{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T17:25:10Z","timestamp":1772645110227,"version":"3.50.1"},"reference-count":46,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276246"],"award-info":[{"award-number":["62276246"]}],"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":[[2024,6]]},"DOI":"10.1016\/j.patcog.2024.110361","type":"journal-article","created":{"date-parts":[[2024,2,21]],"date-time":"2024-02-21T11:53:30Z","timestamp":1708516410000},"page":"110361","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Enhancing identification for person search with multi-scale multi-grained representation learning"],"prefix":"10.1016","volume":"150","author":[{"given":"Zhixiong","family":"Han","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingpeng","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2024.110361_b1","doi-asserted-by":"crossref","unstructured":"L. Zheng, H. Zhang, S. Sun, M. Chandraker, Y. Yang, Q. Tian, Person re-identification in the wild, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2017, pp. 1367\u20131376.","DOI":"10.1109\/CVPR.2017.357"},{"key":"10.1016\/j.patcog.2024.110361_b2","doi-asserted-by":"crossref","unstructured":"D. Chen, S. Zhang, W. Ouyang, J. Yang, Y. Tai, Person search via a mask-guided two-stream cnn model, in: Proceedings of the European Conference on Computer Vision, 2018, pp. 734\u2013750.","DOI":"10.1007\/978-3-030-01234-2_45"},{"key":"10.1016\/j.patcog.2024.110361_b3","doi-asserted-by":"crossref","unstructured":"C. Wang, B. Ma, H. Chang, S. Shan, X. Chen, Tcts: A task-consistent two-stage framework for person search, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11952\u201311961.","DOI":"10.1109\/CVPR42600.2020.01197"},{"key":"10.1016\/j.patcog.2024.110361_b4","doi-asserted-by":"crossref","unstructured":"C. Han, J. Ye, Y. Zhong, X. Tan, C. Zhang, C. Gao, N. Sang, Re-id driven localization refinement for person search, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 9814\u20139823.","DOI":"10.1109\/ICCV.2019.00991"},{"key":"10.1016\/j.patcog.2024.110361_b5","doi-asserted-by":"crossref","unstructured":"X. Lan, X. Zhu, S. Gong, Person search by multi-scale matching, in: Proceedings of the European Conference on Computer Vision, 2018, pp. 536\u2013552.","DOI":"10.1007\/978-3-030-01246-5_33"},{"key":"10.1016\/j.patcog.2024.110361_b6","doi-asserted-by":"crossref","unstructured":"W. Dong, Z. Zhang, C. Song, T. Tan, Instance guided proposal network for person search, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 2585\u20132594.","DOI":"10.1109\/CVPR42600.2020.00266"},{"key":"10.1016\/j.patcog.2024.110361_b7","doi-asserted-by":"crossref","unstructured":"T. Xiao, S. Li, B. Wang, L. Lin, X. Wang, Joint detection and identification feature learning for person search, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2017, pp. 3415\u20133424.","DOI":"10.1109\/CVPR.2017.360"},{"key":"10.1016\/j.patcog.2024.110361_b8","doi-asserted-by":"crossref","unstructured":"Z. Li, D. Miao, Sequential end-to-end network for efficient person search, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, 2021, pp. 2011\u20132019.","DOI":"10.1609\/aaai.v35i3.16297"},{"key":"10.1016\/j.patcog.2024.110361_b9","doi-asserted-by":"crossref","unstructured":"D. Chen, S. Zhang, J. Yang, B. Schiele, Norm-aware embedding for efficient person search, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 12615\u201312624.","DOI":"10.1109\/CVPR42600.2020.01263"},{"key":"10.1016\/j.patcog.2024.110361_b10","doi-asserted-by":"crossref","unstructured":"Y. Yan, J. Li, J. Qin, S. Bai, S. Liao, L. Liu, F. Zhu, L. Shao, Anchor-free person search, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 7690\u20137699.","DOI":"10.1109\/CVPR46437.2021.00760"},{"key":"10.1016\/j.patcog.2024.110361_b11","doi-asserted-by":"crossref","unstructured":"Y. Zhong, X. Wang, S. Zhang, Robust partial matching for person search in the wild, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 6827\u20136835.","DOI":"10.1109\/CVPR42600.2020.00686"},{"key":"10.1016\/j.patcog.2024.110361_b12","doi-asserted-by":"crossref","unstructured":"D. Chen, S. Zhang, W. Ouyang, J. Yang, B. Schiele, Hierarchical online instance matching for person search, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34, 2020, pp. 10518\u201310525.","DOI":"10.1609\/aaai.v34i07.6623"},{"key":"10.1016\/j.patcog.2024.110361_b13","doi-asserted-by":"crossref","unstructured":"W. Dong, Z. Zhang, C. Song, T. Tan, Bi-directional interaction network for person search, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 2839\u20132848.","DOI":"10.1109\/CVPR42600.2020.00291"},{"key":"10.1016\/j.patcog.2024.110361_b14","doi-asserted-by":"crossref","unstructured":"C. Han, Z. Zheng, C. Gao, N. Sang, Y. Yang, Decoupled and memory-reinforced networks: Towards effective feature learning for one-step person search, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, 2021, pp. 1505\u20131512.","DOI":"10.1609\/aaai.v35i2.16241"},{"key":"10.1016\/j.patcog.2024.110361_b15","doi-asserted-by":"crossref","unstructured":"H. Kim, S. Joung, I.