Vision Transformer based Random Walk for Group Re-Identification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916427748868096 |
|---|---|
| author | Zhang, Guoqing Liu, Tianqi Fang, Wenxuan Zheng, Yuhui |
| author_facet | Zhang, Guoqing Liu, Tianqi Fang, Wenxuan Zheng, Yuhui |
| contents | Group re-identification (re-ID) aims to match groups with the same people under different cameras, mainly involves the challenges of group members and layout changes well. Most existing methods usually use the k-nearest neighbor algorithm to update node features to consider changes in group membership, but these methods cannot solve the problem of group layout changes. To this end, we propose a novel vision transformer based random walk framework for group re-ID. Specifically, we design a vision transformer based on a monocular depth estimation algorithm to construct a graph through the average depth value of pedestrian features to fully consider the impact of camera distance on group members relationships. In addition, we propose a random walk module to reconstruct the graph by calculating affinity scores between target and gallery images to remove pedestrians who do not belong to the current group. Experimental results show that our framework is superior to most methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_05808 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Vision Transformer based Random Walk for Group Re-Identification Zhang, Guoqing Liu, Tianqi Fang, Wenxuan Zheng, Yuhui Computer Vision and Pattern Recognition Group re-identification (re-ID) aims to match groups with the same people under different cameras, mainly involves the challenges of group members and layout changes well. Most existing methods usually use the k-nearest neighbor algorithm to update node features to consider changes in group membership, but these methods cannot solve the problem of group layout changes. To this end, we propose a novel vision transformer based random walk framework for group re-ID. Specifically, we design a vision transformer based on a monocular depth estimation algorithm to construct a graph through the average depth value of pedestrian features to fully consider the impact of camera distance on group members relationships. In addition, we propose a random walk module to reconstruct the graph by calculating affinity scores between target and gallery images to remove pedestrians who do not belong to the current group. Experimental results show that our framework is superior to most methods. |
| title | Vision Transformer based Random Walk for Group Re-Identification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.05808 |