{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T16:08:24Z","timestamp":1784563704653,"version":"3.55.0"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010814","name":"Department of Education of Anhui Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010814","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.engappai.2026.115550","type":"journal-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T07:02:21Z","timestamp":1782975741000},"page":"115550","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P4","title":["Grayscale collaborative learning for cross-modal person re-identification"],"prefix":"10.1016","volume":"181","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9303-8574","authenticated-orcid":false,"given":"Xianju","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cuiqun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junwei","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.115550_b1","series-title":"European Conference on Computer Vision","first-page":"720","article-title":"Visible-infrared person re-identification using privileged intermediate information","author":"Alehdaghi","year":"2022"},{"key":"10.1016\/j.engappai.2026.115550_b2","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Alexey","year":"2020"},{"key":"10.1016\/j.engappai.2026.115550_b3","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.engappai.2026.115550_b4","series-title":"Transunet: Transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021"},{"key":"10.1016\/j.engappai.2026.115550_b5","doi-asserted-by":"crossref","unstructured":"Chen, X., Yan, B., Zhu, J., Wang, D., Yang, X., Lu, H., 2021. Transformer tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 8126\u20138135.","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"10.1016\/j.engappai.2026.115550_b6","doi-asserted-by":"crossref","unstructured":"Chen, C., Ye, M., Qi, M., Du, B., 2022. Sketch transformer: Asymmetrical disentanglement learning from dynamic synthesis. In: Proceedings of the 30th ACM International Conference on Multimedia. pp. 4012\u20134020.","DOI":"10.1145\/3503161.3547993"},{"key":"10.1016\/j.engappai.2026.115550_b7","doi-asserted-by":"crossref","unstructured":"Cheng, D., Gong, Y., Zhou, S., Wang, J., Zheng, N., 2016. Person re-identification by multi-channel parts-based CNN with improved triplet loss function. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1335\u20131344.","DOI":"10.1109\/CVPR.2016.149"},{"key":"10.1016\/j.engappai.2026.115550_b8","first-page":"6","article-title":"Cross-modality person re-identification with generative adversarial training","volume":"vol. 1","author":"Dai","year":"2018"},{"key":"10.1016\/j.engappai.2026.115550_b9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L., 2009. Imagenet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition. pp. 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"10.1016\/j.engappai.2026.115550_b10","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Carreira, J., Doersch, C., Zisserman, A., 2019. Video action transformer network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 244\u2013253.","DOI":"10.1109\/CVPR.2019.00033"},{"key":"10.1016\/j.engappai.2026.115550_b11","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1016\/j.neucom.2020.04.060","article-title":"Learning multi-level domain invariant features for sketch re-identification","volume":"403","author":"Gui","year":"2020","journal-title":"Neurocomputing"},{"key":"10.1016\/j.engappai.2026.115550_b12","first-page":"8385","article-title":"HSME: Hypersphere manifold embedding for visible thermal person re-identification","volume":"vol. 33","author":"Hao","year":"2019"},{"key":"10.1016\/j.engappai.2026.115550_b13","doi-asserted-by":"crossref","unstructured":"Hao, X., Zhao, S., Ye, M., Shen, J., 2021. Cross-modality person re-identification via modality confusion and center aggregation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 16403\u201316412.","DOI":"10.1109\/ICCV48922.2021.01609"},{"key":"10.1016\/j.engappai.2026.115550_b14","doi-asserted-by":"crossref","unstructured":"He, S., Luo, H., Wang, P., Wang, F., Li, H., Jiang, W., 2021. TransReID: Transformer-based object re-identification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 15013\u201315022.","DOI":"10.1109\/ICCV48922.2021.01474"},{"issue":"8","key":"10.1016\/j.engappai.2026.115550_b15","doi-asserted-by":"crossref","first-page":"5095","DOI":"10.1109\/TCSVT.2022.3147813","article-title":"Adversarial decoupling and modality-invariant representation learning for visible-infrared person re-identification","volume":"32","author":"Hu","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"8","key":"10.1016\/j.engappai.2026.115550_b16","doi-asserted-by":"crossref","first-page":"5095","DOI":"10.1109\/TCSVT.2022.3147813","article-title":"Adversarial decoupling and modality-invariant representation learning for visible-infrared person re-identification","volume":"32","author":"Hu","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.engappai.2026.115550_b17","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part