{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T07:26:15Z","timestamp":1768980375168,"version":"3.49.0"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2020AAA0108303"],"award-info":[{"award-number":["2020AAA0108303"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62192712"],"award-info":[{"award-number":["62192712"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Project","award":["JCYJ20200109143041798"],"award-info":[{"award-number":["JCYJ20200109143041798"]}]},{"DOI":"10.13039\/501100001809","name":"Shenzhen Stable Supporting Program","doi-asserted-by":"publisher","award":["WDZC20200820200655001"],"award-info":[{"award-number":["WDZC20200820200655001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tnnls.2024.3412947","type":"journal-article","created":{"date-parts":[[2024,6,21]],"date-time":"2024-06-21T13:59:30Z","timestamp":1718978370000},"page":"9565-9576","source":"Crossref","is-referenced-by-count":21,"title":["UniHead: Unifying Multi-Perception for Detection Heads"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0514-0905","authenticated-orcid":false,"given":"Hantao","family":"Zhou","sequence":"first","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8760-5699","authenticated-orcid":false,"given":"Rui","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}]},{"given":"Yachao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9956-7020","authenticated-orcid":false,"given":"Haoran","family":"Duan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Durham University, Durham, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9569-269X","authenticated-orcid":false,"given":"Yawen","family":"Huang","sequence":"additional","affiliation":[{"name":"Tencent Jarvis Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6366-3763","authenticated-orcid":false,"given":"Runze","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0403-1923","authenticated-orcid":false,"given":"Xiu","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2195-2847","authenticated-orcid":false,"given":"Yefeng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Tencent Jarvis Laboratory, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3264551"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3307753"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00720"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref10","first-page":"21002","article-title":"Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection","volume-title":"Proc. NIPS","volume":"33","author":"Li"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00037"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3106641"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3081864"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3204597"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00975"},{"key":"ref20","first-page":"147","article-title":"FreeAnchor: Learning to match anchors for visual object detection","volume-title":"Proc. NIPS","volume":"32","author":"Zhang"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01158"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2876865"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3053577"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3347722"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00077"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3238511"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447410"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10176-7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3241517"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00867"},{"key":"ref40","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_28"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3233482"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3152990"},{"key":"ref45","article-title":"UniQA: Unified vision-language pre-training for image quality and aesthetic assessment","author":"Zhou","year":"2024","journal-title":"arXiv:2406.01069"},{"key":"ref46","article-title":"Improving depth gradient continuity in transformers: A comparative study on monocular depth estimation with CNN","author":"Yao","year":"2023","journal-title":"arXiv:2308.08333"},{"key":"ref47","first-page":"12633","article-title":"Global context vision transformers","volume-title":"Proc. ICML","author":"Hatamizadeh"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref49","article-title":"Axial attention in multidimensional transformers","author":"Ho","year":"2019","journal-title":"arXiv:1912.12180"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref53","article-title":"SeaFormer: Squeeze-enhanced axial transformer for mobile semantic segmentation","author":"Wan","year":"2023","journal-title":"arXiv:2301.13156"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.10882"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1906.07155"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01146"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00917"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3264008"},{"key":"ref61","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","author":"Liu","year":"2022","journal-title":"arXiv:2201.12329"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00708"},{"key":"ref63","first-page":"5621","article-title":"RepPoints v2: Verification meets regression for object detection","volume-title":"Proc. NIPS","volume":"33","author":"Chen"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3241993"},{"key":"ref66","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00511"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00580"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/10982361\/10566886.pdf?arnumber=10566886","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:41Z","timestamp":1764959981000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10566886\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":69,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3412947","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}