{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:14:08Z","timestamp":1783527248378,"version":"3.55.0"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"The Hong Kong Jockey Club Charities Trust","award":["2022-0174"],"award-info":[{"award-number":["2022-0174"]}]},{"DOI":"10.13039\/501100003803","name":"Startup Funding and the Seed Funding for Basic Research for New Staff from The University of Hong Kong","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003803","id-type":"DOI","asserted-by":"publisher"}]},{"name":"UBTECH Robotics"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62002012"],"award-info":[{"award-number":["62002012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tcsvt.2023.3260115","type":"journal-article","created":{"date-parts":[[2023,3,21]],"date-time":"2023-03-21T20:06:58Z","timestamp":1679429218000},"page":"5844-5854","source":"Crossref","is-referenced-by-count":16,"title":["MedoidsFormer: A Strong 3D Object Detection Backbone by Exploiting Interaction With Adjacent Medoid Tokens"],"prefix":"10.1109","volume":"33","author":[{"given":"Xiaoyu","family":"Tian","sequence":"first","affiliation":[{"name":"School of Software, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4277-7702","authenticated-orcid":false,"given":"Ming","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0538-7940","authenticated-orcid":false,"given":"Qian","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junhai","family":"Yong","sequence":"additional","affiliation":[{"name":"School of Software, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2775-9730","authenticated-orcid":false,"given":"Dong","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Hong Kong, Pokfulam, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2008.01.039"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref59","article-title":"AFDet: Anchor free one stage 3D object detection","author":"ge","year":"2020","journal-title":"arXiv 2006 12671"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"ref58","first-page":"923","article-title":"End-to-end multi-view fusion for 3D object detection in LiDAR point clouds","author":"zhou","year":"2020","journal-title":"Proc Conf Robot Learn"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178844"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3181490"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00102"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref10","article-title":"Embracing single stride 3D object detector with sparse transformer","author":"fan","year":"2021","journal-title":"arXiv 2112 06375"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3165934"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref16","first-page":"1","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"qi","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3100848"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3085907"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3166914"},{"key":"ref45","article-title":"Generative transformer for accurate and reliable salient object detection","author":"mao","year":"2021","journal-title":"arXiv 2104 10127"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413172"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164230"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475285"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3127149"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3082763"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref7","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref3","article-title":"PV-RCNN++: Point-Voxel feature set abstraction with local vector representation for 3D object detection","author":"shi","year":"2021","journal-title":"arXiv 2102 00463"},{"key":"ref6","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref35","first-page":"2286","article-title":"ConViT: Improving vision transformers with soft convolutional inductive biases","author":"d\u2019ascoli","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref34","article-title":"CoAtNet: Marrying convolution and attention for all data sizes","author":"dai","year":"2021","journal-title":"arXiv 2106 04803"},{"key":"ref37","first-page":"30392","article-title":"Early convolutions help transformers see better","volume":"34","author":"xiao","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref31","article-title":"CrossFormer: A versatile vision transformer based on cross-scale attention","author":"wang","year":"2021","journal-title":"arXiv 2108 00154"},{"key":"ref30","article-title":"Focal self-attention for local-global interactions in vision transformers","author":"yang","year":"2021","journal-title":"arXiv 2107 00641"},{"key":"ref33","article-title":"LocalViT: Bringing locality to vision transformers","author":"li","year":"2021","journal-title":"arXiv 2104 05707"},{"key":"ref32","article-title":"CSWin Transformer: A general vision transformer backbone with cross-shaped windows","author":"dong","year":"2021","journal-title":"arXiv 2107 00652"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"3337","DOI":"10.3390\/s18103337","article-title":"SECOND: Sparsely embedded convolutional detection","volume":"18","author":"yan","year":"2018","journal-title":"SENSORS"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref38","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00567"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00204"},{"key":"ref68","article-title":"Part-A2 Net: 3D part-aware and aggregation neural network for object detection from point cloud","author":"shi","year":"2019","journal-title":"arXiv 1907 03670"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3102025"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00190"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01296"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00535"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00746"},{"key":"ref63","article-title":"Voxel R-CNN: Towards high performance voxel-based 3D object detection","author":"deng","year":"2020","journal-title":"arXiv 2012 15712"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3201469"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475314"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20194"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00272"},{"key":"ref28","first-page":"1","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume":"32","author":"yang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_2"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00291"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01574"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10269772\/10077567.pdf?arnumber=10077567","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T18:33:20Z","timestamp":1698086000000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10077567\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":71,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3260115","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}