VII 16","first-page":"735","article-title":"Global distance-distributions separation for unsupervised person re-identification","author":"Jin","year":"2020"},{"key":"10.1016\/j.engappai.2026.115550_b18","first-page":"4610","article-title":"Infrared-visible cross-modal person re-identification with an X modality","volume":"vol. 34","author":"Li","year":"2020"},{"key":"10.1016\/j.engappai.2026.115550_b19","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XI 16","first-page":"456","article-title":"Interpretable and generalizable person re-identification with query-adaptive convolution and temporal lifting","author":"Liao","year":"2020"},{"key":"10.1016\/j.engappai.2026.115550_b20","doi-asserted-by":"crossref","unstructured":"Lin, H., Fu, Y., Lu, P., Gong, S., Xue, X., Jiang, Y.G., 2019. Tc-net for isbir: Triplet classification network for instance-level sketch based image retrieval. In: Proceedings of the 27th ACM International Conference on Multimedia. pp. 1676\u20131684.","DOI":"10.1145\/3343031.3350900"},{"key":"10.1016\/j.engappai.2026.115550_b21","first-page":"3747","article-title":"Differentiable auxiliary learning for sketch re-identification","volume":"vol. 38","author":"Liu","year":"2024"},{"key":"10.1016\/j.engappai.2026.115550_b22","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.engappai.2026.115550_b23","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXVII 16","first-page":"159","article-title":"Unsupervised domain adaptation in the dissimilarity space for person re-identification","author":"Mekhazni","year":"2020"},{"issue":"3","key":"10.1016\/j.engappai.2026.115550_b24","doi-asserted-by":"crossref","first-page":"605","DOI":"10.3390\/s17030605","article-title":"Person recognition system based on a combination of body images from visible light and thermal cameras","volume":"17","author":"Nguyen","year":"2017","journal-title":"Sensors"},{"key":"10.1016\/j.engappai.2026.115550_b25","doi-asserted-by":"crossref","unstructured":"Pang, L., Wang, Y., Song, Y.Z., Huang, T., Tian, Y., 2018. Cross-domain adversarial feature learning for sketch re-identification. In: Proceedings of the 26th ACM International Conference on Multimedia. pp. 609\u2013617.","DOI":"10.1145\/3240508.3240606"},{"key":"10.1016\/j.engappai.2026.115550_b26","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1109\/TIFS.2020.3013209","article-title":"Soft semantic representation for cross-domain face recognition","volume":"16","author":"Peng","year":"2020","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"issue":"1","key":"10.1016\/j.engappai.2026.115550_b27","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1007\/s00138-022-01368-w","article-title":"Visible-infrared person re-identification model based on feature consistency and modal indistinguishability","volume":"34","author":"Sun","year":"2023","journal-title":"Mach. Vis. Appl."},{"issue":"11","key":"10.1016\/j.engappai.2026.115550_b28","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.engappai.2026.115550_b29","unstructured":"Vaswani, A., 2017. Attention is all you need. In: Advances in Neural Information Processing Systems."},{"key":"10.1016\/j.engappai.2026.115550_b30","doi-asserted-by":"crossref","first-page":"30949","DOI":"10.1109\/ACCESS.2022.3159805","article-title":"Feature fusion and center aggregation for visible-infrared person re-identification","volume":"10","author":"Wang","year":"2022","journal-title":"IEEE Access"},{"key":"10.1016\/j.engappai.2026.115550_b31","doi-asserted-by":"crossref","first-page":"122038","DOI":"10.1109\/ACCESS.2022.3222267","article-title":"Global and part feature fusion for cross-modality person re-identification","volume":"10","author":"Wang","year":"2022","journal-title":"IEEE Access"},{"key":"10.1016\/j.engappai.2026.115550_b32","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wang, Z., Zheng, Y., Chuang, Y.Y., Satoh, S.I., 2019. Learning to reduce dual-level discrepancy for infrared-visible person re-identification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 618\u2013626.","DOI":"10.1109\/CVPR.2019.00071"},{"key":"10.1016\/j.engappai.2026.115550_b33","doi-asserted-by":"crossref","unstructured":"Wang, G.A., Zhang, T., Cheng, J., Liu, S., Yang, Y., Hou, Z., 2019. RGB-infrared cross-modality person re-identification via joint pixel and feature alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 3623\u20133632.","DOI":"10.1109\/ICCV.2019.00372"},{"key":"10.1016\/j.engappai.2026.115550_b34","doi-asserted-by":"crossref","unstructured":"Wang, G.A., Zhang, T., Cheng, J., Liu, S., Yang, Y., Hou, Z., 2019. RGB-infrared cross-modality person re-identification via joint pixel and feature alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 3623\u20133632.","DOI":"10.1109\/ICCV.2019.00372"},{"key":"10.1016\/j.engappai.2026.115550_b35","first-page":"12144","article-title":"Cross-modality paired-images generation for RGB-infrared person re-identification","volume":"vol. 