摘要 可见光-红外行人重识别是全天候视频监控的关键技术之一,但受模态异质性、姿态变化与遮挡等因素的制约,仍存在局部语义建模容易错位、训练目标与推理目标脱节、单空间匹配鲁棒性不足等问题.针对上述问题,文中提出基于视觉语义动态锚定的双空间约束可见光-红外行人重识别方法(Dual-Space Constrained Visible-Infrared Person Re-identification Method Based on Visual Semantic Dynamic Anchoring, DS-VSDA).首先,设计语义驱动的原型动态锚定模块,引入人体部位空间先验,缓解语义冗余与漂移.然后,提出跨样本邻域关联损失,显式建模批次内样本拓扑关系,使训练约束与推理检索逻辑保持一致.最后,构建双空间一致性约束与匹配动态校准机制,融合深层特征和浅层特征,并通过互证校验优化匹配结果.在SYSU-MM01、RegDB数据集上的实验表明,DS-VSDA在室内外多场景中的性能稳定,由此验证其有效性.
Abstract：Visible-infrared person re-identification is a key technology for all-day video surveillance. However, constrained by modality heterogeneity, pose variations, and occlusions, existing methods still suffer from misalignment in local semantic modeling, a gap between training and inference objectives, and insufficient robustness in single-space matching. To address these issues, a dual-space constrained method based on visual-semantic dynamic anchoring(DS-VSDA)is proposed. First, a semantics-driven prototype dynamic anchoring module is designed to introduce spatial prior initialization of human body parts, thereby alleviating semantic redundancy and drift. Then, a cross-sample neighborhood affinity loss is introduced to explicitly model the topological relations among samples within a batch, bridging the training-inference gap. Finally, a dual-space semantic consistency constraint and a matching calibration mechanism are constructed to fuse shallow and deep features and optimize matching results through mutual verification. Experiments on the SYSU-MM01 and RegDB datasets demonstrate that DS-VSDA achieves stable performance in both indoor and outdoor scenarios, thereby validating its effectiveness.
[1] Chen C Q, Ye M, Qi M B, et al. Structure-aware positional trans-former for visible-infrared person re-identification[J]. IEEE Tran-sactions on Image Processing, 2022, 31: 2352-2364. [2] Kim M, Kim S, Park J, et al. PartMix: regularization strategy to learn part discovery for visible-infrared person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2023: 18621-18632. [3] Liu H J, Tan X H, Zhou X C.Parameter sharing exploration and hetero-center triplet loss for visible-thermal person re-identification[J]. IEEE Transactions on Multimedia, 2021, 23: 4414-4425. [4] Wu A C, Zheng W S, Yu H X, et al. RGB-infrared cross-modality person re-identification[C]//Proceedings of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2017: 5390-5399. [5] Ye M, Shen J B, Lin G J, et al. Deep learning for person re-identification: a survey and outlook[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(6): 2872-2893. [6] Dai P Y, Ji R R, Wang H B, et al. Cross-modality person re-identification with generative adversarial training[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence. San Francisco, USA: IJCAI, 2018: 677-683. [7] Wang G A, Zhang T Z, Cheng J, et al. RGB-infrared cross-modality person re-identification via joint pixel and feature alignment[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2019: 3622-3631. [8] Wang G A, Zhang T Z, Yang Y, et al. Cross-modality paired-images generation for RGB-infrared person re-identification[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7): 12144-12151. [9] Hu B Y, Liu J W, Zha Z J. Adversarial disentanglement and correlation network for RGB-infrared person re-identification[C/OL]//Proceedings of the IEEE International Conference on Multimedia and Expo. Washington, USA: IEEE, 2021. https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9428376. [10] Hu W P, Liu B H, Zeng H T, et al. Adversarial decoupling and modality-invariant representation learning for visible-infrared person re-identification[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(8): 5095-5109. [11] Kansal K, Subramanyam A V, Wang Z, et al. SDL: spectrum-disen-tangled representation learning for visible-infrared person re-identification[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2020, 30(10): 3422-3432. [12] Hao X, Zhao S Y, Ye M, et al. Cross-modality person re-identification via modality confusion and center aggregation[C]//Procee-dings of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2021: 16383-16392. [13] Feng Z X, Lai J H, Xie X H.Learning modality-specific representations for visible-infrared person re-identification[J]. IEEE Transactions on Image Processing, 2020, 29: 579-590. [14] Li D G, Wei X, Hong X P, et al. Infrared-visible cross-modal person re-identification with an X modality[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(4): 4610-4617. [15] Li Y L, Zhang T Z, Liu X, et al. Visible-infrared person re-identification with modality-specific memory network[J]. IEEE Tran-sactions on Image Processing, 2022, 31: 7165-7178. [16] Lu Y, Wu Y, Liu B, et al. Cross-modality person re-identification with shared-specific feature transfer[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2020: 13376-13386. [17] Zhang Q, Lai C Z, Liu J N, et al. FMCNet: feature-level modality compensation for visible-infrared person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2022: 7339-7348. [18] Wei Z Y, Yang X, Wang N N, et al. Syncretic modality collaborative learning for visible infrared person re-identification[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2021: 225-234. [19] Park H, Lee S, Lee J, et al. Learning by aligning: visible-infrared person re-identification using cross-modal correspondences[C]//Proceedings of the IEEE/CVF International Conference on Compu-ter Vision. Washington, USA: IEEE, 2021: 12026-12035. [20] Liu J L, Sun Y F, Zhu F, et al. Learning memory-augmented unidirectional metrics for cross-modality person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2022: 19344-19353. [21] Zhu J Q, Wu H X, Chen Y T,et al. Cross-modal group-relation optimization