Open Set Pedestrian Re Identification through Uncertainty Calibrated Vision Language Similarity
Global Media and Social Sciences Research Journal · 01.02.2026 · 7 (1) · 19-25
DOI: 10.71465/gmssrj140 ↗Kurz gefasst
Fachartikel in der Zeitschrift Global Media and Social Sciences Research Journal, online erschienen am 01.02.2026. Verfasst von Rahul Sharma und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Single-frame pedestrian re-identification is often unstable in traffic scenes due to motion blur and partial visibility, whereas short video clips provide complementary cues. Building on uncertainty-aware CLIP-style modal representations, this work proposes an uncertainty-guided temporal aggregation module that assigns lower weights to unreliable frames and aligns clip-level visual features with text-derived semantic prompts. The model is evaluated on video-based autonomous driving benchmarks containing 52,000 tracklets and 1.1 million frames, with clip lengths ranging from 8 to 32 frames. Comparisons are conducted against video ReID baselines such as temporal pooling, recurrent aggregation, and transformer-based sequence models, as well as frame-level TransReID and CLIP-based methods. The proposed approach improves clip-level mAP by 3.6%–5.4% and rank-1 accuracy by 2.8%–4.1%, with additional gains in fast-motion segments where frame uncertainty is high.
Zitieren
APA
Sharma, R., Gupta, A., & Iyer, V. (2026). Open Set Pedestrian Re Identification through Uncertainty Calibrated Vision Language Similarity. Global Media and Social Sciences Research Journal, 7(1), 19-25. https://doi.org/10.71465/gmssrj140
Vancouver
Sharma R, Gupta A, Iyer V. Open Set Pedestrian Re Identification through Uncertainty Calibrated Vision Language Similarity. Global Media and Social Sciences Research Journal. 2026;7(1):19-25. doi:10.71465/gmssrj140
BibTeX
@article{Sharma2026,
author = {Sharma, Rahul and Gupta, Ananya and Iyer, Vikram},
title = {Open Set Pedestrian Re Identification through Uncertainty Calibrated Vision Language Similarity},
journal = {Global Media and Social Sciences Research Journal},
year = {2026},
volume = {7},
number = {1},
pages = {19--25},
doi = {10.71465/gmssrj140}
}
EUVIMED