{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:00:38Z","timestamp":1777888838139,"version":"3.51.4"},"reference-count":90,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271410,12150007"],"award-info":[{"award-number":["62271410,12150007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00844","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"9024-9035","source":"Crossref","is-referenced-by-count":0,"title":["MixRI: Mixing Features of Reference Images for Novel Object Pose Estimation"],"prefix":"10.1109","author":[{"given":"Xinhang","family":"Liu","sequence":"first","affiliation":[{"name":"School of Electronics and Information, Northwestern Polytechnical University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Electronics and Information, Northwestern Polytechnical University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Dang","sequence":"additional","affiliation":[{"name":"EPFL,CVLab,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchao","family":"Dai","sequence":"additional","affiliation":[{"name":"School of Electronics and Information, Northwestern Polytechnical University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611464"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_35"},{"key":"ref3","article-title":"Efficientpose: An efficient, accurate and scalable end-to-end 6d multi object pose estimation approach","author":"Bukschat","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref4","article-title":"Gs-pose: Cascaded framework for generalizable segmentation-based 6 d object pose estimation","author":"Cai","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73226-3_24"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/965139.807360"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01199"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00280"},{"key":"ref10","article-title":"Zeropose: Cad-model-based zero-shot pose estimation","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00950"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911401765"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196714"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"ref15","first-page":"13610","article-title":"Tap-vid: A benchmark for tracking any point in a video","author":"Doersch","year":"2022","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref16","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Int. Conf. Learn. Represent.","author":"Dosovitskiy","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.390"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540108"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.257"},{"key":"ref20","article-title":"D2-net: A trainable cnn for joint detection and description of local features","author":"Dusmanu","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_4"},{"key":"ref23","volume-title":"Multiple view geometry in computer vision","author":"Hartley","year":"2003"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref26","first-page":"35103","article-title":"Onepose++: Keypoint-free one-shot object pose estimation without cad models","author":"He","year":"2022","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01165"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00302"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00669"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.103"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_2"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00570"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00962"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01385-0"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00338"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.169"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_34"},{"key":"ref38","first-page":"715","article-title":"Megapose: 6d pose estimation of novel objects via render & compare","volume-title":"Conference on Robot Learning (CoRL)","author":"Labb\u00e9","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02039"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2946140"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_42"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00316"},{"key":"ref43","first-page":"7678","article-title":"Cdpn: Coordinatesbased disentangled pose network for real-time rgb-based 6dof object pose estimation","volume-title":"Int. Conf. Comput. Vis.","author":"Li","year":"2019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02636"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812299"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00967"},{"key":"ref47","first-page":"6990","article-title":"Gift: Learning transformation-invariant dense visual descriptors via group cnns","author":"Liu","year":"2019","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_18"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(87)90070-1"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000029664.99615.94"},{"key":"ref52","article-title":"Continuous parametric optical flow","author":"Luo","year":"2024","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref53","article-title":"Cps++: Improving class-level 6d pose and shape estimation from monocular images with self-supervised learning","author":"Manhardt","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2015.2513408"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295236"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00957"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00665"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00227"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00945"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560874"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_10"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00078"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00469"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69525-5_3"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.413"},{"key":"ref66","article-title":"R2d2: Reliable and repeatable detector and descriptor","author":"Revaud","year":"2019","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00671"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00662"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00670"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_28"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_32"},{"key":"ref74","article-title":"Diffdope: Differentiable deep object pose estimation","author":"Tremblay","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_21"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01634"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00275"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01813"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00975"},{"key":"ref80","first-page":"14357","article-title":"General e (2)-equivariant steerable cnns","author":"Weiler","year":"2019","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197350"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00066"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01692"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.019"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121361"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87199-4_16"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01446"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00203"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_7"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00080"}],"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\/11444058.pdf?arnumber=11444058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:59:25Z","timestamp":1777611565000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444058\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":90,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00844","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}