for visible-infrared person re-identification[J/OL]. Neural Networks, 2024, 179. https://doi.org/10.1016/j.neunet.2024.106576. [22] Jiang Y, Yu H, Cheng X, et al. From laboratory to real world: a new benchmark towards privacy-preserved visible-infrared person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2025: 8828-8837. [23] Lu H, Zou X Z, Zhang P P.Learning progressive modality-shared transformers for effective visible-infrared person re-identification[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2023, 37(2): 1835-1843. [24] Hu M N, Zhou Q L, Wang R.Bridging visible and infrared moda-lities: a dual-level joint align network for person re-identification[J]. The Visual Computer, 2025, 41(10): 7063-7078. [25] Jiang K Z, Zhang T Z, Liu X, et al. Cross-modality transformer for visible-infrared person re-identification[C]//Proceedings of the 17th European Conference on Computer Vision. Berlin, Germany: Springer, 2022: 480-496. [26] Guo J T, Du H S, Hao X X,et al. CFET: a cross-fusion enhanced transformer for visible-infrared person re-identification[J/OL]. Expert Systems with Applications, 2025, 271. https://doi.org/10.1016/j.eswa.2025.126645. [27] Fu C Y, Hu Y B, Wu X, et al. CM-NAS: cross-modality neural architecture search for visible-infrared person re-identification[C]//Proceedings of the IEEE/CVF International Conference on Compu-ter Vision. Washington, USA: IEEE, 2021: 11803-11812. [28] Wu Q, Dai P Y, Chen J, et al. Discover cross-modality nuances for visible-infrared person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2021: 4328-4337. [29] Li X L, Lu Y, Liu B, et al. Counterfactual intervention feature transfer for visible-infrared person re-identification[C]//Procee-dings of the 17th European Conference on Computer Vision. Berlin, Germany: Springer, 2022: 381-398. [30] Zhang Y Y, Zhao S Y, Kang Y H, et al. Modality synergy complement learning with cascaded aggregation for visible-infrared person re-identification[C]//Proceedings of the 17th European Confe-rence on Computer Vision. Berlin, Germany: Springer, 2022: 462-479. [31] Ye M, Shen J B, Crandall D J, et al. Dynamic dual-attentive aggregation learning for visible-infrared person re-identification[C]//Proceedings of the 16th European Conference on Computer Vision. Berlin, Germany: Springer, 2020: 229-247. [32] Ye M, Ruan W J, Du B, et al. Channel augmented joint learning for visible-infrared recognition[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2021: 13547-13556. [33] Chen Y H S, Wan L, Li Z H, et al. Neural feature search for RGB-infrared person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2021: 587-597. [34] Sarker P K, Zhao Q J.Enhanced visible-infrared person re-identification based on cross-attention multiscale residual vision transformer[J/OL]. Pattern Recognition, 2024, 149. https://doi.org/10.1016/j.patcog.2024.110288. [35] Sarker P K.Transformer-based neural architecture search for effective visible-infrared person re-identification[J/OL]. Neurocompu-ting, 2025, 620. https://doi.org/10.1016/j.neucom.2024.129257. [36] Li Y L, Zhang T Z, Zhang Y D.Frequency domain modality-invariant feature learning for visible-infrared person re-identification[EB/OL]. [2026-05-15]. https://arxiv.org/pdf/2401.01839. [37] Qiu L X, Chen S, Yan Y, et al. High-order structure based mi-ddle-feature learning for visible-infrared person re-identification[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2024, 38(5): 4596-4604. [38] Wu Q, Xia J E, Dai P Y, et al. CycleTrans: learning neutral yet discriminative features via cycle construction for visible-infrared person re-identification[J]. IEEE Transactions on Neural Networks and Learning Systems, 2025, 36(3): 5469-5479. [39] Wu R Q, Jiao B L, Liu M, et al. Enhancing visible-infrared person re-identification with modality- and instance-aware adaptation learning[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2025, 35(8): 8086-8103. [40] Ning E H, Wang Y F, Wang C S, et al. Enhancement, integration, expansion: activating representation of detailed features for occluded person re-identification[J]. Neural Networks, 2024, 169: 532-541. [41] Lin Y T, Zheng L, Zheng Z D, et al. Improving person re-identification by attribute and identity learning[J]. Pattern Recognition, 2019, 95: 151-161. [42] Huang N C, Xing B C, Zhang Q,et al. Co-segmentation assisted cross-modality person re-identification[J/OL]. Information Fu-sion, 2024, 104. https://doi.org/10.1016/j.inffus.2023.102194. [43] Chen X T, Yan Y, Xue J H,et al. Consistency-driven feature scoring and regularization network for visible-infrared person re-identification[J/OL]. Pattern Recognition, 2025, 159. https://doi.org/10.1016/j.patcog.2024.111131. [44] Zhang Y F, Kong L Q, Li H F, et al. Weakly supervised visible-infrared person re-identification via heterogeneous expert collaborative consistency learning[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2025: 12659-12669. [45] Pang Z Q, Wang C Y, Zhao L L, et al. Augmented and softened matching for unsupervised visible-infrared person re-identification[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2025: 11100-11109. [46] Xu H X, Niu G L.BIT: matching-based bi-directional interaction transformation network for visible-infrared person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2026: 40386-40396. [47] Huang Z P, Liu J W, Li L, et al. Modality-adaptive mixup and invariant decomposition for RGB-infrared person re-identification[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2022, 36(1): 1034-1042. [48] Fang X Y, Yang Y, Fu Y.Visible-infrared person re-identification via semantic alignment and affinity inference[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2023: 11236-11245.
2026, Vol. 39 
