Pith. sign in

REVIEW 3 major objections 6 minor 242 references

This paper argues that person re-identification has become a single spectrum of cross-modal matching tasks, from visible–infrared to text, sketch, and beyond-visibility sensing, and that a simple dual-path Transformer can serve as a competi

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · deepseek-v4-flash

2026-08-02 00:56 UTC pith:VOHE5IA6

load-bearing objection Useful survey of cross-modal ReID that overstates its own baseline; the survey half deserves a serious referee, the baseline claim does not. the 3 major comments →

arxiv 2607.14821 v1 pith:VOHE5IA6 submitted 2026-07-16 cs.CV

Blurring Modal Boundaries: A Unified Survey from Single- to Multi-Modal Person Re-ldentification

Xiao Wang , Bing Wang , Bin Yang , Cuiqun Chen , Xin Xu , Mang Ye This is my paper
classification cs.CV
keywords person re-identificationcross-modal ReIDvisible-infrared ReIDtext-image ReIDsketch ReIDnon-line-of-sight ReIDmodality-invariant representation learningTransformer baseline
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper tries to organize the many branches of person re-identification—matching the same person across non-overlapping cameras—into one map. It argues that the field has moved from single-modal RGB matching to cross-modal settings (visible–infrared, text–image, sketch–photo, and signal-based non-line-of-sight cases), and that newer tri-spectral and multi-modal systems belong on the same conceptual spectrum. Its organizing principle is to classify tasks by retrieval protocol and learning objective rather than by the number of modalities involved. The paper also proposes a Transformer-based visible–infrared baseline and claims it outperforms existing methods on the RegDB and SYSU-MM01 benchmarks in both supervised and unsupervised settings. If the map is right, techniques for reducing modality gaps should transfer across all these subfields instead of being developed in isolation.

Core claim

The paper's central claim is that existing person re-identification research can be described for the first time by a single taxonomy: cross-modal tasks (VI-ReID, TI-ReID, Sketch-ReID, NLOS-ReID) share the problem of heterogeneous modality alignment; tri-spectral ReID centers on spectral-aware representation; and multi-modal ReID centers on multi-source fusion. The authors further claim that a simple Transformer-based framework—separate patch embeddings for visible and infrared inputs, a shared Transformer encoder with a class token as an identity aggregator, feature-level modality confusion, a shared memory bank, and cluster-contrastive learning—captures these principles and achieves strong

What carries the argument

The survey's organizing device is a two-axis taxonomy: each person re-identification task is classified by its retrieval protocol (which modality queries which) and by its primary learning objective (heterogeneous alignment versus spectral-aware representation versus multi-source fusion). This places VI, text-image, sketch, NLOS, tri-spectral, and multi-modal work under one framework. The experimental machinery is a dual-path Transformer baseline for VI-ReID: separate patch embeddings for visible and infrared images, a shared Transformer encoder whose class token aggregates identity information, feature-level modality confusion to erase modality-specific cues, a shared memory bank for cluste

Load-bearing premise

The load-bearing premise for the experimental contribution is that single-run, within-dataset Rank-1 and mAP on RegDB and SYSU-MM01 are sufficient evidence that the proposed Transformer baseline is superior—a premise the paper itself questions in Section 2.1.1, where it calls for cross-dataset and camera-disjoint evaluation rather than reliance on within-dataset numbers alone.

What would settle it

Run the proposed baseline, with the paper's own settings, on the low-light LLCM benchmark without adaptation after training on RegDB or SYSU-MM01; if its Rank-1 and mAP fall to the level of a standard CNN baseline under the same protocol, the claim that simple Transformer-based modality confusion yields robust modality-invariant features is not supported.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • If the taxonomy is right, a method's worth in cross-modal ReID should be judged by how well it solves heterogeneous alignment rather than by which pair of modalities it handles, encouraging technique transfer across VI, text-image, sketch, and NLOS settings.
  • The proposed baseline demonstrates that a Transformer with a shared encoder, class token, and feature-level modality confusion can outperform established CNN-based VI-ReID methods on RegDB and SYSU-MM01 in both supervised and unsupervised settings.
  • IR-guided RGB pseudo-label refinement improves unsupervised performance, supporting the principle that the more stable modality can be used to supervise pseudo-label generation for the noisier one.
  • On the five-modality ORBench-style protocol, adding infrared and color-pencil queries to a text query yields large mAP gains, while adding sketch to an already rich combination gives only marginal gains, so sensor selection should account for diminishing returns.
  • The paper's own recommendation that future work report cross-dataset, camera-disjoint, and missing-modality evaluation implies that current within-dataset Rank-1/mAP numbers should be read cautiously.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Editorial inference: if the taxonomy is adopted, benchmark design could move toward a single multi-modal gallery (RGB, IR, text, sketch, and NLOS-style queries) so that alignment techniques are compared under one protocol instead of separate per-modality-pair datasets.
  • Editorial inference: a testable extension of the baseline is to train on RegDB and evaluate on the low-light LLCM set without adaptation; if the modality-confusion design is genuinely modality-invariant, the drop should be small, and if not, the paper's own recommended cross-dataset protocol would expose it.
  • Editorial inference: the paper's future direction on causal representation learning implies that current disentanglement methods, which separate factors without causal structure, may not transfer to unseen sensors; a concrete test would swap sensor type at test time and measure the drop.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