34","author":"Wang","year":"2020"},{"key":"10.1016\/j.engappai.2026.115550_b36","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"5380","article-title":"RGB-infrared cross-modality person re-identification","author":"Wu","year":"2017"},{"key":"10.1016\/j.engappai.2026.115550_b37","doi-asserted-by":"crossref","unstructured":"Wu, A., Zheng, W.S., Yu, H.X., Gong, S., Lai, J., 2017b. RGB-infrared cross-modality person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 5380\u20135389.","DOI":"10.1109\/ICCV.2017.575"},{"key":"10.1016\/j.engappai.2026.115550_b38","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115550_b39","doi-asserted-by":"crossref","first-page":"2347","DOI":"10.1109\/TMM.2020.3009476","article-title":"Instance-level heterogeneous domain adaptation for limited-labeled sketch-to-photo retrieval","volume":"23","author":"Yang","year":"2020","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.engappai.2026.115550_b40","doi-asserted-by":"crossref","first-page":"2347","DOI":"10.1109\/TMM.2020.3009476","article-title":"Instance-level heterogeneous domain adaptation for limited-labeled sketch-to-photo retrieval","volume":"23","author":"Yang","year":"2020","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.engappai.2026.115550_b41","article-title":"Hierarchical discriminative learning for visible thermal person re-identification","volume":"vol. 32","author":"Ye","year":"2018"},{"key":"10.1016\/j.engappai.2026.115550_b42","doi-asserted-by":"crossref","first-page":"728","DOI":"10.1109\/TIFS.2020.3001665","article-title":"Visible-infrared person re-identification via homogeneous augmented tri-modal learning","volume":"16","author":"Ye","year":"2020","journal-title":"Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.engappai.2026.115550_b43","series-title":"DF2AM: dual-level feature fusion and affinity modeling for RGB-infrared cross-modality person re-identification","author":"Yin","year":"2021"},{"issue":"2","key":"10.1016\/j.engappai.2026.115550_b44","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1007\/s11263-020-01382-3","article-title":"Fine-grained instance-level sketch-based image retrieval","volume":"129","author":"Yu","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.engappai.2026.115550_b45","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Lan, C., Zeng, W., Chen, Z., 2020. Multi-granularity reference-aided attentive feature aggregation for video-based person re-identification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10407\u201310416.","DOI":"10.1109\/CVPR42600.2020.01042"},{"key":"10.1016\/j.engappai.2026.115550_b46","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, Y., Li, H., Li, S., 2022. Cross-compatible embedding and semantic consistent feature construction for sketch re-identification. In: Proceedings of the 30th ACM International Conference on Multimedia. pp. 3347\u20133355.","DOI":"10.1145\/3503161.3548224"},{"key":"10.1016\/j.engappai.2026.115550_b47","doi-asserted-by":"crossref","unstructured":"Zhao, L., Li, X., Zhuang, Y., Wang, J., 2017. Deeply-learned part-aligned representations for person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 3219\u20133228.","DOI":"10.1109\/ICCV.2017.349"},{"key":"10.1016\/j.engappai.2026.115550_b48","doi-asserted-by":"crossref","first-page":"6951","DOI":"10.1109\/TIP.2022.3217697","article-title":"Visible-infrared person re-identification via partially interactive collaboration","volume":"31","author":"Zheng","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.engappai.2026.115550_b49","series-title":"Person re-identification: Past, present and future","author":"Zheng","year":"2016"},{"issue":"1","key":"10.1016\/j.engappai.2026.115550_b50","first-page":"1","article-title":"A discriminatively learned CNN embedding for person reidentification","volume":"14","author":"Zheng","year":"2017","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl. (TOMM)"},{"key":"10.1016\/j.engappai.2026.115550_b51","series-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"10.1016\/j.engappai.2026.115550_b52","doi-asserted-by":"crossref","first-page":"3421","DOI":"10.1109\/TIFS.2022.3208811","article-title":"Cross-domain attention and center loss for sketch re-identification","volume":"17","author":"Zhu","year":"2022","journal-title":"IEEE Trans. Inf. Forensics Secur."}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626018348?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626018348?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T15:46:42Z","timestamp":1784562402000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626018348"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":52,"alternative-id":["S0952197626018348"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115550","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Grayscale collaborative learning for cross-modal person re-identification","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115550","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":"115550"}}