{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T04:36:08Z","timestamp":1780806968404,"version":"3.54.1"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100018599","name":"Guangdong Province Key Laboratory of Information Security Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018599","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22-A2095"],"award-info":[{"award-number":["U22-A2095"]}],"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":[[2026,9]]},"DOI":"10.1016\/j.patcog.2026.113333","type":"journal-article","created":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T16:33:06Z","timestamp":1771518786000},"page":"113333","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":3,"special_numbering":"C","title":["CLIP -powered modality centering with spiral training for visible-infrared person re-identification"],"prefix":"10.1016","volume":"177","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4872-2591","authenticated-orcid":false,"given":"Jianghao","family":"Xiong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0310-4679","authenticated-orcid":false,"given":"Xiaohua","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2055-0848","authenticated-orcid":false,"given":"Qinyu","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3883-2024","authenticated-orcid":false,"given":"Jian-Huang","family":"Lai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113333_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110873","article-title":"Visible-infrared person re-identification via patch-mixed cross-modality learning","volume":"157","author":"Qian","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113333_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111301","article-title":"Bidirectional modality information interaction for visible-infrared person re-identification","volume":"161","author":"Yang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113333_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111131","article-title":"Consistency-driven feature scoring and regularization network for visible-infrared person re-identification","volume":"159","author":"Chen","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113333_bib0004","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"1405","article-title":"CLIP-ReID: exploiting vision-language model for image re-identification without concrete text labels","author":"Li","year":"2023"},{"key":"10.1016\/j.patcog.2026.113333_bib0005","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.113333_bib0006","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"6979","article-title":"Multi-prompts learning with cross-modal alignment for attribute-based person re-identification","author":"Zhai","year":"2024"},{"key":"10.1016\/j.patcog.2026.113333_bib0007","series-title":"The 32th ACM International Conference on Multimedia","first-page":"2331","article-title":"Prototypical prompting for text-to-image person re-identification","author":"Yan","year":"2024"},{"key":"10.1016\/j.patcog.2026.113333_bib0008","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"22752","article-title":"Shape-erased feature learning for visible-infrared person re-identification","author":"Feng","year":"2023"},{"key":"10.1016\/j.patcog.2026.113333_bib0009","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"4596","article-title":"High-order structure based middle-feature learning for visible-infrared person re-identification","author":"Qiu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113333_bib0010","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"393","article-title":"Implicit discriminative knowledge learning for visible-infrared person re-identification","author":"Ren","year":"2024"},{"issue":"10","key":"10.1016\/j.patcog.2026.113333_bib0011","doi-asserted-by":"crossref","first-page":"10988","DOI":"10.1109\/TCYB.2022.3183395","article-title":"RBDF: reciprocal bidirectional framework for visible infrared person reidentification","volume":"52","author":"Wei","year":"2022","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.patcog.2026.113333_bib0012","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"18621","article-title":"PartMix: regularization strategy to learn part discovery for visible-infrared person re-identification","author":"Kim","year":"2023"},{"issue":"4","key":"10.1016\/j.patcog.2026.113333_bib0013","doi-asserted-by":"crossref","first-page":"2299","DOI":"10.1109\/TPAMI.2023.3332875","article-title":"Channel augmentation for visible-infrared re-identification","volume":"46","author":"Ye","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113333_bib0014","series-title":"The 30th ACM International Conference on Multimedia","first-page":"2843","article-title":"Augmented dual-contrastive aggregation learning for unsupervised visible-infrared person re-identification","author":"Yang","year":"2022"},{"issue":"4","key":"10.1016\/j.patcog.2026.113333_bib0015","doi-asserted-by":"crossref","first-page":"2706","DOI":"10.1109\/TCSVT.2023.3310015","article-title":"Cross-modality hierarchical clustering and refinement for unsupervised visible-infrared person re-identification","volume":"34","author":"Pang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113333_bib0016","doi-asserted-by":"crossref","first-page":"6032","DOI":"10.1109\/TIP.2023.3327924","article-title":"CLIP-driven fine-grained text-image person re-identification","volume":"32","author":"Yan","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113333_bib0017","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"27187","article-title":"Noisy-correspondence