{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T23:24:27Z","timestamp":1771025067394,"version":"3.50.1"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"Jiangsu Provincial Science and Technology Major Project","doi-asserted-by":"publisher","award":["BG2024042"],"award-info":[{"award-number":["BG2024042"]}],"id":[{"id":"10.13039\/501100018537","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":[[2025,11]]},"DOI":"10.1109\/tcsvt.2025.3570504","type":"journal-article","created":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T13:34:23Z","timestamp":1747316063000},"page":"10616-10631","source":"Crossref","is-referenced-by-count":1,"title":["Generalized Concordant Vision Transformer With Masked Image Tokens for Object Detection"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5884-6039","authenticated-orcid":false,"given":"Yu","family":"Quan","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4543-2179","authenticated-orcid":false,"given":"Dong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-222X","authenticated-orcid":false,"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3310478"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-023-06430-w"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01465-9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268864"},{"key":"ref8","article-title":"Ultralytics\/YOLOv5: V4.0-nn.Silu() activations, weights & biases logging, PyTorch hub integration (version v4.0)","author":"Jocher","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3480691"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3470230"},{"key":"ref12","article-title":"Toward transformer-based object detection","author":"Beal","year":"2020","journal-title":"arXiv:2012.09958"},{"key":"ref13","article-title":"Benchmarking detection transfer learning with vision transformers","author":"Li","year":"2021","journal-title":"arXiv:2111.11429"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01739-w"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3215979"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3166914"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3275538"},{"key":"ref18","first-page":"1","article-title":"You only look at one sequence: Rethinking transformer in vision through object detection","volume-title":"Proc. Neural Inf. Process. Syst. (NeurIPS)","author":"Fang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00574"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3221658"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02034-6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3458907"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3344713"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01420"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3424651"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3378978"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3522661"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3433555"},{"key":"ref31","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"Vincent","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref34","article-title":"ConvMAE: Masked convolution meets masked autoencoders","author":"Gao","year":"2022","journal-title":"arXiv:2205.03892"},{"key":"ref35","first-page":"35946","article-title":"Masked autoencoders as spatiotemporal learners","volume-title":"Proc. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Feichtenhofer"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3071401"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3344118"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref43","article-title":"Boundary and relation distillation for semantic segmentation","author":"Zhang","year":"2024","journal-title":"arXiv:2401.13174v1"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01928-1"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_20"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3227717"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3139916"},{"key":"ref48","article-title":"A simple single-scale vision transformer for object localization and instance segmentation","author":"Chen","year":"2021","journal-title":"arXiv:2112.09747"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref50","first-page":"1","article-title":"On position embeddings in bert","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.232"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref53","first-page":"1","article-title":"Conditional positional encodings for vision transformers","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Chu"},{"key":"ref54","first-page":"1","article-title":"CAPE: Encoding relative positions with continuous augmented positional embeddings","volume-title":"Proc. Neural Inf. Process. Syst. (NeurIPS)","author":"Likhomanenko"},{"key":"ref55","first-page":"1","article-title":"Encoding word order in complex embeddings","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101851"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01895"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2021.102026"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref62","volume-title":"Detectron2","author":"Wu","year":"2019"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref65","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Loshchilov"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859720"},{"key":"ref68","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00628"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01150"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"ref73","article-title":"YOLOX: Exceeding YOLO series in 2021","author":"Ge","year":"2021","journal-title":"arXiv:2107.08430"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3526990"},{"key":"ref76","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"arXiv:2010.04159","author":"Zhu"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref79","first-page":"12633","article-title":"Global context vision transformers","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Hatamizadeh"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00621"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_6"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-9794-6_13"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref84","first-page":"57570","article-title":"Masked image residual learning for scaling deeper vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"36","author":"Huang"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02327-w"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105171"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11223720\/11005511.pdf?arnumber=11005511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:47:27Z","timestamp":1762195647000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11005511\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":86,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3570504","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}