{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T21:35:06Z","timestamp":1783805706892,"version":"3.55.0"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"General Research Fund of HK","award":["27208720"],"award-info":[{"award-number":["27208720"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tpami.2023.3292030","type":"journal-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:31:42Z","timestamp":1688491902000},"page":"15650-15664","source":"Crossref","is-referenced-by-count":114,"title":["Sparse R-CNN: An End-to-End Framework for Object Detection"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0636-2224","authenticated-orcid":false,"given":"Peize","family":"Sun","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5984-728X","authenticated-orcid":false,"given":"Rufeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Jiang","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9412-1457","authenticated-orcid":false,"given":"Tao","family":"Kong","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4941-6985","authenticated-orcid":false,"given":"Chenfeng","family":"Xu","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1474-1200","authenticated-orcid":false,"given":"Wei","family":"Zhan","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0206-6639","authenticated-orcid":false,"given":"Masayoshi","family":"Tomizuka","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zehuan","family":"Yuan","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6685-7950","authenticated-orcid":false,"given":"Ping","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref56","article-title":"Rethinking transformer-based set prediction for object detection","author":"sun","year":"2020"},{"key":"ref15","article-title":"QueryInst: Parallelly supervised mask query for instance segmentation","author":"fang","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref58","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58452-8_17","article-title":"Conditional convolutions for instance segmentation","author":"tian","year":"2020"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00377"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00807"},{"key":"ref11","article-title":"UP-DETR: Unsupervised pre-training for object detection with transformers","author":"dai","year":"2020"},{"key":"ref55","article-title":"OneNet: Towards end-to-end one-stage object detection","author":"sun","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.255"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00861"},{"key":"ref50","article-title":"CrowdHuman: A benchmark for detecting human in a crowd","author":"shao","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref89","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"zhu","year":"2020"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref47","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref42","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref86","article-title":"CVPODS: All-in-one toolbox for computer vision research","author":"zhu","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref85","article-title":"Objects as points","author":"zhou","year":"2019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_32"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.260"},{"key":"ref87","article-title":"AutoAssign: Differentiable label assignment for dense object detection","author":"zhu","year":"2020"},{"key":"ref49","article-title":"OverFeat: Integrated recognition, localization and detection using convolutional networks","author":"sermanet","year":"2014","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref8","article-title":"RepPoints v2: Verification meets regression for object detection","author":"chen","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref7","first-page":"1","article-title":"SimpleDet: A simple and versatile distributed framework for object detection and instance recognition","volume":"20","author":"chen","year":"2019","journal-title":"J Mach Learn Res"},{"key":"ref9","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"dai","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref4","first-page":"213","article-title":"End-to-End object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00215"},{"key":"ref5","article-title":"MMDetection: Open MMLab detection toolbox and benchmark","author":"chen","year":"2019"},{"key":"ref82","article-title":"FreeAnchor: Learning to match anchors for visual object detection","author":"zhang","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref40","article-title":"SparsePoint: Fully end-to-end sparse 3D object detector","author":"liu","year":"2021"},{"key":"ref84","article-title":"Probabilistic two-stage detection","author":"zhou","year":"2021"},{"key":"ref83","article-title":"Object detection made simpler by eliminating heuristic NMS","author":"zhou","year":"2021"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.474"},{"key":"ref35","article-title":"DETR for pedestrian detection","author":"lin","year":"2020"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00615"},{"key":"ref78","article-title":"Double anchor R-CNN for human detection in a crowd","author":"zhang","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00975"},{"key":"ref30","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref74","article-title":"Tracking instances as queries","author":"yang","year":"2021"},{"key":"ref33","article-title":"Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection","author":"li","year":"2020"},{"key":"ref77","first-page":"260","article-title":"Dynamic R-CNN: Towards high quality object detection via dynamic training","author":"zhang","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref32","first-page":"765","article-title":"CornerNet: Detecting objects as paired keypoints","author":"law","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref76","article-title":"Cascade RetinaNet: Maintaining consistency for single-stage object detection","author":"zhang","year":"2019","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"ref39","first-page":"21","article-title":"SSD: Single shot MultiBox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref38","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01221"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.327"},{"key":"ref73","first-page":"6740","article-title":"Learning object bounding boxes for 3D instance segmentation on point clouds","author":"yang","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref68","article-title":"Towards high-quality temporal action detection with sparse proposals","author":"wu","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref67","article-title":"SOLOv2: Dynamic and fast instance segmentation","author":"wang","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref26","article-title":"DenseBox: Unifying landmark localization with end to end object detection","author":"huang","year":"2015"},{"key":"ref25","article-title":"ISTR: End-to-end instance segmentation with transformers","author":"hu","year":"2021"},{"key":"ref69","article-title":"Detectron2","author":"wu","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref64","article-title":"Scaled-YOLOv4: Scaling cross stage partial network","author":"wang","year":"2020"},{"key":"ref63","article-title":"Cascade RPN: Delving into high-quality region proposal network with adaptive convolution","author":"vu","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"ref21","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref65","article-title":"End-to-end object detection with fully convolutional network","author":"wang","year":"2020"},{"key":"ref28","first-page":"667","article-title":"Dynamic filter networks","author":"jia","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref27","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3002345"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990517"},{"key":"ref61","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10308548\/10172265.pdf?arnumber=10172265","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T19:52:37Z","timestamp":1701114757000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10172265\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":89,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3292030","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}