3 major / 6 minor

Summary. The paper surveys person re-identification from single-modal to cross-modal and multi-modal settings. It organizes VI-ReID, TI-ReID, Sketch-ReID, NLOS-ReID, tri-spectral ReID, and multi-modal ReID under a taxonomy based on retrieval protocol and learning objective, and reviews datasets and representative methods. As a second contribution, it proposes a Transformer-based VI-ReID baseline with supervised and unsupervised variants, evaluated on SYSU-MM01 and RegDB. The paper claims to be the first survey covering this combination of scenarios.

Significance. If the survey's coverage claim holds, the paper provides a useful structured reference: it brings together six task families that are usually treated separately, includes extensive method and dataset tables, and is candid about benchmark-specific biases and the need for stronger evaluation protocols. The proposed taxonomy is a reasonable organizing principle. The baseline contribution, however, is not established as claimed: the experimental evidence in the paper's own Tables 3 and 4 contradicts the 'superior overall performance' statement, and no code or error bars are provided. The survey content remains defensible, but the experimental claim requires substantial revision.

major comments (3)
  1. [§5 / Table 12 vs Tables 3 and 4] The claim in §5 that the proposed baseline 'demonstrates superior overall performance on both the RegDB and SYSU-MM01 datasets' under supervised and unsupervised settings is contradicted by the paper's own tables. In the supervised setting, DEN [54] (Table 3) outperforms the baseline on every reported metric: SYSU-MM01 All 76.36/71.38 vs 69.93/68.91, Indoor 83.56/84.65 vs 76.07/81.50, RegDB V→I 95.34/90.21 vs 93.48/88.72, and I→V 94.98/90.24 vs 92.61/87.72. PartMix [55] also beats the baseline on SYSU-MM01 All and Indoor. In the unsupervised setting, SDCL [99] (Table 4) exceeds the baseline on SYSU-MM01 All (64.49/63.24 vs 60.87/59.56) and Indoor (71.37/76.90 vs 66.13/73.21). None of these methods appears in Table 12. The comparison is therefore selective, and the 'superior overall' statement should be replaced with a qualified claim or the table should include the full set of methods fr
  2. [§5 / §2.1.1 Evaluation protocol] The experimental support for the baseline is limited to single-run within-dataset Rank-1 and mAP on SYSU-MM01 and RegDB. No cross-dataset evaluation, camera-disjoint testing, or robustness to degraded modalities is reported, despite §2.1.1 explicitly recommending that 'future studies should report cross-dataset evaluation, camera- or environment-disjoint testing' rather than relying solely on within-dataset Rank-1 and mAP. The absence of error bars or multiple-seed results further weakens the 'superior' and 'significantly surpass' wording. These limitations are structurally separate from the survey's coverage contribution and should be fixed by strengthening the evaluation or by re-scoping the claim.
  3. [§5.2 Ablation study] The ablations in Table 13 report single-run numbers without variance or statistical tests. Since the reported gaps among some variants are small (e.g., supervised SYSU R-1 69.93 vs 67.21), it is not possible to determine whether the differences are meaningful. In addition, the ablation does not include a standard Transformer ReID baseline (e.g., DC-Former [238], which the design explicitly draws on), so the incremental contribution of the proposed modules is not isolated from the gains of the backbone. Please provide repeated runs, variance, or a stronger baseline comparison.
minor comments (6)
  1. [§6] The paragraph 'Identity-aware Foundation Models' appears twice verbatim in the Future Research section; remove the duplicate.
  2. [§2.4] The Wi-PER81 dataset is introduced twice through the same reference [214]; the later 'More recently, Cascio et al. [214] further advanced' sentence should be merged with the earlier description.
  3. [Table 6] For PD [160], the RSTPReid mAP is listed as '????'; please supply the value or mark it as not reported consistently with other entries.
  4. [Table 2] The header 'Identitiesr' contains a typo; should be 'Identities'. Also the table caption says 'Low-light' but the column is not defined in the main text.
  5. [§2.2] The text refers to 'Fig. 1, D' when discussing noisy correspondence in TI-ReID; the intended figure appears to be Fig. 5. Please correct the cross-reference.
  6. [§2.4] The NLOS ReID section would benefit from a performance summary table analogous to Tables 3, 4, 6, 8, 9, and 11; currently the relative strengths of ReID3D, mmWave, and RF methods are described only qualitatively.

