{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T20:24:59Z","timestamp":1783023899855,"version":"3.54.6"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302378"],"award-info":[{"award-number":["62302378"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302359"],"award-info":[{"award-number":["62302359"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114190","type":"journal-article","created":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T06:32:52Z","timestamp":1780727572000},"page":"114190","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["ITDRCNN: An Interactive Task-Decoupled RCNN for enhanced object detection"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9660-3460","authenticated-orcid":false,"given":"Shuai","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0579-1716","authenticated-orcid":false,"given":"Hang","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yining","family":"Quan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunwei","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiguang","family":"Miao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114190_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111549","article-title":"Adaptive spatial and scale label assignment for anchor-free object detection","volume":"164","author":"Dang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114190_b2","article-title":"Styleshot: A snapshot on any style","author":"Gao","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114190_b3","doi-asserted-by":"crossref","first-page":"1348","DOI":"10.1109\/TIP.2024.3362062","article-title":"Learning domain invariant prompt for vision-language models","volume":"33","author":"Zhao","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114190_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109627","article-title":"CPSS-FAT: A consistent positive sample selection for object detection with full adaptive threshold","volume":"141","author":"Yang","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114190_b5","series-title":"Advances in Neural Information Processing Systems","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"Ren","year":"2015"},{"key":"10.1016\/j.patcog.2026.114190_b6","doi-asserted-by":"crossref","unstructured":"G. Song, Y. Liu, X. Wang, Revisiting the sibling head in object detector, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11563\u201311572.","DOI":"10.1109\/CVPR42600.2020.01158"},{"key":"10.1016\/j.patcog.2026.114190_b7","doi-asserted-by":"crossref","unstructured":"Y. Wu, Y. Chen, L. Yuan, Z. Liu, L. Wang, H. Li, Y. Fu, Rethinking classification and localization for object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 10186\u201310195.","DOI":"10.1109\/CVPR42600.2020.01020"},{"issue":"9","key":"10.1016\/j.patcog.2026.114190_b8","doi-asserted-by":"crossref","first-page":"6324","DOI":"10.1109\/TCSVT.2022.3167114","article-title":"Decoupled R-CNN: Sensitivity-specific detector for higher accurate localization","volume":"32","author":"Wang","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114190_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109878","article-title":"Feature disentanglement in one-stage object detection","volume":"145","author":"Lin","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114190_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109377","article-title":"Cascaded feature fusion with multi-level self-attention mechanism for object detection","volume":"138","author":"Wang","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114190_b11","doi-asserted-by":"crossref","first-page":"2058","DOI":"10.1109\/TMM.2021.3075323","article-title":"Deformable template network (DTN) for object detection","volume":"24","author":"Wu","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.114190_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110569","article-title":"LDDMM-face: Large deformation diffeomorphic metric learning for cross-annotation face alignment","volume":"154","author":"Yang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114190_b13","doi-asserted-by":"crossref","unstructured":"J. Pang, K. Chen, J. Shi, H. Feng, W. Ouyang, D. Lin, Libra r-cnn: Towards balanced learning for object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 821\u2013830.","DOI":"10.1109\/CVPR.2019.00091"},{"key":"10.1016\/j.patcog.2026.114190_b14","doi-asserted-by":"crossref","unstructured":"P. Sun, R. Zhang, Y. Jiang, T. Kong, C. Xu, W. Zhan, M. Tomizuka, L. Li, Z. Yuan, C. Wang, et al., Sparse r-cnn: End-to-end object detection with learnable proposals, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 14454\u201314463.","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"10.1016\/j.patcog.2026.114190_b15","doi-asserted-by":"crossref","unstructured":"J. Redmon, S. Divvala, R. Girshick, A. Farhadi, You only look once: Unified, real-time object detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 779\u2013788.","DOI":"10.1109\/CVPR.2016.91"},{"key":"10.1016\/j.patcog.2026.114190_b16","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"21","article-title":"Ssd: Single shot multibox detector","author":"Liu","year":"2016"},{"key":"10.1016\/j.patcog.2026.114190_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111425","article-title":"FSENet: Feature suppression and enhancement network for tiny object detection","author":"Hu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114190_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110330","article-title":"GPONet: A two-stream gated progressive optimization network for salient object detection","volume":"150","author":"Yi","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114190_b19","doi-asserted-by":"crossref","unstructured":"K. Oksuz, B.C. Cam, E. Akbas, S. Kalkan, Rank & sort loss for object detection and instance segmentation, in: Proceedings of the IEEE International Conference on Computer Vision, 2021, pp. 3009\u20133018.","DOI":"10.1109\/ICCV48922.2021.00300"},{"key":"10.1016\/j.patcog.2026.114190_b20","doi-asserted-by":"crossref","unstructured":"S. Zhang, C. Chi, Y. Yao, Z. Lei, S.Z. Li, Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2020, pp. 9759\u20139768.","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"10.1016\/j.patcog.2026.114190_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111275","article-title":"DrKD: Decoupling response-based distillation for object detection","volume":"161","author":"Lv","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114190_b22","doi-asserted-by":"crossref","unstructured":"H. Law, J. Deng, Cornernet: Detecting objects as paired keypoints, in: