{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T17:07:13Z","timestamp":1772644033902,"version":"3.50.1"},"reference-count":69,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T00:00:00Z","timestamp":1766534400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T00:00:00Z","timestamp":1766534400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s00371-025-04231-x","type":"journal-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T03:42:58Z","timestamp":1766547778000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing cross-modal person reidentification: multi-scale feature alignment and optimization"],"prefix":"10.1007","volume":"42","author":[{"given":"Tianyu","family":"Zang","sequence":"first","affiliation":[]},{"given":"Yunrui","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Pan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yuwei","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Yuan","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,12,24]]},"reference":[{"key":"4231_CR1","doi-asserted-by":"publisher","unstructured":"He, S., Luo, H., Wang, P., Wang, F., Li, H., Jiang, W.: TransReID: Transformer-based object re-identification, In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 14993\u201315002, (2021) https:\/\/doi.org\/10.1109\/ICCV48922.2021.01474","DOI":"10.1109\/ICCV48922.2021.01474"},{"issue":"1","key":"4231_CR2","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1109\/TCSVT.2022.3199394","volume":"33","author":"S Yang","year":"2023","unstructured":"Yang, S., Liu, W., Yu, Y., Hu, H., Chen, D., Su, T.: Diverse feature learning network with attention suppression and part level background suppression for person re-identification. IEEE Trans. Circuits Syst. Video Technol. 33(1), 283\u2013297 (2023). https:\/\/doi.org\/10.1109\/TCSVT.2022.3199394","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"4","key":"4231_CR3","doi-asserted-by":"publisher","first-page":"486","DOI":"10.1109\/TBIOM.2023.3281357","volume":"5","author":"C Zhao","year":"2023","unstructured":"Zhao, C., et al.: Person Re-Identification with visual semantic representation mining and reasoning. IEEE Trans. Biomet. Behavior Identity Sci. 5(4), 486\u2013497 (2023). https:\/\/doi.org\/10.1109\/TBIOM.2023.3281357","journal-title":"IEEE Trans. Biomet. Behavior Identity Sci."},{"key":"4231_CR4","doi-asserted-by":"publisher","unstructured":"Tan, L., Dai, P., Ji, R., Wu, Y.: Dynamic prototype mask for occluded person re-identification, In: Proceedings of the 30th ACM International Conference on Multimedia (2022) https:\/\/doi.org\/10.1145\/3503161.3547764","DOI":"10.1145\/3503161.3547764"},{"key":"4231_CR5","unstructured":"Wu, A., Zheng, W.-S., Yu, H.-X., Gong, S., Lai, J.: Rgb-infrared cross-modality per-son re-identification. In: Proceedings of the ICCV, pages 5380\u20135389, (2017). 5"},{"issue":"3","key":"4231_CR6","doi-asserted-by":"publisher","first-page":"605","DOI":"10.3390\/s17030605","volume":"17","author":"D Nguyen","year":"2017","unstructured":"Nguyen, D., Hong, H., Kim, K., Park, K.: Person recognition system based on a combination of body images from visible light and thermal cameras. Sensors 17(3), 605 (2017). https:\/\/doi.org\/10.3390\/s17030605","journal-title":"Sensors"},{"key":"4231_CR7","doi-asserted-by":"publisher","unstructured":"Sun, H., et al.: Not all pixels are matched, In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5333\u20135341 (2022) https:\/\/doi.org\/10.1145\/3503161.3547970","DOI":"10.1145\/3503161.3547970"},{"key":"4231_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, H.: Diverse embedding expansion network and low-light cross-modality benchmark for visible-infrared