Circularity Check

0 steps flagged

No load-bearing circularity; survey coverage claim is independent and the baseline is externally evaluated, although its 'superior overall performance' statement is inconsistent with the paper's own tables.

full rationale

The paper's primary contribution is a survey and taxonomy, not a derivation. The 'first survey' claim is supported by comparison with prior surveys in Table 1 and is not justified by self-citation. The proposed Transformer baseline is trained and evaluated on external benchmarks SYSU-MM01 and RegDB; its components are borrowed or described (random channel augmentation from [50], class token from DC-Former [238], cluster contrast learning, IR-guided pseudo-label refinement), and the reported numbers are not fitted to the claims. The main weakness is evaluative, not circular: Section 2.1.1 states that 'future studies should report cross-dataset evaluation, camera- or environment-disjoint testing... rather than relying solely on within-dataset Rank-1 accuracy and mAP,' while Section 5 claims 'superior overall performance' based only on within-dataset results. Moreover, Table 12 omits stronger methods from Tables 3 and 4 (e.g., DEN, PartMix, PMCM, SDCL, MCL), so the 'superior' claim is unsupported or selective. This is a correctness/reporting concern, not a reduction of a prediction to its inputs by construction. Self-citations by the author group appear in baseline design, but they are not used to forbid alternatives or to establish a uniqueness result; the baseline remains checkable against public data. Therefore the circularity score is low.

Axiom & Free-Parameter Ledger

9 free parameters · 4 axioms · 0 invented entities

The survey itself introduces no free parameters; the free parameters listed belong to the proposed baseline and are hand-set validation hyperparameters. The baseline relies on the domain assumptions stated in Section 5 (Transformer superiority, IR label stability) and the representativeness of the two benchmarks. No new physical or conceptual entities (e.g., new sensors, new features) are invented beyond the architectural components.

free parameters (9)
  • DBSCAN threshold = 0.6
    Used for pseudo-label clustering in unsupervised VI-ReID; chosen by the authors, no sensitivity analysis reported (Section 5.1).
  • DBSCAN min_samples = 4
    Clustering parameter in the unsupervised pipeline (Section 5.1).
  • Re-ranking k1, k2 = k1=30, k2=6
    Parameters for re-ranked Jaccard distance used in clustering (Section 5.1).
  • Contrastive temperature = 0.05
    Temperature for memory-based contrastive loss (Section 5.1).
  • Memory momentum = 0.1
    Momentum for updating memory banks (Section 5.1).
  • Initial learning rate = 3.5e-4
    SGD learning rate (Section 5.1).
  • Weight decay = 5e-4
    SGD weight decay (Section 5.1).
  • Learning rate schedule = decay 0.1 every 20 epochs
    Learning rate reduction schedule (Section 5.1).
  • Image size = 288x144
    Input resolution for all images (Section 5.1).
axioms (4)
  • domain assumption Transformer backbones are better suited than CNNs for cross-modal VI-ReID global modeling
    Section 5 motivates the baseline by claiming Transformers are better for global structural and shape information, especially for infrared images.
  • domain assumption IR modality retains more stable structural information, so IR cluster labels can refine RGB pseudo-labels
    Stated in Section 5 as the basis for the unsupervised IR-PR module.
  • domain assumption The taxonomy based on retrieval protocol and learning objective is a natural grouping of ReID tasks
    Section 1 and Fig. 2 propose this organizational scheme; the survey's value depends on this grouping being useful.
  • domain assumption SYSU-MM01 and RegDB are representative benchmarks for VI-ReID evaluation
    The baseline is evaluated only on these two datasets; the paper itself calls for cross-dataset evaluation in Section 2.1.1 but does not perform it.

pith-pipeline@v1.3.0-alltime-deepseek · 44375 in / 12469 out tokens · 93027 ms · 2026-08-02T00:56:39.834465+00:00 · methodology

