Saved in:
Bibliographic Details
Main Authors: Yang, Qiwei, Zhang, Pingping, Wang, Yuhao, Gong, Zijing
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.05535
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908754757287936
author Yang, Qiwei
Zhang, Pingping
Wang, Yuhao
Gong, Zijing
author_facet Yang, Qiwei
Zhang, Pingping
Wang, Yuhao
Gong, Zijing
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_05535
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SAS-VPReID: A Scale-Adaptive Framework with Shape Priors for Video-based Person Re-Identification at Extreme Far Distances
Yang, Qiwei
Zhang, Pingping
Wang, Yuhao
Gong, Zijing
Computer Vision and Pattern Recognition
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.
title SAS-VPReID: A Scale-Adaptive Framework with Shape Priors for Video-based Person Re-Identification at Extreme Far Distances
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.05535