{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:24:46Z","timestamp":1780053886630,"version":"3.54.0"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62173035"],"award-info":[{"award-number":["62173035"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61803033"],"award-info":[{"award-number":["61803033"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836001"],"award-info":[{"award-number":["61836001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Xiaomi Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3284598","type":"journal-article","created":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T17:19:37Z","timestamp":1686676777000},"page":"1665-1680","source":"Crossref","is-referenced-by-count":7,"title":["CatTrack: Single-Stage Category-Level 6D Object Pose Tracking via Convolution and Vision Transformer"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0709-1024","authenticated-orcid":false,"given":"Sheng","family":"Yu","sequence":"first","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8653-8626","authenticated-orcid":false,"given":"Di-Hua","family":"Zhai","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5977-4911","authenticated-orcid":false,"given":"Yuanqing","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6523-6900","authenticated-orcid":false,"given":"Dong","family":"Li","sequence":"additional","affiliation":[{"name":"China Unicom Research Institute, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiqi","family":"Zhao","sequence":"additional","affiliation":[{"name":"China Unicom Research Institute, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127492"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956703"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01309"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3230064"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00346"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2749409"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR-Adjunct.2019.00-42"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00469"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00038"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.23"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341314"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696485"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3056043"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00275"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01199"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00163"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3110538"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11009-3_41"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00277"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00354"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_32"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196679"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635991"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01296"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811720"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812299"},{"key":"ref30","article-title":"Objects as points","author":"Zhou","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3143954"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487396"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37331-2_42"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2011.40"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.336"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2913321"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3117092"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3092149"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00051"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.169"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00777"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_8"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989233"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01165"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.413"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00203"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-008-0152-6"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811799"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00773"},{"key":"ref52","article-title":"MobilePose: Real-time pose estimation for unseen objects with weak shape supervision","author":"Hou","year":"2020"},{"key":"ref53","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Qi","year":"2017"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3041332"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2936503"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref58","first-page":"16743","article-title":"SwinTrack: A simple and strong baseline for transformer tracking","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Lin","year":"2022"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2898567"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353536"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487184"},{"key":"ref62","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref68","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00298"},{"key":"ref71","article-title":"End-to-end object detection with adaptive clustering transformer","author":"Zheng","year":"2020"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00583"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3125981"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00255"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00052"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2006.1656526"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.14358\/PERS.81.2.103"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341623"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_42"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696810"},{"key":"ref85","article-title":"Open3D: A modern library for 3D data processing","author":"Zhou","year":"2018"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2018.00024"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10149532.pdf?arnumber=10149532","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:13:00Z","timestamp":1706757180000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10149532\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3284598","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}