0 comments
read the original abstract

Person re-identification (ReID) serves as a critical component in intelligent surveillance systems, aiming to match identities across disjoint camera networks. While traditional methods primarily rely on single-modal RGB imagery, they are often constrained by environmental challenges such as low illumination and occlusion. To overcome these limitations, the field is rapidly evolving toward cross-modal and multi-modal paradigms. This survey presents a comprehensive overview of this transition, systematically reviewing key cross-modal tasks including visible-infrared (VI-ReID), text-image (TI-ReID), sketch-based (Sketch-ReID), and the emerging Non-Line-of-Sight (NLOS) ReID, which extends perception beyond direct visibility. Furthermore, we examine tri-spectral and multi-modal fusion ReID, discussing how complementary information from diverse sensors enhances robustness. Beyond summarizing datasets, challenges, and methodologies, we propose a Transformer-based baseline framework for visible-infrared ReID, designed to effectively capture modality-invariant features. Finally, based on the current landscape, we outline several promising directions for future research.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

242 extracted references · 21 linked inside Pith

  1. [1]

    Cao, C., Fu, X., Xu, S., Ge, C., Wang, K., Zha, Z.: Learning robust event- guided representations for person re-identification. Int. J. Comput. Vis.134(2), 82 (2026)

    2026

  2. [2]

    Dai, Y., Sun, Y., Liu, J., Tong, Z., Duan, L.: Bridging the source-to-target gap for cross-domain person re-identification with intermediate domains. Int. J. Comput. Vis.133(1), 410–434 (2025)

    2025

  3. [3]

    Zhang, G., Tan, S., Ji, Z., Fang, Y.: Dynamic attention vision-language trans- former network for person re-identification. Int. J. Comput. Vis.133(4), 1927–1939 (2025)

    1927

  4. [4]

    arXiv preprint arXiv:1610.02984 (2016)

    Zheng, L., Yang, Y., Hauptmann, A.G.: Person re-identification: Past, present and future. arXiv preprint arXiv:1610.02984 (2016)

    Pith/arXiv arXiv 2016

  5. [5]

    In: International Conference on Neural Information Processing, pp

    Wieczorek, M., Rychalska, B., Dąbrowski, J.: On the unreasonable effective- ness of centroids in image retrieval. In: International Conference on Neural Information Processing, pp. 212–223 (2021). Springer

    2021

  6. [6]

    In: Proceedings of the AAAI Conference on Artificial Intelligence, vol

    Wang, G., Lai, J., Huang, P., Xie, X.: Spatial-temporal person re-identification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8933–8940 (2019)

    2019

  7. [7]

    Journal of Big Data10(1), 74 (2023)

    Alnissany, A., Dayoub, Y.: Modified centroid triplet loss for person re- identification. Journal of Big Data10(1), 74 (2023)

    2023

  8. [8]

    Image and Vision Computing116, 104330 (2021)

    Zang, X., Li, G., Gao, W., Shu, X.: Learning to disentangle scenes for person re-identification. Image and Vision Computing116, 104330 (2021)

    2021

  9. [9]

    In: ICASSP 2023- 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp

    Shi, X., Liu, H., Shi, W., Zhou, Z., Li, Y.: Boosting person re-identification 40 with viewpoint contrastive learning and adversarial training. In: ICASSP 2023- 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1–5 (2023). IEEE

    2023

  10. [10]

    In: Advances in Neural Information Processing Systems, vol

    Gong, Y., Zhong, Z., Qu, Y., Luo, Z., Ji, R., Jiang, M.: Cross-modality per- turbation synergy attack for person re-identification. In: Advances in Neural Information Processing Systems, vol. 37, pp. 23352–23377 (2024)

    2024

  11. [11]

    In: Proceedings of the IEEE International Conference on Computer Vision, pp

    Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable per- son re-identification: A benchmark. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1116–1124 (2015)

    2015

  12. [12]

    In: 2012 19th IEEE International Conference on Image Processing, pp

    D’Orazio, T., Cicirelli, G.: People re-identification and tracking from multi- ple cameras: A review. In: 2012 19th IEEE International Conference on Image Processing, pp. 1601–1604 (2012). IEEE

    2012

  13. [13]

    Image and vision computing32(4), 270–286 (2014)

    Bedagkar-Gala, A., Shah, S.K.: A survey of approaches and trends in person re-identification. Image and vision computing32(4), 270–286 (2014)

    2014

  14. [14]

    arXiv preprint arXiv:1307.5748 (2013)

    Satta, R.: Appearance descriptors for person re-identification: a comprehensive review. arXiv preprint arXiv:1307.5748 (2013)

    Pith/arXiv arXiv 2013

  15. [15]

    IEEE Transactions on Circuits and Systems for Video Technology30(4), 1092– 1108 (2019)

    Leng, Q., Ye, M., Tian, Q.: A survey of open-world person re-identification. IEEE Transactions on Circuits and Systems for Video Technology30(4), 1092– 1108 (2019)

