{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T23:32:28Z","timestamp":1784071948559,"version":"3.55.0"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100012542","name":"Sichuan Province Science and Technology Support Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471034"],"award-info":[{"award-number":["62471034"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003787","name":"Hebei Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["F2023105001"],"award-info":[{"award-number":["F2023105001"]}],"id":[{"id":"10.13039\/501100003787","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.neunet.2026.108719","type":"journal-article","created":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T00:26:50Z","timestamp":1770856010000},"page":"108719","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["SD2-ReID: A semantic-stylistic decoupled distillation framework for robust multi-modal object re-identification"],"prefix":"10.1016","volume":"198","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2797-3686","authenticated-orcid":false,"given":"Yonghao","family":"Yan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8581-821X","authenticated-orcid":false,"given":"Meijing","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingzhou","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huanyu","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sibo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108719_bib0001","series-title":"2018 IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"2109","article-title":"Multi-level factorisation net for person re-identification","author":"Chang","year":"2018"},{"key":"10.1016\/j.neunet.2026.108719_bib0002","doi-asserted-by":"crossref","first-page":"2015","DOI":"10.1109\/TMM.2024.3521822","article-title":"MDANet: modality-aware domain alignment network for visible-Infrared person re-identification","volume":"27","author":"Cheng","year":"2025","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2026.108719_bib0003","unstructured":"Crawford, J., Yin, H., McDermott, L., & Cummings, D. (2023). UniCat: Crafting a Stronger Fusion Baseline for Multimodal Re-IdentificationarXiv: 2310.18812. 10.48550\/arXiv.2310.18812."},{"key":"10.1016\/j.neunet.2026.108719_bib0004","doi-asserted-by":"crossref","first-page":"2696","DOI":"10.1109\/TIFS.2024.3352408","article-title":"DMA: Dual modality-aware alignment for visible-infrared person re-identification","volume":"19","author":"Cui","year":"2024","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"10.1016\/j.neunet.2026.108719_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111510","article-title":"Learning multi-granularity representation with transformer for visible-infrared person re-identification","volume":"164","author":"Feng","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.108719_bib0006","doi-asserted-by":"crossref","first-page":"1401","DOI":"10.1109\/TMM.2022.3229969","article-title":"Occluded visible-infrared person re-Identification","volume":"25","author":"Feng","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2026.108719_bib0007","doi-asserted-by":"crossref","first-page":"7647","DOI":"10.1109\/TMM.2022.3224663","article-title":"Visible-infrared person re-identification via cross-modality interaction transformer","volume":"25","author":"Feng","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2026.108719_bib0008","series-title":"2016 IEEE Conference on computer vision and pattern recognition (CVPR)","first-page":"2414","article-title":"Image style transfer using convolutional neural networks","author":"Gatys","year":"2016"},{"key":"10.1016\/j.neunet.2026.108719_bib0009","unstructured":"Guerra-Manzanares, A., & Shamout, F. E. (2025). MIND: Modality-informed knowledge distillation framework for multimodal clinical prediction tasksarXiv: 2502.01158. 10.48550\/arXiv.2502.01158."},{"key":"10.1016\/j.neunet.2026.108719_bib0010","series-title":"2022 7th international conference on intelligent computing and signal processing (ICSP)","first-page":"1565","article-title":"Generative and attentive fusion for multi-spectral vehicle re-Identification","author":"Guo","year":"2022"},{"issue":"11","key":"10.1016\/j.neunet.2026.108719_bib0011","doi-asserted-by":"crossref","first-page":"12431","DOI":"10.1109\/TITS.2023.3285758","article-title":"Graph-based progressive fusion network for multi-Modality vehicle re-identification","volume":"24","author":"He","year":"2023","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.neunet.2026.108719_bib0012","series-title":"2021 IEEE\/CVF International conference on computer vision (ICCV)","first-page":"14993","article-title":"TransReID: transformer-based object re-identification","author":"He","year":"2021"},{"key":"10.1016\/j.neunet.2026.108719_bib0013","unstructured":"Hermans, A., Beyer, L., & Leibe, B. (2017). In Defense of the Triplet Loss for Person Re-IdentificationarXiv: 1703.07737. 10.48550\/arXiv.1703.07737."},{"key":"10.1016\/j.neunet.2026.108719_bib0014","unstructured":"Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the Knowledge in a Neural NetworkarXiv: 1503.02531. 10.48550\/arXiv.1503.02531."