{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:25:36Z","timestamp":1780392336183,"version":"3.54.1"},"reference-count":102,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00571","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"6046-6057","source":"Crossref","is-referenced-by-count":1,"title":["HORT: Monocular Hand-held Objects Reconstruction with Transformers"],"prefix":"10.1109","author":[{"given":"Zerui","family":"Chen","sequence":"first","affiliation":[{"name":"Inria, &#x00C9;cole normale sup&#x00E9;rieure, CNRS, PSL Research University,France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rolandos Alexandros","family":"Potamias","sequence":"additional","affiliation":[{"name":"Imperial College London,United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shizhe","family":"Chen","sequence":"additional","affiliation":[{"name":"Inria, &#x00C9;cole normale sup&#x00E9;rieure, CNRS, PSL Research University,France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cordelia","family":"Schmid","sequence":"additional","affiliation":[{"name":"Inria, &#x00C9;cole normale sup&#x00E9;rieure, CNRS, PSL Research University,France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01874"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00116"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_46"},{"key":"ref4","article-title":"Introducing HOT3D: An egocentric dataset for 3D hand and object tracking","author":"Banerjee","year":"2024","journal-title":"arXiv:2406.09598"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01110"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR.2015.7251504"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01219"},{"key":"ref8","article-title":"ShapeNet: An information-rich 3D model repository","author":"Chang","year":"2015","journal-title":"arXiv preprint arXiv:1512.03012"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00893"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812302"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01307"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00609"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_42"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01525-0"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01239"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127358"},{"key":"ref18","article-title":"Deep point cloud reconstruction","volume-title":"ICLR","author":"Choe","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00931"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610694"},{"key":"ref21","article-title":"Scaling egocentric vision: The EPIC-KITCHENS dataset","volume-title":"ECCV","author":"Damen","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1983.1056714"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_25"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00054"},{"key":"ref25","article-title":"D-SCo: Dual-stream conditional diffusion for monocular hand-held object reconstruction","volume-title":"ECCV","author":"Fu","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00030"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00326"},{"key":"ref29","article-title":"HO3Dv3: Improving the accuracy of hand-object annotations of the HO-3D dataset","author":"Hampali","year":"2021","journal-title":"arXiv preprint arXiv:2107.00887"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01081"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01638"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01208"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00075"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.1996.557255"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27995"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555401"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_8"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00043"},{"key":"ref39","article-title":"Poisson surface reconstruction","volume-title":"SGP","author":"Kazhdan","year":"2006"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2570"},{"key":"ref41","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"ref42","article-title":"Single image 3D hand reconstruction with mesh convolutions","volume-title":"BMVC","author":"Kulon","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00504"},{"key":"ref44","article-title":"Recent advances in 3D object and hand pose estimation","author":"Lepetit","year":"2020","journal-title":"arXiv preprint arXiv:2006.05927"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00866"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00278"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02034"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00660"},{"key":"ref50","article-title":"CORe50: a new dataset and benchmark for continuous object recognition","volume-title":"CoRL","author":"Lomonaco","year":"2017"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/37402.37422"},{"key":"ref52","article-title":"HandTailor: Towards highprecision monocular 3D hand recovery","volume-title":"BMVC","author":"Lv","year":"2021"},{"key":"ref53","article-title":"DexVIP: Learning dexterous grasping with human hand pose priors from video","volume-title":"CoRL","author":"Mandikal","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00064"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01242"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_22"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref59","article-title":"Graspit! a versatile simulator for robotic grasping","author":"Miller","year":"2004","journal-title":"RAM"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00533"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00013"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322958"},{"key":"ref63","article-title":"Point-E: A system for generating 3D point clouds from complex prompts","author":"Nichol","year":"2022","journal-title":"arXiv preprint arXiv:2212.08751"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126483"},{"key":"ref65","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01143"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73229-4_8"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00989"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_33"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0028333"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00201"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00989"},{"key":"ref77","article-title":"Scorebased generative modeling through stochastic differential equations","volume-title":"ICLR","author":"Song","year":"2021"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01104"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_33"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.490"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00352"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00464"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00171"},{"key":"ref84","article-title":"Attention is all you need","volume-title":"NeurIPS","author":"Vaswani","year":"2017"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417852"},{"key":"ref86","article-title":"HO-Cap: A capture system and dataset for 3D reconstruction and pose tracking of hand-object interaction","author":"Wang","year":"2024","journal-title":"arXiv:2406.06843"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2462000"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00066"},{"key":"ref89","article-title":"Reconstructing hand-held objects in 3D","author":"Wu","year":"2024","journal-title":"arXiv:2404.06507"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00545"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00088"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01091"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00277"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02028"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00387"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01806"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00895"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00279"},{"key":"ref99","article-title":"DDF-HO: hand-held object reconstruction via conditional directed distance field","volume-title":"NeurIPS","author":"Zhang","year":"2024"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00175"},{"key":"ref101","article-title":"Get a grip: Reconstructing hand-object stable grasps in egocentric videos","author":"Zhu","year":"2023","journal-title":"arXiv:2312.15719"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.525"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445904.pdf?arnumber=11445904","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:16:03Z","timestamp":1777529763000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445904\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":102,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00571","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}