    2019

  16. [16]

    IEEE Transactions on Pattern Analysis and Machine Intelligence44(6), 2872–2893 (2022) https://doi.org/10

    Ye, M., Shen, J., Lin, G., Xiang, T., Shao, L., Hoi, S.C.H.: Deep learning for person re-identification: A survey and outlook. IEEE Transactions on Pattern Analysis and Machine Intelligence44(6), 2872–2893 (2022) https://doi.org/10. 1109/TPAMI.2021.3054775

    arXiv 2022

  17. [17]

    Electronics 11(3), 454 (2022)

    Zheng, H., Zhong, X., Huang, W., Jiang, K., Liu, W., Wang, Z.: Visible-infrared person re-identification: A comprehensive survey and a new setting. Electronics 11(3), 454 (2022)

    2022

  18. [18]

    Multimedia Tools and Applications83(42), 90243–90270 (2024)

    Chang, H., Xu, X., Liu, W., Lu, L., Li, W.: A comprehensive survey of visible infrared person re-identification from an application perspective. Multimedia Tools and Applications83(42), 90243–90270 (2024)

    2024

  19. [19]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Nguyen, V.D., Mirza, S., Zakeri, A., Gupta, A., Khaldi, K., Aloui, R., Mantini, P., Shah, S.K., Merchant, F.: Tackling domain shifts in person re-identification: A survey and analysis. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4149–4159 (2024)

    2024

  20. [20]

    Mathematics12(16), 2495 (2024) 41

    Chen, Y., Wang, K., Ye, H., Tao, L., Tie, Z.: Person re-identification in special scenes based on deep learning: A comprehensive survey. Mathematics12(16), 2495 (2024) 41

    2024

  21. [21]

    arXiv preprint arXiv:1905.10048 (2019)

    Wang, Z., Wang, Z., Zheng, Y., Wu, Y., Zeng, W., Satoh, S.: Beyond intra- modality: A survey of heterogeneous person re-identification. arXiv preprint arXiv:1905.10048 (2019)

    Pith/arXiv arXiv 1905

  22. [22]

    Infor- mation Fusion91, 396–411 (2023)

    Huang, N., Liu, J., Miao, Y., Zhang, Q., Han, J.: Deep learning for visible- infrared cross-modality person re-identification: A comprehensive review. Infor- mation Fusion91, 396–411 (2023)

    2023

  23. [23]

    In: Visual Analysis of Behaviour: From Pixels to Semantics, pp

    Gong, S., Xiang, T.: Person re-identification. In: Visual Analysis of Behaviour: From Pixels to Semantics, pp. 301–313. Springer, ??? (2014)

    2014

  24. [24]

    In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)

    Wu, A., Zheng, W.-S., Yu, H.-X., Gong, S., Lai, J.: Rgb-infrared cross-modality person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)

    2017

  25. [25]

    Sensors17(3), 605 (2017)

    Nguyen, D.T., Hong, H.G., Kim, K.W., Park, K.R.: Person recognition system based on a combination of body images from visible light and thermal cameras. Sensors17(3), 605 (2017)

    2017

  26. [26]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    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. 2153–2162 (2023)

    2023

  27. [27]

    In: Proceedings of the AAAI Conference on Artificial Intelligence, vol

    Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmen- tation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 13001–13008 (2020)

    2020

  28. [28]

    In: Proceedings of the European Confer- ence on Computer Vision (ECCV) Workshops, pp

    Kniaz, V.V., Knyaz, V.A., Hladuvka, J., Kropatsch, W.G., Mizginov, V.: Thermalgan: Multimodal color-to-thermal image translation for person re- identification in multispectral dataset. In: Proceedings of the European Confer- ence on Computer Vision (ECCV) Workshops, pp. 1–10 (2018)

    2018

  29. [29]

    In: Proceedings of the 2020 International Conference on Multimedia Retrieval, pp

    Zhong, X., Lu, T., Huang, W., Yuan, J., Liu, W., Lin, C.-W.: Visible-infrared person re-identification via colorization-based siamese generative adversarial network. In: Proceedings of the 2020 International Conference on Multimedia Retrieval, pp. 421–427 (2020)

    2020

  30. [30]

    In: Pro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Wang, Z., Wang, Z., Zheng, Y., Chuang, Y.-Y., Satoh, S.: Learning to reduce dual-level discrepancy for infrared-visible person re-identification. In: Pro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 618–626 (2019)

    2019

  31. [31]

    In: Proceedings of the IEEE International Conference on Computer Vision, pp

    Zhu, J.-Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image transla- tion using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223–2232 (2017) 42

