Jiaxu Wan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jiaxu Wan has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Ding Yuan
Beihang University
4 shared publications - Yifan Yang
Beihang University, Beijing, China
4 shared publications - Hong Zhang
School of Astronautics, Beihang University, Beijing 100191, China
3 shared publications - Hanyang Liu
School of Astronautics, Beihang University, Beijing, China
2 shared publications Hong Zhang
Beihang University
2 shared publicationsDing Yuan
1 shared publication
Latest Publications
- 14 November 2026
- Published by Springer Nature
- p. 224-236
Aerial-VGGT: Topology-Guided World-Model Frame Completion for Aerial 3D Reconstruction Model Adaptation
- 14 November 2026
- Published by Springer Nature
- p. 224-236
Aerial-VGGT: Topology-Guided World-Model Frame Completion for Aerial 3D Reconstruction Model Adaptation
- 24 October 2026
- Published by Elsevier in Neurocomputing
- Vol. 712
SPW-Net: An efficient soft prior-guided wavelet attention network for shadow removal
- 24 October 2026
- Published by Elsevier in Neurocomputing
- Vol. 712
SPW-Net: An efficient soft prior-guided wavelet attention network for shadow removal
- 26 February 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (3) , 138
MGFNet: Meta Global Filter Network for multi-size image feature extraction
- 26 February 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (3) , 138
MGFNet: Meta Global Filter Network for multi-size image feature extraction
- Open Access
- 23 December 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (1) , 1-22
P2FTrack: Multi-Object Tracking with Motion Prior and Feature Posterior
Multiple object tracking (MOT) has emerged as a crucial component of the rapidly developing computer vision. However, existing multi-object tracking methods often overlook the relationship between features and motion, hindering the ability to strike a performance balance between coupled motion and complex scenes. In this work, we propose a novel end-to-end multi-object tracking method that integrates motion and feature information. To achieve this, we introduce a motion prior generator that transforms motion information into attention masks. Additionally, we leverage prior-posterior fusion multi-head attention to combine the motion-derived priors and attention-based posteriors. Our proposed method is extensively evaluated on MOT17 and DanceTrack datasets through comprehensive experiments and ablation studies, demonstrating state-of-the-art performance in the feature-based method with reasonable speed.
- 23 December 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (1) , 1-22
Open AccessP2FTrack: Multi-Object Tracking with Motion Prior and Feature Posterior
Multiple object tracking (MOT) has emerged as a crucial component of the rapidly developing computer vision. However, existing multi-object tracking methods often overlook the relationship between features and motion, hindering the ability to strike a performance balance between coupled motion and complex scenes. In this work, we propose a novel end-to-end multi-object tracking method that integrates motion and feature information. To achieve this, we introduce a motion prior generator that transforms motion information into attention masks. Additionally, we leverage prior-posterior fusion multi-head attention to combine the motion-derived priors and attention-based posteriors. Our proposed method is extensively evaluated on MOT17 and DanceTrack datasets through comprehensive experiments and ablation studies, demonstrating state-of-the-art performance in the feature-based method with reasonable speed.
- Open Access
- 8 July 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (14) , 8010
FusionTrack: Multiple Object Tracking with Enhanced Information Utilization
Multi-object tracking (MOT) is one of the significant directions of computer vision. Though existing methods can solve simple tasks like pedestrian tracking well, some complex downstream tasks featuring uniform appearance and diverse motion remain difficult. Inspired by DETR, the tracking-by-attention (TBA) method uses transformers to accomplish multi-object tracking tasks. However, there are still issues with existing TBA methods within the TBA paradigm, such as difficulty detecting and tracking objects due to gradient conflict in shared parameters, and insufficient use of features to distinguish similar objects. We introduce FusionTrack to address these issues. It utilizes a joint track-detection decoder and a score-guided multi-level query fuser to enhance the usage of information within and between frames. With these improvements, FusionTrack achieves 11.1% higher by HOTA metric on the DanceTrack dataset compared with the baseline model MOTR.
- 8 July 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (14) , 8010
Open AccessFusionTrack: Multiple Object Tracking with Enhanced Information Utilization
Multi-object tracking (MOT) is one of the significant directions of computer vision. Though existing methods can solve simple tasks like pedestrian tracking well, some complex downstream tasks featuring uniform appearance and diverse motion remain difficult. Inspired by DETR, the tracking-by-attention (TBA) method uses transformers to accomplish multi-object tracking tasks. However, there are still issues with existing TBA methods within the TBA paradigm, such as difficulty detecting and tracking objects due to gradient conflict in shared parameters, and insufficient use of features to distinguish similar objects. We introduce FusionTrack to address these issues. It utilizes a joint track-detection decoder and a score-guided multi-level query fuser to enhance the usage of information within and between frames. With these improvements, FusionTrack achieves 11.1% higher by HOTA metric on the DanceTrack dataset compared with the baseline model MOTR.