{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T16:12:55Z","timestamp":1790352775159,"version":"4.1.0"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JKW Research Funds","award":["20-163-14-LZ-001-004-01"],"award-info":[{"award-number":["20-163-14-LZ-001-004-01"]}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2108085UD12"],"award-info":[{"award-number":["2108085UD12"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"name":"GPU cluster"},{"name":"MCC Lab of Information Science and Technology Institution, USTC"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3264008","type":"journal-article","created":{"date-parts":[[2023,4,5]],"date-time":"2023-04-05T13:49:50Z","timestamp":1680702590000},"page":"284-298","source":"Crossref","is-referenced-by-count":44,"title":["DDOD: Dive Deeper into the Disentanglement of Object Detector"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1843-4478","authenticated-orcid":false,"given":"Zehui","family":"Chen","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenhongyi","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Engineering, University of Edinburgh, Edinburgh, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4200-0961","authenticated-orcid":false,"given":"Jiahao","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6767-8105","authenticated-orcid":false,"given":"Feng","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2510-8993","authenticated-orcid":false,"given":"Zheng-Jun","family":"Zha","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref3","article-title":"MMDetection: Open MMLAB detection toolbox and benchmark","author":"Chen","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00511"},{"key":"ref5","first-page":"1","article-title":"Reppoints V2: Verification meets regression for object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen","year":"2020"},{"key":"ref6","article-title":"BEVDistill: Cross-modal BEV distillation for multi-view 3D object detection","author":"Chen","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475351"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074273"},{"key":"ref11","article-title":"RetinaFace: Single-stage dense face localisation in the wild","author":"Deng","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.155"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","article-title":"DenseBox: Unifying landmark localization with end to end object detection","author":"Huang","year":"2015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01204-1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01060"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01146"},{"key":"ref27","first-page":"21002","article-title":"Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Li","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref32","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","author":"Liu","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01306"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00754"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.522"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00984"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00091"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_32"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref43","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"ref44","first-page":"1","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Ren","year":"2015"},{"key":"ref45","article-title":"CrowdHuman: A benchmark for detecting human in a crowd","author":"Shao","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01158"},{"key":"ref47","first-page":"9934","article-title":"What makes for end-to-end object detection?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun","year":"2021"},{"key":"ref48","article-title":"ONENet: Towards end-to-end one-stage object detection","author":"Sun","year":"2020"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01559"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_24"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.529"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3075323"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3085208"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01330"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.596"},{"key":"ref62","article-title":"Efficient DETR: Improving end-to-end object detector with dense prior","author":"Yao","year":"2021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00638"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2909864"},{"key":"ref65","article-title":"ASFD: Automatic and scalable face detector","author":"Zhang","year":"2020"},{"key":"ref66","article-title":"Accurate face detection for high performance","author":"Zhang","year":"2019"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2997456"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_8"},{"key":"ref74","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"ref75","article-title":"Tinaface: Strong but simple baseline for face detection","author":"Zhu","year":"2020"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10093087.pdf?arnumber=10093087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T19:30:29Z","timestamp":1705001429000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10093087\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3264008","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}