},{"key":"10.1016\/j.neunet.2026.108719_bib0015","series-title":"Computer vision \u2013 ECCV 2022","first-page":"87","article-title":"Cross-modality knowledge distillation network for monocular 3D object detection","author":"Hong","year":"2022"},{"key":"10.1016\/j.neunet.2026.108719_bib0016","series-title":"2017 IEEE International conference on computer vision (ICCV)","first-page":"1510","article-title":"Arbitrary style transfer in real-time with adaptive instance normalization","author":"Huang","year":"2017"},{"key":"10.1016\/j.neunet.2026.108719_bib0017","series-title":"Proceedings of the 27th ACM international conference on multimedia, MM \u201919","first-page":"365","article-title":"Illumination-invariant person re-Identification","author":"Huang","year":"2019"},{"key":"10.1016\/j.neunet.2026.108719_bib0018","series-title":"2024 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"16006","article-title":"C2KD: Bridging the modality gap for cross-modal knowledge distillation","author":"Huo","year":"2024"},{"key":"10.1016\/j.neunet.2026.108719_bib0019","series-title":"2020 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"3140","article-title":"Style normalization and restitution for generalizable person re-identification","author":"Jin","year":"2020"},{"issue":"07","key":"10.1016\/j.neunet.2026.108719_bib0020","doi-asserted-by":"crossref","first-page":"11345","DOI":"10.1609\/aaai.v34i07.6796","article-title":"Multi-spectral vehicle re-identification: a challenge","volume":"34","author":"Li","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.neunet.2026.108719_bib0021","series-title":"2018 IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"2285","article-title":"Harmonious attention network for person re-identification","author":"Li","year":"2018"},{"key":"10.1016\/j.neunet.2026.108719_bib0022","first-page":"1","article-title":"Multispectral scene classification via cross-modal knowledge distillation","volume":"60","author":"Liu","year":"2022","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.108719_bib0023","series-title":"2019 IEEE\/CVF Conference on computer vision and pattern recognition workshops (CVPRW)","first-page":"1487","article-title":"Bag of tricks and a strong baseline for deep person re-identification","author":"Luo","year":"2019"},{"issue":"86","key":"10.1016\/j.neunet.2026.108719_bib0024","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.108719_bib0025","unstructured":"van den Oord, A., Li, Y., & Vinyals, O. (2019). Representation Learning with Contrastive Predictive CodingarXiv: 1807.03748. 10.48550\/arXiv.1807.03748."},{"key":"10.1016\/j.neunet.2026.108719_bib0026","series-title":"2017 IEEE International conference on computer vision (ICCV)","first-page":"5409","article-title":"Multi-scale deep learning architectures for person re-identification","author":"Qian","year":"2017"},{"key":"10.1016\/j.neunet.2026.108719_bib0027","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"},{"issue":"13","key":"10.1016\/j.neunet.2026.108719_bib0028","doi-asserted-by":"crossref","first-page":"14875","DOI":"10.1609\/aaai.v38i13.29407","article-title":"XKD: Cross-Modal knowledge distillation with domain alignment for video representation learning","volume":"38","author":"Sarkar","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.neunet.2026.108719_bib0029","doi-asserted-by":"crossref","first-page":"561","DOI":"10.1016\/j.neucom.2021.09.038","article-title":"Mask-guided contrastive attention and two-stream metric co-learning for person re-identification","volume":"465","author":"Song","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.108719_bib0030","series-title":"Computer vision \u2013 ECCV 2018","first-page":"501","article-title":"Beyond part models: person retrieval with refined part pooling (and a strong convolutional baseline)","author":"Sun","year":"2018"},{"key":"10.1016\/j.neunet.2026.108719_bib0031","series-title":"2016 IEEE Conference on computer vision and pattern recognition (CVPR)","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","author":"Szegedy","year":"2016"},{"key":"10.1016\/j.neunet.2026.108719_bib0032","series-title":"Proceedings of the 26th ACM international conference on multimedia","first-page":"274","article-title":"Learning discriminative features with multiple granularities for person re-identification","author":"Wang","year":"2018"},{"key":"10.1016\/j.neunet.2026.108719_bib0033","series-title":"Pattern recognition and computer vision","first-page":"347","article-title":"Bridging modality gap for visual grounding with effecitve cross-modal distillation","author":"Wang","year":"2025"},{"issue":"8","key":"10.1016\/j.neunet.2026.108719_bib0034","doi-asserted-by":"crossref","first-page":"8150","DOI":"10.1609\/aaai.v39i8.32879","article-title":"MambaPro: multi-modal object re-identification with mamba aggregation and synergistic prompt","volume":"39","author":"Wang","year":"2025","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"issue":"6","key":"10.1016\/j.neunet.2026.108719_bib0035","doi-asserted-by":"crossref","first-page":"5758","DOI":"10.1609\/aaai.v38i6.28388","article-title":"TOP-ReID: multi-Spectral object re-identification with token permutation","volume":"38","author":"Wang","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"issue":"8","key":"10.1016\/j.neunet.2026.108719_bib0036","doi-asserted-by":"crossref","first-page":"8141","DOI":"10.1609\/aaai.v39i8.32878","article-title":"DeMo: decoupled feature-based mixture of experts