{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:09:56Z","timestamp":1788808196635,"version":"build-2803163510"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"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":"crossref","award":["62073101"],"award-info":[{"award-number":["62073101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Self-Planned Task of State Key Laboratory of Robotics and Systems","award":["SKLRS202610B"],"award-info":[{"award-number":["SKLRS202610B"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/tcsvt.2026.3693829","type":"journal-article","created":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T19:55:27Z","timestamp":1778874927000},"page":"13346-13360","source":"Crossref","is-referenced-by-count":0,"title":["M2F2: A Multi-Scale and Multi-View Feature Fusion Network for Generalizable Object Pose Estimation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1826-1018","authenticated-orcid":false,"given":"Hongbo","family":"Gao","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9302-4718","authenticated-orcid":false,"given":"Zhengyu","family":"Li","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4179-2898","authenticated-orcid":false,"given":"Tao","family":"Xie","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1383-7745","authenticated-orcid":false,"given":"Ruifeng","family":"Li","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9122-4032","authenticated-orcid":false,"given":"Zhendong","family":"Fan","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6714-3394","authenticated-orcid":false,"given":"Kun","family":"Dai","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Wen","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9108-8276","authenticated-orcid":false,"given":"Lijun","family":"Zhao","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3092149"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3181597"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3169144"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3309902"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3397997"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2929600"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3275366"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3115564"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196714"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911401765"},{"key":"ref11","article-title":"Deep object pose estimation for semantic robotic grasping of household objects","author":"Tremblay","year":"2018","journal-title":"arXiv:1809.10790"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09888-5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907430"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3117092"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/pres.1997.6.4.355"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2015.2513408"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00300"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.103898"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3144958"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.169"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00038"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00203"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00777"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00469"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00275"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00773"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_9"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00670"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_18"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00080"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/3dv62453.2024.00078"},{"key":"ref33","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01165"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00302"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00776"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00346"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00429"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00033"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00668"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01634"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3142441"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00666"},{"key":"ref45","article-title":"DISP6D: Disentangled implicit shape and pose learning for scalable 6D pose estimation","author":"Wen","year":"2021","journal-title":"arXiv:2107.12549"},{"key":"ref46","first-page":"16779","article-title":"Sparse steerable convolutions: An efficient learning of SE(3)-equivariant features for estimation and tracking of object poses in 3D space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Lin"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00354"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00163"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00277"},{"key":"ref50","article-title":"SAM-6D: Segment anything model meets zero-shot 6D object pose estimation","author":"Lin","year":"2023","journal-title":"arXiv:2311.15707"},{"key":"ref51","article-title":"Target driven instance detection","author":"Ammirato","year":"2018","journal-title":"arXiv:1803.04610"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3145488"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00155"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_38"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01629-1"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01675"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00318"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3174072"},{"key":"ref59","article-title":"RepViT: Revisiting mobile CNN from ViT perspective","author":"Wang","year":"2023","journal-title":"arXiv:2307.09283"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123792"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00322"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298930"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2544"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00078"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37331-2_42"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.103"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_43"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_7"},{"key":"ref69","article-title":"Pose from shape: Deep pose estimation for arbitrary 3D objects","author":"Xiao","year":"2019","journal-title":"arXiv:1906.05105"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11679504\/11520905.pdf?arnumber=11520905","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:04:26Z","timestamp":1788807866000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11520905\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":69,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3693829","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}