learning for text-to-image person re-identification","author":"Qin","year":"2024"},{"key":"10.1016\/j.patcog.2026.113333_bib0018","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"6764","article-title":"TF-CLIP: learning text-free CLIP for video-based person re-identification","author":"Yu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113333_bib0019","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"17343","article-title":"A pedestrian is worth one prompt: towards language guidance person re- identification","author":"Yang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113333_bib0020","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.113333_bib0021","doi-asserted-by":"crossref","first-page":"2112","DOI":"10.1109\/TMM.2024.3521764","article-title":"CLIP-based modality compensation for visible-infrared image re-identification","volume":"27","author":"Hu","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113333_bib0022","article-title":"CLIP-driven semantic discovery network for visible-infrared person re-identification","author":"Yu","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113333_bib0023","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021"},{"key":"10.1016\/j.patcog.2026.113333_bib0024","series-title":"Advances in Neural Information Processing Systems","article-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","year":"2022"},{"key":"10.1016\/j.patcog.2026.113333_bib0025","series-title":"International Conference on Machine Learning","first-page":"19730","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.patcog.2026.113333_bib0026","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"19175","article-title":"Image as a foreign language: BEIT pretraining for vision and vision-language tasks","author":"Wang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113333_bib0027","series-title":"Advances in Neural Information Processing Systems","first-page":"34892","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113333_bib0028","series-title":"International Conference on Learning Representations","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.patcog.2026.113333_bib0029","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.patcog.2026.113333_bib0030","doi-asserted-by":"crossref","first-page":"2872","DOI":"10.1109\/TPAMI.2021.3054775","article-title":"Deep learning for person re-identification: a survey and outlook","volume":"44","author":"Ye","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113333_bib0031","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.patcog.2026.113333_bib0032","series-title":"IEEE International Conference on Computer Vision","first-page":"5390","article-title":"RGB-infrared cross-modality person re-identification","author":"Wu","year":"2017"},{"key":"10.1016\/j.patcog.2026.113333_bib0033","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2153","article-title":"Diverse embedding expansion network and low-light cross-modality benchmark for visible-infrared person re-identification","author":"Zhang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113333_bib0034","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13662","article-title":"Similarity metric learning for RGB-infrared group re-identification","author":"Xiong","year":"2023"},{"key":"10.1016\/j.patcog.2026.113333_bib0035","series-title":"IEEE\/CVF International Conference on Computer Vision","first-page":"11236","article-title":"Visible-infrared person re-identification via semantic alignment and affinity inference","author":"Fang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113333_bib0036","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"ImageNet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.patcog.2026.113333_bib0037","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"1835","article-title":"Learning progressive modality-shared transformers for effective visible-infrared person re-identification","author":"Lu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113333_bib0038","doi-asserted-by":"crossref","first-page":"9026","DOI":"10.1109\/TIFS.2024.3426335","article-title":"Unified conditional image generation for visible-infrared person re-identification","volume":"19","author":"Pan","year":"2024","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.patcog.2026.113333_bib0039","series-title":"The 29th ACM International Conference on Multimedia","first-page":"788","article-title":"Towards a unified middle modality learning for visible-infrared person re-Identification","author":"Zhang","year":"2021"},{"key":"10.1016\/j.patcog.2026.113333_bib0040","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR","first-page":"14288","article-title":"Learning with twin noisy labels for visible-infrared person re-identification","author":"Yang","year":"2022"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326002980?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326002980?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:45:57Z","timestamp":1777567557000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326002980"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":40,"alternative-id":["S0031320326002980"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113333","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CLIP -powered modality centering with spiral training for visible-infrared person re-identification","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113333","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":"113333"}}