person re-identification, In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2153\u20132162. III-A, I,IV-A (2023)","DOI":"10.1109\/CVPR52729.2023.00214"},{"key":"4231_CR9","doi-asserted-by":"publisher","unstructured":"Ling, Y., et al.: Cross-Modality Earth mover\u2019s distance for visible thermal person re-identification. In: Proceedings of the AAAI Conference on Artificial Intelligence 37(2), 1631\u20131639 (2023). https:\/\/doi.org\/10.1609\/aaai.v37i2.25250","DOI":"10.1609\/aaai.v37i2.25250"},{"key":"4231_CR10","doi-asserted-by":"publisher","unstructured":"Feng, J., Wu, A., Zheng, W.-S.: Shape-erased feature learning for visible-infrared person re-identification, In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023) https:\/\/doi.org\/10.1109\/CVPR52729.2023.02179","DOI":"10.1109\/CVPR52729.2023.02179"},{"key":"4231_CR11","doi-asserted-by":"publisher","unstructured":"Lu, H., Zou, X., Zhang, P.: Learning Progressive Modality-Shared transformers for effective Visible-Infrared Person Re-identification. In: Proceedings of the AAAI Conference on Artificial Intelligence 37(2), 1835\u20131843 (2023). https:\/\/doi.org\/10.1609\/aaai.v37i2.25273","DOI":"10.1609\/aaai.v37i2.25273"},{"issue":"1","key":"4231_CR12","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1109\/TCSVT.2023.3287300","volume":"34","author":"J Qi","year":"2024","unstructured":"Qi, J., Liang, T., Liu, W., Li, Y., Jin, Y.: A generative-based image fusion strategy for visible-infrared person re-identification. IEEE Trans. Circuits Syst. Video Technol. 34(1), 518\u2013533 (2024). https:\/\/doi.org\/10.1109\/TCSVT.2023.3287300","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"11","key":"4231_CR13","doi-asserted-by":"publisher","first-page":"6764","DOI":"10.1109\/TCSVT.2023.3268080","volume":"33","author":"Z Chai","year":"2023","unstructured":"Chai, Z., Ling, Y., Luo, Z., Lin, D., Jiang, M., Li, S.: Dual-stream transformer with distribution alignment for visible-infrared person re-identification. IEEE Trans. Circuits Syst. Video Technol. 33(11), 6764\u20136776 (2023). https:\/\/doi.org\/10.1109\/TCSVT.2023.3268080","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"2","key":"4231_CR14","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/TCSVT.2023.3289170","volume":"34","author":"S Park","year":"2024","unstructured":"Park, S., Vien, A.G., Lee, C.: Cross-Modal transformers for infrared and visible image fusion. IEEE Trans. Circuits Syst. Video Technol. 34(2), 770\u2013785 (2024). https:\/\/doi.org\/10.1109\/TCSVT.2023.3289170","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"8","key":"4231_CR15","doi-asserted-by":"publisher","first-page":"4415","DOI":"10.1109\/TCSVT.2023.3241988","volume":"33","author":"Z Cui","year":"2023","unstructured":"Cui, Z., Zhou, J., Peng, Y., Zhang, S., Wang, Y.: DCR-ReID: Deep component reconstruction for cloth-changing person re-identification. IEEE Trans. Circuits Syst. Video Technol. 33(8), 4415\u20134428 (2023). https:\/\/doi.org\/10.1109\/TCSVT.2023.3241988","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"4231_CR16","doi-asserted-by":"publisher","unstructured":"Zhang, R., Cao, Z., Huang, Y., Yang, S., Xu, L., Xu, M.: Visible-Infrared Person Re-identification with Real-world Label Noise, In: IEEE Transactions on Circuits and Systems for Video Technology, https:\/\/doi.org\/10.1109\/TCSVT.2025.3526449","DOI":"10.1109\/TCSVT.2025.3526449"},{"issue":"4","key":"4231_CR17","doi-asserted-by":"publisher","first-page":"2706","DOI":"10.1109\/TCSVT.2023.3310015","volume":"34","author":"Z Pang","year":"2024","unstructured":"Pang, Z., Wang, C., Zhao, L., Liu, Y., Sharma, G.: Cross-modality hierarchical clustering and refinement for unsupervised visible-infrared person re-identification. IEEE Trans. Circuits Syst. Video Technol. 