    2017

  32. [32]

    IEEE Transactions on Circuits and Systems for Video Technology34(1), 518–533 (2023)

    Qi, J., Liang, T., Liu, W., Li, Y., Jin, Y.: A generative-based image fusion strat- egy for visible-infrared person re-identification. IEEE Transactions on Circuits and Systems for Video Technology34(1), 518–533 (2023)

    2023

  33. [33]

    IEEE Signal Processing Letters31, 346–350 (2024)

    Qian, Y., Tang, S.-K.: Pose attention-guided paired-images generation for visible-infrared person re-identification. IEEE Signal Processing Letters31, 346–350 (2024)

    2024

  34. [34]

    In: Proceedings of the 29th ACM International Conference on Multimedia, pp

    Zhang, Y., Yan, Y., Lu, Y., Wang, H.: Towards a unified middle modality learn- ing for visible-infrared person re-identification. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 788–796 (2021)

    2021

  35. [35]

    Huang, Z., Liu, J., Li, L., Zheng, K., Zha, Z.-J.: Modality-adaptive mixup and invariantdecompositionforrgb-infraredpersonre-identification.In:Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 1034–1042 (2022)

    2022

  36. [36]

    Pattern Recognition157, 110873 (2025)

    Qian, Z., Lin, Y., Du, B.: Visible–infrared person re-identification via patch- mixed cross-modality learning. Pattern Recognition157, 110873 (2025)

    2025

  37. [37]

    In: IJCAI, vol

    Ye, M., Wang, Z., Lan, X., Yuen, P.C.: Visible thermal person re-identification via dual-constrained top-ranking. In: IJCAI, vol. 1, p. 2 (2018)

    2018

  38. [38]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Choi,S.,Lee,S.,Kim,Y.,Kim,T.,Kim,C.:Hi-cmd:Hierarchicalcross-modality disentanglement for visible-infrared person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10257–10266 (2020)

    2020

  39. [39]

    In: Proceedings of the AAAI Conference on Artificial Intelligence, vol

    Wang, G.-A., Zhang, T., Yang, Y., Cheng, J., Chang, J., Liang, X., Hou, Z.-G.: Cross-modality paired-images generation for rgb-infrared person re- identification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12144–12151 (2020)

    2020

  40. [40]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp

    Wang, G., Zhang, T., Cheng, J., Liu, S., Yang, Y., Hou, Z.: 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. 3623–3632 (2019)

    2019

  41. [41]

    In: Proceedings of the AAAI Conference on Artificial Intelligence, vol

    Li, D., Wei, X., Hong, X., Gong, Y.: Infrared-visible cross-modal person re- identification with an x modality. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 4610–4617 (2020)

    2020

  42. [42]

    Crandall, D., Shao, L., Luo, J.: Dynamic dual-attentive aggregation learning for visible-infrared person re-identification

    Ye, M., Shen, J., J. Crandall, D., Shao, L., Luo, J.: Dynamic dual-attentive aggregation learning for visible-infrared person re-identification. In: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XVII 16, pp. 229–247 (2020). Springer 43

    2020

  43. [43]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp

    Park, H., Lee, S., Lee, J., Ham, B.: Learning by aligning: Visible-infrared per- son re-identification using cross-modal correspondences. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 12046–12055 (2021)

    2021

  44. [44]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Chen, Y., Wan, L., Li, Z., Jing, Q., Sun, Z.: Neural feature search for rgb- infrared person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 587–597 (2021)

    2021

  45. [45]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp

    Fu, C., Hu, Y., Wu, X., Shi, H., Mei, T., He, R.: Cm-nas: Cross-modality neural architecture search for visible-infrared person re-identification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 11823– 11832 (2021)

    2021

  46. [46]

    In: International Conference on Computer Vision, pp

    Hao, X., Zhao, S., Ye, M., Shen, J.: Cross-modality person re-identification via modality confusion and center aggregation. In: International Conference on Computer Vision, pp. 16403–16412 (2021)

    2021

  47. [47]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Zhang, Q., Lai, C., Liu, J., Huang, N., Han, J.: Fmcnet: Feature-level modality compensation for visible-infrared person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7349– 7358 (2022)

    2022

  48. [48]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp

    Wei, Z., Yang, X., Wang, N., Gao, X.: Syncretic modality collaborative learning for visible infrared person re-identification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 225–234 (2021)

    2021

  49. [49]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Yang, M., Huang, Z., Hu, P., Li, T., Lv, J., Peng, X.: Learning with twin noisy labels for visible-infrared person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14308–14317 (2022)