for multi-modal object re-identification","volume":"39","author":"Wang","year":"2025","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.neunet.2026.108719_bib0037","series-title":"2018 IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"8042","article-title":"Resource aware person re-identification across multiple resolutions","author":"Wang","year":"2018"},{"issue":"3","key":"10.1016\/j.neunet.2026.108719_bib0038","doi-asserted-by":"crossref","first-page":"2633","DOI":"10.1609\/aaai.v36i3.20165","article-title":"Interact, embed, and enlarge: boosting modality-specific representations for multi-modal person re-identification","volume":"36","author":"Wang","year":"2022","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.neunet.2026.108719_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125716","article-title":"LRMM: Low rank multi-scale multi-modal fusion for person re-identification based on RGB-NI-TI","volume":"263","author":"Wu","year":"2025","journal-title":"Expert Systems with Applications"},{"issue":"2s","key":"10.1016\/j.neunet.2026.108719_bib0040","first-page":"1","article-title":"Rank-in-rank loss for person re-identification","volume":"18","author":"Xu","year":"2022","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"},{"issue":"3","key":"10.1016\/j.neunet.2026.108719_bib0041","doi-asserted-by":"crossref","first-page":"1711","DOI":"10.1109\/TPAMI.2022.3163451","article-title":"Intra-inter domain similarity for unsupervised person re-Identification","volume":"46","author":"Xuan","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"6","key":"10.1016\/j.neunet.2026.108719_bib0042","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 Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"4","key":"10.1016\/j.neunet.2026.108719_bib0043","doi-asserted-by":"crossref","first-page":"3633","DOI":"10.1109\/TCSVT.2024.3509817","article-title":"Representation selective coupling via token sparsification for multi-spectral object re-identification","volume":"35","author":"Yu","year":"2025","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"3","key":"10.1016\/j.neunet.2026.108719_bib0044","doi-asserted-by":"crossref","first-page":"560","DOI":"10.1109\/JSTSP.2023.3250989","article-title":"Searching parameterized retrieval & verification loss for re-identification","volume":"17","author":"Yuan","year":"2023","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"10.1016\/j.neunet.2026.108719_bib0045","series-title":"2024 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"17117","article-title":"Magic tokens: select diverse tokens for multi-modal object re-identification","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neunet.2026.108719_bib0046","series-title":"2021 IEEE\/CVF International conference on computer vision (ICCV)","first-page":"205","article-title":"Heterogeneous relational complement for vehicle re-identification","author":"Zhao","year":"2021"},{"key":"10.1016\/j.neunet.2026.108719_bib0047","unstructured":"Zheng, A., He, Z., Wang, Z., Li, C., & Tang, J. (2023a). Dynamic Enhancement Network for Partial Multi-modality Person Re-identificationarXiv: 2305.15762. 10.48550\/arXiv.2305.15762."},{"issue":"4","key":"10.1016\/j.neunet.2026.108719_bib0048","doi-asserted-by":"crossref","first-page":"3529","DOI":"10.1609\/aaai.v35i4.16467","article-title":"Robust multi-modality person re-identification","volume":"35","author":"Zheng","year":"2021","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.neunet.2026.108719_bib0049","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101901","article-title":"Cross-directional consistency network with adaptive layer normalization for multi-spectral vehicle re-identification and a high-quality benchmark","volume":"100","author":"Zheng","year":"2023","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2026.108719_bib0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102128","article-title":"Multi-modal person re-identification based on transformer relational regularization","volume":"103","author":"Zheng","year":"2024","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2026.108719_bib0051","unstructured":"Zheng, Z., Yang, X., Yu, Z., Zheng, L., Yang, Y., & Kautz, J. (2021b). Joint Discriminative and Generative Learning for Person Re-identificationarXiv: 1904.07223. 10.48550\/arXiv.1904.07223."},{"key":"10.1016\/j.neunet.2026.108719_bib0052","series-title":"2019 IEEE\/CVF International conference on computer vision (ICCV)","first-page":"3701","article-title":"Omni-scale feature learning for person re-identification","author":"Zhou","year":"2019"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026001814?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026001814?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T20:04:40Z","timestamp":1777579480000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026001814"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":52,"alternative-id":["S0893608026001814"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108719","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SD2-ReID: A semantic-stylistic decoupled distillation framework for robust multi-modal object re-identification","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108719","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":"108719"}}