34(4), 2706\u20132718 (2024). https:\/\/doi.org\/10.1109\/TCSVT.2023.3310015","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"10","key":"4231_CR18","doi-asserted-by":"publisher","first-page":"7226","DOI":"10.1109\/TCSVT.2022.3168999","volume":"32","author":"J Liu","year":"2022","unstructured":"Liu, J., Wang, J., Huang, N., Zhang, Q., Han, J.: Revisiting modality-specific feature compensation for visible-infrared person re-identification. IEEE Trans. Circuits Syst. Video Technol. 32(10), 7226\u20137240 (2022). https:\/\/doi.org\/10.1109\/TCSVT.2022.3168999","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"11","key":"4231_CR19","doi-asserted-by":"publisher","first-page":"12032","DOI":"10.1109\/TCSVT.2024.3425536","volume":"34","author":"H Zhang","year":"2024","unstructured":"Zhang, H., Cheng, S., Du, A.: Multi-stage auxiliary learning for visible-infrared person re-identification. IEEE Trans. Circuits Syst. Video Technol. 34(11), 12032\u201312047 (2024). https:\/\/doi.org\/10.1109\/TCSVT.2024.3425536","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"3","key":"4231_CR20","doi-asserted-by":"publisher","first-page":"1418","DOI":"10.1109\/TCSVT.2021.3072171","volume":"32","author":"X Zhong","year":"2022","unstructured":"Zhong, X., Lu, T., Huang, W., Ye, M., Jia, X., Lin, C.-W.: Grayscale enhancement colorization network for visible-infrared person re-identification. IEEE Trans. Circuits Syst. Video Technol. 32(3), 1418\u20131430 (2022). https:\/\/doi.org\/10.1109\/TCSVT.2021.3072171","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"2","key":"4231_CR21","first-page":"309","volume":"2","author":"Komal Vij","year":"2009","unstructured":"Vij, Komal, Singh, Yaduvir: Enhancement of images using histogram processing techniques. Int. J. Comp. Tech. Appl 2(2), 309\u2013313 (2009)","journal-title":"Int. J. Comp. Tech. Appl"},{"key":"4231_CR22","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.infrared.2015.07.003","volume":"72","author":"W Gan","year":"2015","unstructured":"Gan, W., et al.: Infrared and visible image fusion with the use of multi-scale edge-preserving decomposition and guided image filter. Inf. Phys. Technol. 72, 37\u201351 (2015). https:\/\/doi.org\/10.1016\/j.infrared.2015.07.003","journal-title":"Inf. Phys. Technol."},{"key":"4231_CR23","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1016\/j.neunet.2020.05.008","volume":"128","author":"G Wang","year":"2020","unstructured":"Wang, G., et al.: Cross-modality paired-images generation and augmentation for RGB-infrared person re-identification. Neural Netw. 128, 294\u2013304 (2020). https:\/\/doi.org\/10.1016\/j.neunet.2020.05.008","journal-title":"Neural Netw."},{"key":"4231_CR24","doi-asserted-by":"publisher","unstructured":"Lu, Y., et al.: Cross-Modality person Re-Identification with Shared-Specific feature transfer, In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13376\u201313386 (2020) https:\/\/doi.org\/10.1109\/CVPR42600.2020.01339","DOI":"10.1109\/CVPR42600.2020.01339"},{"issue":"3","key":"4231_CR25","first-page":"6","volume":"1","author":"Pingyang Dai","year":"2018","unstructured":"Dai, Pingyang, et al.: Cross-modality person re-identification with generative adversarial training. IJCAI 1(3), 6 (2018)","journal-title":"IJCAI"},{"key":"4231_CR26","doi-asserted-by":"publisher","unstructured":"Park, H., Lee, S., Lee, J., Ham, B.: Learning by aligning: Visible-infrared person re-identification using cross-modal correspondences, In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) (2021) https:\/\/doi.org\/10.1109\/ICCV48922.2021.01183","DOI":"10.1109\/ICCV48922.2021.01183"},{"key":"4231_CR27","doi-asserted-by":"publisher","first-page":"103703","DOI":"10.1016\/j.cviu.2023.103703","volume":"232","author":"J Gong","year":"2023","unstructured":"Gong, J., Zhao, S., Lam, K.