    2022

  50. [50]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp

    Ye, M., Ruan, W., Du, B., Shou, M.Z.: Channel augmented joint learning for visible-infrared recognition. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 13567–13576 (2021)

    2021

  51. [51]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Wu, Q., Dai, P., Chen, J., Lin, C.-W., Wu, Y., Huang, F., Zhong, B., Ji, R.: Discover cross-modality nuances for visible-infrared person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4330–4339 (2021)

    2021

  52. [52]

    In: Proceedings of the 30th ACM International Conference on Multimedia, pp

    Sun, H., Liu, J., Zhang, Z., Wang, C., Qu, Y., Xie, Y., Ma, L.: Not all pixels are matched: Dense contrastive learning for cross-modality person re-identification. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5333–5341 (2022) 44

    2022

  53. [53]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Liu, J., Sun, Y., Zhu, F., Pei, H., Yang, Y., Li, W.: Learning memory- augmented unidirectional metrics for cross-modality person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 19366–19375 (2022)

    2022

  54. [54]

    In: Winter Conference on Applications of Computer Vision (WACV), pp

    Kim, S., Gwon, S., Seo, K.: Enhancing diverse intra-identity representation for visible-infrared person re-identification. In: Winter Conference on Applications of Computer Vision (WACV), pp. 2513–2522 (2024)

    2024

  55. [55]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Kim, M., Kim, S., Park, J., Park, S., Sohn, K.: Partmix: Regularization strat- egy to learn part discovery for visible-infrared person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 18621–18632 (2023)

    2023

  56. [56]

    IEEE Transactions on Information Forensics and Security16, 728–739 (2020)

    Ye, M., Shen, J., Shao, L.: Visible-infrared person re-identification via homo- geneous augmented tri-modal learning. IEEE Transactions on Information Forensics and Security16, 728–739 (2020)

    2020

  57. [57]

    IEEE Transactions on neural networks and learning systems34(4), 1958–1971 (2021)

    Liu, H., Ma, S., Xia, D.: Sfanet: A spectrum-aware feature augmentation net- work for visible-infrared person reidentification. IEEE Transactions on neural networks and learning systems34(4), 1958–1971 (2021)

    1958

  58. [58]

    IEEE Transactions on Circuits and Systems for Video Technology (2024)

    Zhang, H., Cheng, S., Du, A.: Multi-stage auxiliary learning for visible-infrared person re-identification. IEEE Transactions on Circuits and Systems for Video Technology (2024)

    2024

  59. [59]

    IEEE Transactions on Pattern Analysis and Machine Intelligence 46(4), 2299–2315 (2023)

    Ye, M., Wu, Z., Chen, C., Du, B.: Channel augmentation for visible-infrared re- identification. IEEE Transactions on Pattern Analysis and Machine Intelligence 46(4), 2299–2315 (2023)

    2023

  60. [60]

    IEEE Transactions on Information Forensics and Security18, 1554–1565 (2022)

    Zhang, Y., Kang, Y., Zhao, S., Shen, J.: Dual-semantic consistency learning for visible-infrared person re-identification. IEEE Transactions on Information Forensics and Security18, 1554–1565 (2022)

    2022

  61. [61]

    arXiv preprint arXiv:2003.00213 (2020)

    Fan, X., Luo, H., Zhang, C., Jiang, W.: Cross-spectrum dual-subspace pair- ing for rgb-infrared cross-modality person re-identification. arXiv preprint arXiv:2003.00213 (2020)

    Pith/arXiv arXiv 2003

  62. [62]

    arXiv preprint arXiv:2411.01225 (2024)

    Tan, L., Zhang, Y., Han, K., Dai, P., Zhang, Y., Wu, Y., Ji, R.: Rle: A uni- fied perspective of data augmentation for cross-spectral re-identification. arXiv preprint arXiv:2411.01225 (2024)

    Pith/arXiv arXiv 2024

  63. [63]

    IEEE Transactions on Information Forensics and Security (2025) 45

    Alehdaghi, M., Josi, A., Cruz, R.M., Shamsolameli, P., Granger, E.: Adaptive generation of privileged intermediate information for visible-infrared person re- identification. IEEE Transactions on Information Forensics and Security (2025) 45

    2025

  64. [64]

    In: Proceedings of the 28th ACM International Conference on Multimedia, pp

    Pu, N., Chen, W., Liu, Y., Bakker, E.M., Lew, M.S.: Dual gaussian-based vari- ational subspace disentanglement for visible-infrared person re-identification. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2149–2158 (2020)

    2020

  65. [65]