Proceedings of the European Conference on Computer Vision, 2018, pp. 734\u2013750.","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"10.1016\/j.patcog.2026.114190_b23","doi-asserted-by":"crossref","unstructured":"K. Duan, S. Bai, L. Xie, H. Qi, Q. Huang, Q. Tian, Centernet: Keypoint triplets for object detection, in: Proceedings of the IEEE International Conference on Computer Vision, 2019, pp. 6569\u20136578.","DOI":"10.1109\/ICCV.2019.00667"},{"key":"10.1016\/j.patcog.2026.114190_b24","doi-asserted-by":"crossref","unstructured":"Z. Tian, C. Shen, H. Chen, T. He, Fcos: Fully convolutional one-stage object detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 9627\u20139636.","DOI":"10.1109\/ICCV.2019.00972"},{"key":"10.1016\/j.patcog.2026.114190_b25","series-title":"European Conference on Computer Vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.patcog.2026.114190_b26","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.120539","article-title":"HA-transformer: Harmonious aggregation from local to global for object detection","volume":"230","author":"Chen","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2026.114190_b27","unstructured":"S. Liu, F. Li, H. Zhang, X. Yang, X. Qi, H. Su, J. Zhu, L. Zhang, DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR, in: International Conference on Learning Representations, 2022."},{"key":"10.1016\/j.patcog.2026.114190_b28","doi-asserted-by":"crossref","unstructured":"F. Li, H. Zhang, S. Liu, J. Guo, L.M. Ni, L. Zhang, Dn-detr: Accelerate detr training by introducing query denoising, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 13619\u201313627.","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"10.1016\/j.patcog.2026.114190_b29","article-title":"ASCFormer: An adaptive strucure-aware cascaded transformer for 3D object detection","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114190_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110976","article-title":"Tbnet: A texture and boundary-aware network for small weak object detection in remote-sensing imagery","volume":"158","author":"Li","year":"2025","journal-title":"Pattern Recognit."},{"issue":"27","key":"10.1016\/j.patcog.2026.114190_b31","doi-asserted-by":"crossref","DOI":"10.1002\/cpe.7246","article-title":"Disentangling classification and regression in siamese-based network for visual tracking","volume":"34","author":"Zhang","year":"2022","journal-title":"Concurr. Comput.: Pr. Exp."},{"key":"10.1016\/j.patcog.2026.114190_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2022.102205","article-title":"Dual attentional siamese network for visual tracking","volume":"74","author":"Zhang","year":"2022","journal-title":"Displays"},{"key":"10.1016\/j.patcog.2026.114190_b33","doi-asserted-by":"crossref","unstructured":"Z. Yang, S. Liu, H. Hu, L. Wang, S. Lin, Reppoints: Point set representation for object detection, in: Proceedings of the IEEE International Conference on Computer Vision, 2019, pp. 9657\u20139666.","DOI":"10.1109\/ICCV.2019.00975"},{"key":"10.1016\/j.patcog.2026.114190_b34","first-page":"3309","article-title":"LGD: Label-guided self-distillation for object detection","volume":"vol. 36","author":"Zhang","year":"2022"},{"key":"10.1016\/j.patcog.2026.114190_b35","doi-asserted-by":"crossref","first-page":"3092","DOI":"10.1109\/TIP.2019.2957850","article-title":"HAR-net: Joint learning of hybrid attention for single-stage object detection","volume":"29","author":"Li","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114190_b36","article-title":"Learning to match anchors for visual object detection","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114190_b37","doi-asserted-by":"crossref","first-page":"2153","DOI":"10.1109\/TMM.2022.3143707","article-title":"Latent feature pyramid network for object detection","volume":"25","author":"Xie","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.114190_b38","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.126375","article-title":"EJRSNet: A joint mechanism network for object detection with efficient receiving and sending of hierarchical feature information","volume":"268","author":"Zhang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2026.114190_b39","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110620","article-title":"MixingMask: A contour-aware approach for joint object detection and instance segmentation","volume":"155","author":"Ouyang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114190_b40","doi-asserted-by":"crossref","unstructured":"T.Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Doll\u00e1r, C.L. Zitnick, Microsoft COCO: Common Objects in Context, in: Proceedings of the European Conference on Computer Vision, 2014, pp. 740\u2013755.","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"2","key":"10.1016\/j.patcog.2026.114190_b41","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (voc) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.114190_b42","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125871","article-title":"Learning to zoom: Exploiting mixed-scale contextual information for object detection","volume":"264","author":"Wang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2026.114190_b43","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110172","article-title":"GhostFormer: Efficiently amalgamated CNN-transformer architecture for object detection","volume":"148","author":"Xie","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114190_b44","doi-asserted-by":"crossref","unstructured":"X. Dai, Y. Chen, J. Yang, P. Zhang, L. Yuan, L. Zhang, Dynamic detr: End-to-end object detection with dynamic attention, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 2988\u20132997.","DOI":"10.1109\/ICCV48922.2021.00298"},{"key":"10.1016\/j.patcog.2026.114190_b45","first-page":"2567","article-title":"Anchor detr: Query design for transformer-based detector","volume":"vol. 36","author":"Wang","year":"2022"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326011556?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326011556?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T19:56:55Z","timestamp":1783022215000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326011556"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":45,"alternative-id":["S0031320326011556"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114190","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"ITDRCNN: An Interactive Task-Decoupled RCNN for enhanced object detection","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114190","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114190"}}