-M., Gao, X., Shen, J.: Spectrum-irrelevant fine-grained representation for visible\u2013infrared person re-identification. Comput. Vis. Image Underst. 232, 103703 (2023). https:\/\/doi.org\/10.1016\/j.cviu.2023.103703","journal-title":"Comput. Vis. Image Underst."},{"key":"4231_CR28","doi-asserted-by":"crossref","unstructured":"Jiang, Na., et al.: Joint Visual-Textual Reasoning and Visible-Infrared Modality Alignment for Person Re-Identification. In: 2024 IEEE International Conference on Multimedia and Expo (ICME). IEEE (2024)","DOI":"10.1109\/ICME57554.2024.10688362"},{"key":"4231_CR29","unstructured":"Jun-Yan, Z., et al.: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks (2020). Available: https:\/\/www.proquest.com\/working-papers\/unpaired-image-translation-using-cycle-consistent\/docview\/2071583150\/se-2"},{"issue":"6","key":"4231_CR30","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1016\/j.vrih.2023.06.003","volume":"5","author":"M Wang","year":"2023","unstructured":"Wang, M., Meng, M., Liu, J., Wu, J.: Adequate alignment and interaction for cross-modal retrieval. Virtual Reality Intell. Hardware 5(6), 509\u2013522 (2023). https:\/\/doi.org\/10.1016\/j.vrih.2023.06.003","journal-title":"Virtual Reality Intell. Hardware"},{"key":"4231_CR31","unstructured":"Alehdaghi, M., Bhattacharya, R., Shamsolmoali, P., Cruz, R.M., Granger, E.: From Cross-Modal to Mixed-Modal Visible-Infrared Re-Identification (2025)"},{"key":"4231_CR32","unstructured":"Li, Yu-Jhe et al.: Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond. arXiv:2002.09274 (2020): n. pag"},{"key":"4231_CR33","doi-asserted-by":"crossref","unstructured":"Lu, Y., et al.: Cross-modality Person re-identification with Shared-Specific Feature Transfer (2020). Available: https:\/\/www.proquest.com\/working-papers\/cross-modality-person-re-identification-with\/docview\/2370237991\/se-2","DOI":"10.1109\/CVPR42600.2020.01339"},{"key":"4231_CR34","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/j.neucom.2018.11.010","volume":"330","author":"C Yuan","year":"2018","unstructured":"Yuan, C., et al.: A jointly learned deep embedding for person re-identification. Neurocomputing 330, 127\u2013137 (2018). https:\/\/doi.org\/10.1016\/j.neucom.2018.11.010","journal-title":"Neurocomputing"},{"key":"4231_CR35","doi-asserted-by":"crossref","unstructured":"Li, J., Qiu, Z., Yang, Y., Li, Y., Dong, Z., and Yang, C.: Prototype-Driven Multi-Feature Generation for Visible-Infrared Person Re-identification. (2024) arXiv:2409.05642","DOI":"10.1109\/ICASSP49660.2025.10889917"},{"key":"4231_CR36","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Hetero-Center Loss for Cross-Modality Person Re-Identification (2019) Available: https:\/\/www.proquest.com\/working-papers\/hetero-center-loss-cross-modality-person-re\/docview\/2307884292\/se-2","DOI":"10.1016\/j.neucom.2019.12.100"},{"key":"4231_CR37","doi-asserted-by":"publisher","unstructured":"Zhu, X., Yao, X., Chen, L., Li, Z., Zhang, J. J.: TMSDNet: Transformer with multi-scale dense network for single and multi-view 3D reconstruction, In: Computer Animation and Virtual Worlds, vol. 35, no. 1, art. no. e2201 (2024) https:\/\/doi.org\/10.1002\/cav.2201","DOI":"10.1002\/cav.2201"},{"key":"4231_CR38","unstructured":"Zhang, X., et al.: Enhancing unsupervised visible-infrared person re-identification with bidirectional-consistency gradual matching, In: IEEE Transactions on