Video-based Person Re-IDentification (VPReID) aims to retrieve the same person from videos captured by non-overlapping cameras. At extreme far distances, VPReID is highly challenging due to severe resolution degradation, drastic viewpoint variation and inevitable appearance noise. To address these issues, we propose a Scale-Adaptive framework with Shape Priors for VPReID, named SAS-VPReID. The framework is built upon three complementary modules. First, we deploy a Memory-Enhanced Visual Backbone (MEVB) to extract discriminative feature representations, which leverages the CLIP vision encoder and multi-proxy memory. Second, we propose a Multi-Granularity Temporal Modeling (MGTM) to construct sequences at multiple temporal granularities and adaptively emphasize motion cues across scales. Third, we incorporate Prior-Regularized Shape Dynamics (PRSD) to capture body structure dynamics. With these modules, our framework can obtain more discriminative feature representations. Experiments on the VReID-XFD benchmark demonstrate the effectiveness of each module and our final framework ranks the first on the VReID-XFD challenge leaderboard. The source code is available at https://github.com/YangQiWei3/SAS-VPReID.
@article{arxiv.2601.05535,
title = {SAS-VPReID: A Scale-Adaptive Framework with Shape Priors for Video-based Person Re-Identification at Extreme Far Distances},
author = {Qiwei Yang and Pingping Zhang and Yuhao Wang and Zijing Gong},
journal= {arXiv preprint arXiv:2601.05535},
year = {2026}
}
Comments
Accepted by WACV2026 VReID-XFD Workshop. Our final framework ranks the first on the VReID-XFD challenge leaderboard