AG-VPReID 2025: Aerial-Ground Video-based Person Re-identification Challenge Results
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909665012482048 |
|---|---|
| author | Nguyen, Kien Fookes, Clinton Sridharan, Sridha Nguyen, Huy Liu, Feng Liu, Xiaoming Ross, Arun Michalski, Dana Endrei, Tamás DeAndres-Tame, Ivan Tolosana, Ruben Vera-Rodriguez, Ruben Morales, Aythami Fierrez, Julian Ortega-Garcia, Javier Gong, Zijing Wang, Yuhao Liu, Xuehu Zhang, Pingping Rashidunnabi, Md Proença, Hugo Hambarde, Kailash A. Rezaei, Saeid |
| author_facet | Nguyen, Kien Fookes, Clinton Sridharan, Sridha Nguyen, Huy Liu, Feng Liu, Xiaoming Ross, Arun Michalski, Dana Endrei, Tamás DeAndres-Tame, Ivan Tolosana, Ruben Vera-Rodriguez, Ruben Morales, Aythami Fierrez, Julian Ortega-Garcia, Javier Gong, Zijing Wang, Yuhao Liu, Xuehu Zhang, Pingping Rashidunnabi, Md Proença, Hugo Hambarde, Kailash A. Rezaei, Saeid |
| contents | Person re-identification (ReID) across aerial and ground vantage points has become crucial for large-scale surveillance and public safety applications. Although significant progress has been made in ground-only scenarios, bridging the aerial-ground domain gap remains a formidable challenge due to extreme viewpoint differences, scale variations, and occlusions. Building upon the achievements of the AG-ReID 2023 Challenge, this paper introduces the AG-VPReID 2025 Challenge - the first large-scale video-based competition focused on high-altitude (80-120m) aerial-ground ReID. Constructed on the new AG-VPReID dataset with 3,027 identities, over 13,500 tracklets, and approximately 3.7 million frames captured from UAVs, CCTV, and wearable cameras, the challenge featured four international teams. These teams developed solutions ranging from multi-stream architectures to transformer-based temporal reasoning and physics-informed modeling. The leading approach, X-TFCLIP from UAM, attained 72.28% Rank-1 accuracy in the aerial-to-ground ReID setting and 70.77% in the ground-to-aerial ReID setting, surpassing existing baselines while highlighting the dataset's complexity. For additional details, please refer to the official website at https://agvpreid25.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_22843 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AG-VPReID 2025: Aerial-Ground Video-based Person Re-identification Challenge Results Nguyen, Kien Fookes, Clinton Sridharan, Sridha Nguyen, Huy Liu, Feng Liu, Xiaoming Ross, Arun Michalski, Dana Endrei, Tamás DeAndres-Tame, Ivan Tolosana, Ruben Vera-Rodriguez, Ruben Morales, Aythami Fierrez, Julian Ortega-Garcia, Javier Gong, Zijing Wang, Yuhao Liu, Xuehu Zhang, Pingping Rashidunnabi, Md Proença, Hugo Hambarde, Kailash A. Rezaei, Saeid Computer Vision and Pattern Recognition Person re-identification (ReID) across aerial and ground vantage points has become crucial for large-scale surveillance and public safety applications. Although significant progress has been made in ground-only scenarios, bridging the aerial-ground domain gap remains a formidable challenge due to extreme viewpoint differences, scale variations, and occlusions. Building upon the achievements of the AG-ReID 2023 Challenge, this paper introduces the AG-VPReID 2025 Challenge - the first large-scale video-based competition focused on high-altitude (80-120m) aerial-ground ReID. Constructed on the new AG-VPReID dataset with 3,027 identities, over 13,500 tracklets, and approximately 3.7 million frames captured from UAVs, CCTV, and wearable cameras, the challenge featured four international teams. These teams developed solutions ranging from multi-stream architectures to transformer-based temporal reasoning and physics-informed modeling. The leading approach, X-TFCLIP from UAM, attained 72.28% Rank-1 accuracy in the aerial-to-ground ReID setting and 70.77% in the ground-to-aerial ReID setting, surpassing existing baselines while highlighting the dataset's complexity. For additional details, please refer to the official website at https://agvpreid25.github.io. |
| title | AG-VPReID 2025: Aerial-Ground Video-based Person Re-identification Challenge Results |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.22843 |