Estimation via Spatial-Temporal Autoregressive Diffusion","author":"Yang Haoxin","year":"2025","unstructured":"Haoxin Yang, Weihong Chen, Xuemiao Xu, Cheng Xu, Peng Xiao, Cuifeng Sun, Shaoyu Huang, and Shengfeng He. 2025. StarPose: 3D Human Pose Estimation via Spatial-Temporal Autoregressive Diffusion. IEEE Transactions on Circuits and Systems for Video Technology (2025)."},{"key":"e_1_3_2_1_39_1","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Zanfir Andrei","year":"2018","unstructured":"Andrei Zanfir, Elisabeta Marinoiu, Mihai Zanfir, Alin-Ionut Popa, and Cristian Sminchisescu. 2018. Deep network for the integrated 3d sensing of multiple people in natural images. Advances in Neural Information Processing Systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00119"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_11"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_33"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"e_1_3_2_1_44_1","volume-title":"Asia Conference on Machine Learning. PMLR, 1763-1778","author":"Zhuang Zonghuang","year":"2024","unstructured":"Zonghuang Zhuang and Yue Zhou. 2024. FasterVoxelPose: Fast and accurate voxel-based 3D human pose estimation by depth-wise projection decay. In Asia Conference on Machine Learning. PMLR, 1763-1778."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3758216","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:02:49Z","timestamp":1765342969000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758216"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":44,"alternative-id":["10.1145\/3746027.3758216","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758216","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"}}]}}