Jiaxu Wan

Jiaxu Wan

Auto-generated profile, based on publicly available information

Jiaxu Wan

The School of Astronautics, Beihang University, Beijing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 December 2024 in ACM Transactions on Multimedia Computing, Communications, and Applications
Verified
Journal Article
Open access
HZHong Zhang
Hong Zhang
JWJiaxu Wan
Jiaxu Wan
JZJing Zhang
Jing Zhang
DYDing Yuan
Ding Yuan
XLXuliang Li
Xuliang Li
YYYifan Yang
Yifan Yang
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.

8 July 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YYYifan Yang
Yifan Yang
ZMZiqi He Martin
Ziqi He Martin
JWJiaxu Wan
Jiaxu Wan
DYDing Yuan
Ding Yuan
HLHanyang Liu
Hanyang Liu
HZHong Zhang
Hong Zhang
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.

26 February 2026 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
HZHong Zhang
Hong Zhang
JWJiaxu Wan
Jiaxu Wan
JSJianbo Song
Jianbo Song
HLHanyang Liu
Hanyang Liu
DYDing Yuan
Ding Yuan
YYYifan Yang
Yifan Yang

24 October 2026 in Neurocomputing
Verified
Journal Article
Closed access
DYDing Yuan
Ding Yuan
YMYuqian Meng
Yuqian Meng
JWJiaxu Wan
Jiaxu Wan
DYDeng Yangyan
Deng Yangyan
HZHong Zhang
Hong Zhang
YYYifan Yang
Yifan Yang

14 November 2026
Verified
Book Chapter
Closed access
PDF file
HLHaotian Li
Haotian Li
DYDing Yuan
Ding Yuan
JWJiaxu Wan
Jiaxu Wan
HZHong Zhang
Hong Zhang
YYYifan Yang
Yifan Yang