EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Vision Transformers in Person Re-Identification: A Review

Bariş Ünver, Mehmet Türkay Yoldar, Simay Özkan, Murat Köklü

IEEE Access · 2026 · 14 · 92748-92764

DOI: 10.1109/access.2026.3704666 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Bariş Ünver und 3 weiteren Autor:innen. Die Arbeit nennt 115 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Vision transformers (ViTs) have emerged as the dominant architecture for person re-identification (Re-ID)—the task of matching individuals across spatially disjoint surveillance cameras in the face of substantial variation in viewpoint, lighting, occlusion, and clothing. This article provides a focused review of transformer-based Re-ID, covering the CNN-to-ViT transition, pure transformer backbones, efficiency-oriented approximations, occlusion-hardened variants, parameter-efficient foundation-model adaptations, spatio-temporal models for video Re-ID, and unified multimodal frameworks. The analysis is organised along five axes: architectural progression from convolutional to self-attention representations; design choices governing efficiency, robustness, and modality coverage; foundation-model adaptation strategies; quantitative performance across established benchmarks; and outstanding research challenges. Under standard controlled benchmarks, ViT methods achieve 95%+ rank-1 accuracy in supervised settings, rising to 97.6% with CLIP-guided unsupervised clustering. Unified transformer frameworks support visible, infrared, and natural-language query modalities concurrently. Significant limitations persist, however: accuracy on cloth-changing benchmarks stalls at 40–60%, cross-domain transfer incurs 15–25% degradation, adversarial patch perturbations can reduce performance to near zero, and on-device inference cost constrains practical deployment. The review synthesises these findings, delineating where transformers have substantively advanced Re-ID and where fundamental challenges remain unsolved.

Zitieren

APA

Ünver, B., Yoldar, M. T., Özkan, S., & Köklü, M. (2026). Vision Transformers in Person Re-Identification: A Review. IEEE Access, 14, 92748-92764. https://doi.org/10.1109/access.2026.3704666

Vancouver

Ünver B, Yoldar MT, Özkan S, Köklü M. Vision Transformers in Person Re-Identification: A Review. IEEE Access. 2026;14:92748-92764. doi:10.1109/access.2026.3704666

BibTeX
@article{nver2026,
  author = {Ünver, Bariş and Yoldar, Mehmet Türkay and Özkan, Simay and Köklü, Murat},
  title = {Vision Transformers in Person Re-Identification: A Review},
  journal = {IEEE Access},
  year = {2026},
  volume = {14},
  pages = {92748--92764},
  doi = {10.1109/access.2026.3704666}
}
Kostenlos starten →