Pattern Analysis and Machine Intelligence (2025)"},{"key":"4231_CR39","unstructured":"Li, H., et al.: Relieving universal label noise for unsupervised visible-infrared person re-identification by inferring from neighbors, In: Proceedings of AAAI (2025)"},{"key":"4231_CR40","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep Residual Learning for Image Recognition. Infrared and Visible Image Fusion With the Use of Multi-scale Edge-preserving Decomposition and Guided Image Filter (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"4231_CR41","doi-asserted-by":"publisher","unstructured":"Sun, L., Dong, J., Tang, J., Pan, J.: Spatially-Adaptive feature modulation for efficient image Super-Resolution, In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) (2023) https:\/\/doi.org\/10.1109\/ICCV51070.2023.01213","DOI":"10.1109\/ICCV51070.2023.01213"},{"key":"4231_CR42","unstructured":"Wang, T., Chen, G., Zhang, X., Liu, C., Tan, X., Wang, J., He, C., and Zhou, W.: LMFNet: An Efficient Multimodal Fusion Approach for Semantic Segmentation in High-Resolution Remote Sensing (2024) arXiv:2404.13659"},{"key":"4231_CR43","doi-asserted-by":"publisher","unstructured":"Feng, D., et al.: Deep multi-modal object detection and semantic segmentation for autonomous driving: Datasets. Methods, and Challenges, In: IEEE Transactions on Intelligent Transportation Systems 22(3), 1341\u20131360 (2021). https:\/\/doi.org\/10.1109\/TITS.2020.2972974","DOI":"10.1109\/TITS.2020.2972974"},{"key":"4231_CR44","unstructured":"Mohan, R., Cattaneo, D., Drews, F., Valada, A.: Progressive Multi-Modal Fusion for Robust 3D Object Detection. (2024) arXiv:2410.07475"},{"key":"4231_CR45","unstructured":"Snell, J., Swersky, K., Zemel, R.S.: Prototypical Networks for Few-shot Learning. Neural Inf. Process. Syst. (2017)"},{"key":"4231_CR46","unstructured":"Gentile, C., Warmuth, M. K.: Linear hinge loss and average margin, Neural Inf. Process. Syst., vol. 11, pp. 225\u2013231 (1998) [Online]. Available: http:\/\/papers.nips.cc\/paper\/1610-linear-hinge-loss-and-average-margin.pdf"},{"key":"4231_CR47","doi-asserted-by":"publisher","unstructured":"Yuan, Y., Chen, W., Yang, Y., Wang, Z.: In defense of the triplet loss again: Learning robust person re-identification with fast approximated triplet loss and label distillation, In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2020) https:\/\/doi.org\/10.1109\/CVPRW50498.2020.00185","DOI":"10.1109\/CVPRW50498.2020.00185"},{"key":"4231_CR48","doi-asserted-by":"crossref","unstructured":"De Cheng et al.: Person re-identification by multi-channel parts-based cnn with improved triplet loss func-tion. In: Proceedings of the iEEE Conference on Computer Vision and Pattern Recognition. pp. 1335\u20131344 (2016)","DOI":"10.1109\/CVPR.2016.149"},{"key":"4231_CR49","doi-asserted-by":"publisher","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence 34(7), 13001\u201313008 (2020). https:\/\/doi.org\/10.1609\/aaai.v34i07.7000","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"4231_CR50","unstructured":"Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification (2017) arXiv:1703.07737 [Online]"},{"key":"4231_CR51","doi-asserted-by":"publisher","unstructured":"Liu, X., Wang, Y., Zhang, Z., Chen, H.: Hierarchical Feature Fusion for Cross-Modality Person Re-identification, Int. J. Pattern Recogn. Artif. Intell. 