{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T17:40:01Z","timestamp":1782236401126,"version":"3.54.5"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2042020KF0016"],"award-info":[{"award-number":["2042020KF0016"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Wuhan University-Infinova project","award":["2019010019"],"award-info":[{"award-number":["2019010019"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2021.3068645","type":"journal-article","created":{"date-parts":[[2021,3,30]],"date-time":"2021-03-30T20:42:23Z","timestamp":1617136943000},"page":"4008-4021","source":"Crossref","is-referenced-by-count":67,"title":["Joint Hand-Object 3D Reconstruction From a Single Image With Cross-Branch Feature Fusion"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3709-6125","authenticated-orcid":false,"given":"Yujin","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5003-2260","authenticated-orcid":false,"given":"Zhigang","family":"Tu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6683-2342","authenticated-orcid":false,"given":"Ruizhi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9543-3754","authenticated-orcid":false,"given":"Linchao","family":"Bao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengyou","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7324-7034","authenticated-orcid":false,"given":"Junsong","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2894422"},{"key":"ref72","first-page":"119","article-title":"Propagating LSTM: 3D pose estimation based on joint interdependency","author":"lee","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref71","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc NeurIPS"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178826"},{"key":"ref76","first-page":"540","article-title":"MarrNet: 3D shape reconstruction via 2.5 D sketches","author":"wu","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref77","first-page":"2257","article-title":"Learning to reconstruct shapes from unseen classes","author":"zhang","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref74","first-page":"1010","article-title":"NTU RGB+D: A large scale dataset for 3D human activity analysis","author":"shahroudy","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00054"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.103"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2012.24"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00326"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2930425"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.90"},{"key":"ref30","first-page":"294","article-title":"Real-time joint tracking of a hand manipulating an object from RGB-D input","author":"sridhar","year":"2016","journal-title":"Proc ECCV"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.167"},{"key":"ref36","first-page":"333","article-title":"Grasping field: Learning implicit representations for human grasps","author":"karunratanakul","year":"2020","journal-title":"Proc 3DVT"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_30"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00464"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.264"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.701"},{"key":"ref61","first-page":"1","article-title":"Learning efficient point cloud generation for dense 3D object reconstruction","author":"lin","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.230"},{"key":"ref28","first-page":"640","article-title":"Motion capture of hands in action using discriminative salient points","author":"ballan","year":"2012","journal-title":"Proc ECCV"},{"key":"ref64","first-page":"7433","article-title":"Learning elementary structures for 3D shape generation and matching","author":"deprelle","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459282"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00988"},{"key":"ref66","first-page":"216","article-title":"A papier-mâché approach to learning 3D surface generation","author":"groueix","year":"2018","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0895-4"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00411"},{"key":"ref68","first-page":"5866","article-title":"Geometrics: Exploiting geometric structure for graph-encoded objects","author":"smith","year":"2019","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref69","first-page":"52","article-title":"Pixel2mesh: Generating 3D mesh models from single RGB images","author":"wang","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2830102"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/VR.2018.8448284"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1145\/3130800.3130883","article-title":"Embodied hands: Modeling and capturing hands and bodies together","volume":"36","author":"romero","year":"2017","journal-title":"ACM Trans Graph"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00065"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967961"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref23","first-page":"1","article-title":"Learning to infer and execute 3D shape programs","author":"tian","year":"2019","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540150"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509753"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.490"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00023"},{"key":"ref59","first-page":"646","article-title":"Learning shape priors for single-view 3D completion and reconstruction","author":"wu","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref58","first-page":"628","article-title":"3D-R2N2: A unified approach for single and multi-view 3D object reconstruction","author":"choy","year":"2016","journal-title":"Proc ECCV"},{"key":"ref57","first-page":"1","article-title":"I2l-MeshNet: Image-to-lixel prediction network for accurate 3D human pose and mesh estimation from a single RGB image","author":"moon","year":"0","journal-title":"Proc Eur Conf Comput Vis (ECCV) 2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00116"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01110"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00090"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00244"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01109"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00013"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00017"},{"key":"ref40","first-page":"666","article-title":"Weakly-supervised 3D hand pose estimation from monocular RGB images","author":"cai","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00279"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.525"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01208"},{"key":"ref15","first-page":"536","article-title":"Learning 6D object pose estimation using 3D object coordinates","author":"brachmann","year":"2014","journal-title":"Proc ECCV"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2004.1371616"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2907951"},{"key":"ref81","article-title":"ShapeNet: An information-rich 3D model repository","author":"chang","year":"2015","journal-title":"arXiv 1512 03012"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00664"},{"key":"ref84","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.88"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00050"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298869"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.226"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2890749"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.2004.1301601"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2779600"},{"key":"ref85","first-page":"219","article-title":"Joint object pose estimation and shape reconstruction in urban street scenes using 3D shape priors","author":"engelmann","year":"2016","journal-title":"Proc German Conf Pattern Recognit"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00966"},{"key":"ref86","first-page":"371","article-title":"Learning category-specific mesh reconstruction from image collections","author":"kanazawa","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref7","first-page":"1502","article-title":"Hand detection in first person vision","author":"morerio","year":"2013","journal-title":"Proc 16th Int Conf Inf Fusion"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298683"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00008"},{"key":"ref88","article-title":"Reconstructing hand-object interactions in the wild","author":"cao","year":"2020","journal-title":"arXiv 2012 09856"},{"key":"ref9","article-title":"Mediapipe: A framework for perceiving and augmenting reality","author":"lugaresi","year":"2019","journal-title":"Proc CVPR Workshop Comput Vis Augmented Virtual Reality"},{"key":"ref46","first-page":"475","article-title":"Point-to-point regression pointnet for 3D hand pose estimation","author":"ge","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00706"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00533"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8297136"},{"key":"ref42","first-page":"118","article-title":"Hand pose estimation via latent 2.5 D heatmap regression","author":"iqbal","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00236"},{"key":"ref44","article-title":"Model-based 3D hand reconstruction via self-supervised learning","author":"chen","year":"2021","journal-title":"arXiv 2103 11703"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-013-0822-4"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09390307.pdf?arnumber=9390307","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:10Z","timestamp":1652194210000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9390307\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":88,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3068645","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}