    In: IEEE International Conference on Multimedia and Expo (ICME), pp

    Li, X., Liang, T., Jin, Y., Wang, T., Li, Y.: Camera-aware style separation and contrastive learning for unsupervised person re-identification. In: IEEE International Conference on Multimedia and Expo (ICME), pp. 1–6 (2022). IEEE

    2022

  66. [66]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp

    Feng, J., Wu, A., Zheng, W.-S.: Shape-erased feature learning for visible- infrared person re-identification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 22752–22761 (2023)

    2023

  67. [67]

    Pattern Recognition135, 109145 (2023)

    Huang, N., Liu, J., Luo, Y., Zhang, Q., Han, J.: Exploring modality-shared appearance features and modality-invariant relation features for cross-modality person re-identification. Pattern Recognition135, 109145 (2023)

    2023

  68. [68]

    Electronics13(14), 2825 (2024)

    Zhou, F., Cheng, Z., Yang, H., Song, Y., Fu, S.: Progressive discriminative feature learning for visible-infrared person re-identification. Electronics13(14), 2825 (2024)

    2024

  69. [69]

    In: IJCAI, vol

    Dai, P., Ji, R., Wang, H., Wu, Q., Huang, Y.: Cross-modality person re- identification with generative adversarial training. In: IJCAI, vol. 1, p. 6 (2018)

    2018

  70. [70]

    IEEE Transactions on Image Processing29, 579–590 (2019)

    Feng, Z., Lai, J., Xie, X.: Learning modality-specific representations for visible- infrared person re-identification. IEEE Transactions on Image Processing29, 579–590 (2019)

    2019

  71. [71]

    IEEE transactions on information forensics and security15, 407–419 (2019)

    Ye, M., Lan, X., Wang, Z., Yuen, P.C.: Bi-directional center-constrained top- ranking for visible thermal person re-identification. IEEE transactions on information forensics and security15, 407–419 (2019)

    2019

  72. [72]

    Neurocomputing386, 97–109 (2020)

    Zhu, Y., Yang, Z., Wang, L., Zhao, S., Hu, X., Tao, D.: Hetero-center loss for cross-modality person re-identification. Neurocomputing386, 97–109 (2020)

    2020

  73. [73]

    IEEE Transactions on neural networks and learning systems (2021)

    Zhang, L., Du, G., Liu, F., Tu, H.: Global-local multiple granularity learning for cross-modality visible-infrared person reidentification. IEEE Transactions on neural networks and learning systems (2021)

    2021

  74. [74]

    In: European Conference on Computer Vision, pp

    Zhang, Y., Zhao, S., Kang, Y.: Modality synergy complement learning with cascaded aggregation for visible-infrared person re-identification. In: European Conference on Computer Vision, pp. 462–479 (2022). Springer

    2022

  75. [75]

    In: Proceedings of the IEEE/CVF 46 International Conference on Computer Vision, pp

    Yu, H., Cheng, X., Peng, W., Liu, W., Zhao, G.: Modality unifying network for visible-infrared person re-identification. In: Proceedings of the IEEE/CVF 46 International Conference on Computer Vision, pp. 11185–11195 (2023)

    2023

  76. [76]

    arXiv preprint arXiv:2110.08994 (2021)

    Liang, T., Jin, Y., Gao, Y., Liu, W., Feng, S., Wang, T., Li, Y.: Cmtr: Cross- modality transformer for visible-infrared person re-identification. arXiv preprint arXiv:2110.08994 (2021)

    Pith/arXiv arXiv 2021

  77. [77]

    IEEE Transactions on multimedia 25, 3668–3680 (2022)

    Zhao, J., Wang, H., Zhou, Y., Yao, R.: Spatial-channel enhanced transformer for visible-infrared person re-identification. IEEE Transactions on multimedia 25, 3668–3680 (2022)

    2022

  78. [78]

    IEEE Transactions on Circuits and Systems for Video Technology33(11), 6764–6776 (2023)

    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 Transactions on Circuits and Systems for Video Technology33(11), 6764–6776 (2023)

    2023

  79. [79]

    IEEE Transactions on Instrumentation and Measurement73, 1–10 (2024)

    Liu, M., Sun, Y., Wang, X., Bian, Y.: Pose-guided modality-invariant feature alignment for visible–infrared object re-identification. IEEE Transactions on Instrumentation and Measurement73, 1–10 (2024)

    2024

  80. [80]

    Neurocomputing556, 126652 (2023)

    Miao, Y., Huang, N., Ma, X., Zhang, Q., Han, J.: On exploring pose estima- tion as an auxiliary learning task for visible–infrared person re-identification. Neurocomputing556, 126652 (2023)

    2023

Showing first 80 references.