38(5), art. no. 2457017 (2025) https:\/\/doi.org\/10.1142\/S0218001424570179","DOI":"10.1142\/S0218001424570179"},{"key":"4231_CR52","doi-asserted-by":"publisher","unstructured":"Guo, Y., Zhang, W., Jiao, L., Wang, S., Wang, S., Liu, F.: Visible-infrared person re-identification with region-based augmentation and cross modality attention, Scientif. Rep. 15, art. no. 18225 (2025) https:\/\/doi.org\/10.1038\/s41598-025-01979-z","DOI":"10.1038\/s41598-025-01979-z"},{"key":"4231_CR53","doi-asserted-by":"publisher","unstructured":"Hao, Y., et al.: Multi-Scale contrastive learning with hierarchical knowledge synergy for visible-infrared person re-identification, Sensors 25(1), art. no. 152 (2025) https:\/\/doi.org\/10.3390\/s25010152","DOI":"10.3390\/s25010152"},{"key":"4231_CR54","unstructured":"Ye, Mang., Ruan, Weijian., Du, Bo., Shou, Mike Zheng.: Channel augmented joint learning for visible-infrared recog-nition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pages 13567\u201313576 (2021). 1,5, 6, 7, 8"},{"key":"4231_CR55","doi-asserted-by":"publisher","first-page":"2352","DOI":"10.1109\/TIP.2022.3141868","volume":"31","author":"C Chen","year":"2022","unstructured":"Chen, C., Ye, M., Qi, M., Wu, J., Jiang, J., Lin, C.-W.: Structure-aware positional transformer for visible-infrared person re-identification. IEEE Trans. Image Process. 31, 2352\u20132364 (2022). https:\/\/doi.org\/10.1109\/TIP.2022.3141868","journal-title":"IEEE Trans. Image Process."},{"key":"4231_CR56","doi-asserted-by":"publisher","unstructured":"Liu, J., Sun, Y., Zhu, F., Pei, H., Yang, Y., Li, W.: Learning Memory-Augmented unidirectional metrics for cross-modality person re-identification, In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19344\u201319353 (2022) https:\/\/doi.org\/10.1109\/CVPR52688.2022.01876","DOI":"10.1109\/CVPR52688.2022.01876"},{"key":"4231_CR57","doi-asserted-by":"crossref","unstructured":"Jiang, Kongzhu, et al.: Cross-modality transformer for visible-infrared person re-identification. In: European Conference on Computer Vision, pp. 480\u2013496. Springer (2022)","DOI":"10.1007\/978-3-031-19781-9_28"},{"key":"4231_CR58","doi-asserted-by":"publisher","unstructured":"Yang, M., Huang, Z., Hu, P., Li, T., Lv, J., Peng, X.: Learning with Twin Noisy Labels for Visible-Infrared Person Re-Identification. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14288\u201314297. New Orleans, LA, USA (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01391","DOI":"10.1109\/CVPR52688.2022.01391"},{"key":"4231_CR59","doi-asserted-by":"publisher","first-page":"109150","DOI":"10.1016\/j.patcog.2022.109150","volume":"135","author":"Lin Wan","year":"2023","unstructured":"Wan, Lin, et al.: G2DA: Geometry-guided dual-alignment learning for RGB-infrared person re-identification. Pattern Recogn. 135, 109150 (2023)","journal-title":"Pattern Recogn."},{"key":"4231_CR60","doi-asserted-by":"publisher","unstructured":"Qiu, L., Chen, S., Yan, Y., Xue, J.-H., Wang, D.-H., Zhu, S.: High-Order structure based Middle-Feature learning for Visible-Infrared Person re-identification. In: Proceedings of the AAAI Conference on Artificial Intelligence 38(5), 4596\u20134604 (2024). https:\/\/doi.org\/10.1609\/aaai.v38i5.28259","DOI":"10.1609\/aaai.v38i5.28259"},{"key":"4231_CR61","doi-asserted-by":"publisher","unstructured":"Kim, S., Gwon, S., Seo, K.: Enhancing diverse intra-identity representation for Visible-Infrared Person Re-Identification, In: 2022 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2024) https:\/\/doi.org\/10.1109\/WACV57701.2024.00250","DOI":"10.1109\/WACV57701.2024.00250"},{"key":"4231_CR62","doi-asserted-by":"publisher","unstructured":"Liu, M., Sun, Y., Wang, X., Bian, Y., Zhang, Z., Wang, Y.: Pose-guided modality-invariant feature alignment for visible\u2013infrared object re-identification. In: IEEE Transactions on Instrumentation and Measurement, vol. 73, pp. 1\u201310, Art no. 5017610 (2024). https:\/\/doi.org\/10.1109\/TIM.2024.3384558","DOI":"10.1109\/TIM.2024.3384558"},{"issue":"6","key":"4231_CR63","doi-asserted-by":"publisher","first-page":"5104","DOI":"10.1109\/TCSVT.2023.3338813","volume":"34","author":"Y Ling","year":"2024","unstructured":"Ling, Y., Zhong, Z., Luo, Z., Li, S., Sebe, N.: Bridge gap in pixel and feature level for cross-modality person re-identification. IEEE Trans. Circuits Syst. Video Technol. 