dorsal/arxiv
View SchemaSAS-VPReID: A Scale-Adaptive Framework with Shape Priors for Video-based Person Re-Identification at Extreme Far Distances
| Authors | Qiwei Yang, Pingping Zhang, Yuhao Wang, Zijing Gong |
|---|---|
| Categories | |
| ArXiv ID | 2601.05535vv1 |
| URL | https://arxiv.org/abs/2601.05535 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
Abstract
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.
{
"annotation_id": "ecf8ccd1-0962-462d-b393-9d04cb891501",
"date_created": "2026-02-17T05:53:05.048000Z",
"date_modified": "2026-02-17T05:53:05.048000Z",
"file_hash": "45507cebddfc90eca02d992f4b92e6e759540fdfb13cc0b6248d9bc6096682b9",
"private": false,
"record": {
"abstract": "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.",
"arxiv_id": "2601.05535",
"authors": [
"Qiwei Yang",
"Pingping Zhang",
"Yuhao Wang",
"Zijing Gong"
],
"categories": [
"cs.CV"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "SAS-VPReID: A Scale-Adaptive Framework with Shape Priors for Video-based Person Re-Identification at Extreme Far Distances",
"url": "https://arxiv.org/abs/2601.05535",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "585b64b7-58ec-4755-8cca-416715309134",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}