{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:30:47Z","timestamp":1778081447014,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":63,"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":[{"name":"The National Natural Science Foundation of China","award":["62076101"],"award-info":[{"award-number":["62076101"]}]},{"name":"The Guangdong Provincial Key Laboratory of Human Digital Twin","award":["2022B1212010004"],"award-info":[{"award-number":["2022B1212010004"]}]},{"name":"The 2024 Tencent AI Lab Rhino-Bird Focused Research Program"},{"name":"The TCL Young Scholars Program"},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2024B1515020082,2023A1515010007"],"award-info":[{"award-number":["2024B1515020082,2023A1515010007"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681068","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"5338-5346","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Decoupling Heterogeneous Features for Robust 3D Interacting Hand Poses Estimation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6426-9379","authenticated-orcid":false,"given":"Huan","family":"Yao","sequence":"first","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7232-3181","authenticated-orcid":false,"given":"Changxing","family":"Ding","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8462-507X","authenticated-orcid":false,"given":"Xuanda","family":"Xu","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4605-2802","authenticated-orcid":false,"given":"Zhifeng","family":"Lin","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_33"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01100"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01245"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00831"},{"key":"e_1_3_2_1_5_1","volume-title":"Monocular 3D reconstruction of interacting hands via collision-aware factorized refinements. In 3DV","author":"Rong Y.","year":"2021","unstructured":"Y. Rong, J. Wang, Z. Liu, and C. Loy. Monocular 3D reconstruction of interacting hands via collision-aware factorized refinements. In 3DV, 2021."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_22"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01633"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01116"},{"key":"e_1_3_2_1_9_1","volume-title":"Learning to disambiguate strongly interacting hands via probabilistic per-pixel part segmentation. In 3DV","author":"Fan Z.","year":"2021","unstructured":"Z. Fan, A. Spurr, M. Kocabas, S. Tang, M. Black, and O. Hilliges. Learning to disambiguate strongly interacting hands via probabilistic per-pixel part segmentation. In 3DV, 2021."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00062"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00736"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28087"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01081"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00278"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_16_1","volume-title":"NeurIPS","author":"Vaswani A.","year":"2017","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. Gomez, Attention is all you need. In NeurIPS, 2017."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00339"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00854"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00244"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00155"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01989"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01988"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00484"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02028"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6761"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00540"},{"key":"e_1_3_2_1_28_1","volume-title":"TPAMI","author":"Deng X.","year":"2022","unstructured":"X. Deng, D. Zuo, Y. Zhang, Z. Cui, J. Cheng, P. Tan, L. Chang, M. Pollefeys, S. Fanello, and H. Wang. Recurrent 3d hand pose estimation using cascaded pose-guided 3d alignments. In TPAMI, 2022."},{"key":"e_1_3_2_1_29_1","volume-title":"CVPR","author":"Moon G.","year":"2018","unstructured":"G. Moon, J. Chang, and K. Lee. V2v-posenet: Voxel-to-voxel prediction network for accurate 3d hand and human pose estimation from a single depth map. In CVPR, 2018."},{"key":"e_1_3_2_1_30_1","volume-title":"ICCV","author":"Mueller F.","year":"2017","unstructured":"F. Mueller, D. Mehta, O. Sotnychenko, S. Sridhar, D. Casas, and C. Theobalt. Realtime hand tracking under occlusion from an egocentric rgb-d sensor. In ICCV, 2017."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01109"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_41"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451022"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00088"},{"key":"e_1_3_2_1_35_1","volume-title":"CVPR","author":"Guan H.","year":"2006","unstructured":"H. Guan, J. Chang, L. Chen, and R. Feris. Multi-view appearance-based 3D hand pose estimation. In CVPR, 2006."},{"key":"e_1_3_2_1_36_1","volume-title":"TAI","author":"Khaleghi L.","year":"2022","unstructured":"L. Khaleghi, A. Sepas-Moghaddam, J. Marshall, and A. Etemad. Multi-view videobased 3D hand pose estimation. In TAI, 2022."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00080"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00504"},{"key":"e_1_3_2_1_39_1","volume-title":"Towards unconstrained joint hand-object reconstruction from rgb videos. In 3DV","author":"Hasson Y.","year":"2021","unstructured":"Y. Hasson, Towards unconstrained joint hand-object reconstruction from rgb videos. In 3DV, 2021."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01248"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.438"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126483"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.494"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_46"},{"key":"e_1_3_2_1_45_1","volume-title":"ToG","author":"Han S.","year":"2020","unstructured":"S. Han, B. Liu, R. Cabezas, C. Twigg, P. Zhang, J. Petkau, T. Yu, C. Tai, M. Akbay, Z. Wang, MEgATrack: monochrome egocentric articulated hand-tracking for virtual reality. In ToG, 2020."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322958"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417768"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01238"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097259"},{"key":"e_1_3_2_1_51_1","volume-title":"TPAMI","author":"Ren S.","year":"2016","unstructured":"S. Ren, K. He, R. Girshick, and J. Sun. Faster R-CNN: Towards real-time object detection with region proposal networks. In TPAMI, 2016."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01208"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417852"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612590"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413775"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612390"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413651"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3591106.3592215"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463648"},{"key":"e_1_3_2_1_61_1","volume-title":"ICHR","author":"Romero J.","year":"2009","unstructured":"J. Romero, Monocular real-time 3D articulated hand pose estimation. In ICHR, 2009."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.490"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3402232"}],"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\/3664647.3681068","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:52Z","timestamp":1750294672000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681068"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":63,"alternative-id":["10.1145\/3664647.3681068","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681068","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"}}]}}