34(6), 5104\u20135117 (2024). https:\/\/doi.org\/10.1109\/TCSVT.2023.3338813","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"4231_CR64","doi-asserted-by":"publisher","first-page":"2696","DOI":"10.1109\/TIFS.2024.3352408","volume":"19","author":"Z Cui","year":"2024","unstructured":"Cui, Z., Zhou, J., Peng, Y.: DMA: Dual modality-aware alignment for visible-infrared person re-identification. IEEE Trans. Inf. Forensics Secur. 19, 2696\u20132708 (2024). https:\/\/doi.org\/10.1109\/TIFS.2024.3352408","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"4231_CR65","doi-asserted-by":"publisher","first-page":"6273","DOI":"10.1109\/TMM.2023.3347855","volume":"26","author":"X Yang","year":"2024","unstructured":"Yang, X., et al.: SSRR: Structural semantic representation reconstruction for visible-infrared person re-identification. IEEE Trans. Multimedia 26, 6273\u20136284 (2024). https:\/\/doi.org\/10.1109\/TMM.2023.3347855","journal-title":"IEEE Trans. Multimedia"},{"key":"4231_CR66","unstructured":"Zhang, Z. et al.: Mutual Information Guided Optimal Transport for Unsupervised Visible-Infrared Person Re-identification. arXiv:2407.12758 (2024): n. pag"},{"issue":"4","key":"4231_CR67","doi-asserted-by":"publisher","first-page":"2361","DOI":"10.1109\/TCSVT.2023.3309647","volume":"34","author":"G Du","year":"2024","unstructured":"Du, G., Zhang, L.: Enhanced invariant feature joint learning via modality-invariant neighbor relations for cross-modality person re-identification. IEEE Trans. Circuits Syst. Video Technol. 34(4), 2361\u20132373 (2024). https:\/\/doi.org\/10.1109\/TCSVT.2023.3309647","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"4231_CR68","doi-asserted-by":"publisher","first-page":"8172","DOI":"10.1109\/TMM.2024.3377139","volume":"26","author":"X Yang","year":"2024","unstructured":"Yang, X., Dong, W., Li, M., Wei, Z., Wang, N., Gao, X.: Cooperative separation of modality shared-specific features for visible-infrared person re-identification. IEEE Trans. Multimedia 26, 8172\u20138183 (2024). https:\/\/doi.org\/10.1109\/TMM.2024.3377139","journal-title":"IEEE Trans. Multimedia"},{"issue":"6","key":"4231_CR69","doi-asserted-by":"publisher","first-page":"4503","DOI":"10.1109\/TCSVT.2023.3340225","volume":"34","author":"H Li","year":"2024","unstructured":"Li, H., Li, M., Peng, Q., Wang, S., Yu, H., Wang, Z.: Correlation-guided semantic consistency network for visible-infrared person re-identification. IEEE Trans. Circuits Syst. Video Technol. 34(6), 4503\u20134515 (2024). https:\/\/doi.org\/10.1109\/TCSVT.2023.3340225","journal-title":"IEEE Trans. Circuits Syst. Video Technol."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04231-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-04231-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04231-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T13:03:58Z","timestamp":1772629438000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-04231-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,24]]},"references-count":69,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["4231"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-04231-x","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,24]]},"assertion":[{"value":"26 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"91"}}