-J. Kim, K. Sohn, Prototype-guided saliency feature learning for person search, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 4865\u20134874.","DOI":"10.1109\/CVPR46437.2021.00483"},{"key":"10.1016\/j.patcog.2024.110361_b16","doi-asserted-by":"crossref","unstructured":"B.-J. Han, K. Ko, J.-Y. Sim, End-to-end trainable trident person search network using adaptive gradient propagation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 925\u2013933.","DOI":"10.1109\/ICCV48922.2021.00096"},{"key":"10.1016\/j.patcog.2024.110361_b17","doi-asserted-by":"crossref","unstructured":"R. Yu, D. Du, R. LaLonde, D. Davila, C. Funk, A. Hoogs, B. Clipp, Cascade Transformers for End-to-End Person Search, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 7267\u20137276.","DOI":"10.1109\/CVPR52688.2022.00712"},{"key":"10.1016\/j.patcog.2024.110361_b18","doi-asserted-by":"crossref","unstructured":"J. Cao, Y. Pang, R.M. Anwer, H. Cholakkal, J. Xie, M. Shah, F.S. Khan, PSTR: End-to-End One-Step Person Search With Transformers, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 9458\u20139467.","DOI":"10.1109\/CVPR52688.2022.00924"},{"key":"10.1016\/j.patcog.2024.110361_b19","first-page":"1","article-title":"Efficient person search: An anchor-free approach","author":"Yan","year":"2023","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2024.110361_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.108654","article-title":"Making person search enjoy the merits of person re-identification","volume":"127","author":"Liu","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2024.110361_b21","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2024.110361_b22","unstructured":"X. Zhu, W. Su, L. Lu, B. Li, X. Wang, J. Dai, Deformable DETR: Deformable Transformers for End-to-End Object Detection, in: International Conference on Learning Representations, 2021."},{"key":"10.1016\/j.patcog.2024.110361_b23","doi-asserted-by":"crossref","unstructured":"T.-Y. Lin, P. Goyal, R. Girshick, K. He, P. Doll\u00e1r, Focal loss for dense object detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2017, pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"10.1016\/j.patcog.2024.110361_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.2024.110361_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109837","article-title":"Learning consistent region features for lifelong person re-identification","volume":"144","author":"Huang","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2024.110361_b26","article-title":"Joint discriminative representation learning for end-to-end person search","author":"Zhang","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2024.110361_b27","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, N. Houlsby, An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, in: International Conference on Learning Representations, 2021."},{"key":"10.1016\/j.patcog.2024.110361_b28","doi-asserted-by":"crossref","unstructured":"W. Wang, E. Xie, X. Li, D.-P. Fan, K. Song, D. Liang, T. Lu, P. Luo, L. Shao, Pyramid vision transformer: A versatile backbone for dense prediction without convolutions, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 568\u2013578.","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"10.1016\/j.patcog.2024.110361_b29","doi-asserted-by":"crossref","unstructured":"Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, B. Guo, Swin transformer: Hierarchical vision transformer using shifted windows, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10.1016\/j.patcog.2024.110361_b30","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume":"34","author":"Chu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2024.110361_b31","unstructured":"C.-F. Chen, R. Panda, Q. Fan, Regionvit: Regional-to-local attention for vision transformers, in: International Conference on Learning Representations, 2022."},{"key":"10.1016\/j.patcog.2024.110361_b32","doi-asserted-by":"crossref","unstructured":"Z. Liu, H. Hu, Y. Lin, Z. Yao, Z. Xie, Y. Wei, J. Ning, Y. Cao, Z. Zhang, L. Dong, et al., Swin transformer v2: Scaling up capacity and resolution, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 12009\u201312019.","DOI":"10.1109\/CVPR52688.2022.01170"},{"issue":"3","key":"10.1016\/j.patcog.2024.110361_b33","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","article-title":"Pvt v2: Improved baselines with pyramid vision transformer","volume":"8","author":"Wang","year":"2022","journal-title":"Comput. Vis. Media"},{"key":"10.1016\/j.patcog.2024.110361_b34","doi-asserted-by":"crossref","unstructured":"N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, S. Zagoruyko, End-to-end object detection with transformers, in: Proceedings of the European Conference on Computer Vision, 2020, pp. 213\u2013229.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"10.1016\/j.patcog.2024.110361_b35","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2024.110361_b36","doi-asserted-by":"crossref","unstructured":"Y. Li, J. He, T. Zhang, X. Liu, Y. Zhang, F. Wu, Diverse part discovery: Occluded person re-identification with part-aware transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 2898\u20132907.","DOI":"10.1109\/CVPR46437.2021.00292"},{"key":"10.1016\/j.patcog.2024.110361_b37","doi-asserted-by":"crossref","unstructured":"Z. Xia, X. Pan, S. Song, L.E. Li, G. Huang, Vision transformer with deformable attention, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4794\u20134803.","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"10.1016\/j.patcog.2024.110361_b38","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.patcog.2024.110361_b39","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1016\/j.patcog.2018.10.028","article-title":"IAN: the individual aggregation network for person search","volume":"87","author":"Xiao","year":"2019","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2024.110361_b40","doi-asserted-by":"crossref","unstructured":"H. Liu, J. Feng, Z. Jie, K. Jayashree, B. Zhao, M. Qi, J. Jiang, S. Yan, Neural person search machines, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 493\u2013501.","DOI":"10.1109\/ICCV.2017.61"},{"key":"10.1016\/j.patcog.2024.110361_b41","doi-asserted-by":"crossref","unstructured":"X. Chang, P.-Y. Huang, Y.-D. Shen, X. Liang, Y. Yang, A.G. Hauptmann, Rcaa: Relational context-aware agents for person search, in: Proceedings of the European Conference on Computer Vision, 2018, pp. 84\u2013100.","DOI":"10.1007\/978-3-030-01240-3_6"},{"key":"10.1016\/j.patcog.2024.110361_b42","doi-asserted-by":"crossref","unstructured":"Y. Yan, Q. Zhang, B. Ni, W. Zhang, M. Xu, X. Yang, Learning context graph for person search, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 2158\u20132167.","DOI":"10.1109\/CVPR.2019.00226"},{"key":"10.1016\/j.patcog.2024.110361_b43","doi-asserted-by":"crossref","unstructured":"B. Munjal, S. Amin, F. Tombari, F. Galasso, Query-guided end-to-end person search, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 811\u2013820.","DOI":"10.1109\/CVPR.2019.00090"},{"key":"10.1016\/j.patcog.2024.110361_b44","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2022.3221079","article-title":"DMRNet++: Learning discriminative features with decoupled networks and enriched pairs for one-step person search","author":"Han","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2024.110361_b45","doi-asserted-by":"crossref","unstructured":"M. Fiaz, H. Cholakkal, R.M. Anwer, F.S. Khan, SAT: Scale-Augmented Transformer for Person Search, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2023, pp. 4820\u20134829.","DOI":"10.1109\/WACV56688.2023.00480"},{"key":"10.1016\/j.patcog.2024.110361_b46","doi-asserted-by":"crossref","unstructured":"L. Jaffe, A. Zakhor, Gallery Filter Network for Person Search, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2023, pp. 1684\u20131693.","DOI":"10.1109\/WACV56688.2023.00173"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320324001122?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320324001122?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T17:21:17Z","timestamp":1758475277000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320324001122"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":46,"alternative-id":["S0031320324001122"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2024.110361","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2024,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Enhancing identification for person search with multi-scale multi-grained representation learning","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2024.110361","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"110361"}}