Chunjiang Li

Chunjiang Li

Auto-generated profile, based on publicly available information

Chunjiang Li

College of Computer Science, Sichuan University, Chengdu, China

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
27 August 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
JMJianbo Ma
Jianbo Ma
FWFei Wu
Fei Wu
CLChunjiang Li
Chunjiang Li
CTchuanming tang
chuanming tang
JZJianlin Zhang
Jianlin Zhang
Dongxu LiuDongxu Liu
Dongxu Liu
The one-shot multiple object tracking framework simultaneously generates detected targets and re-identification (ReID) embeddings, and employs them to associate previous tracks. However, the continuity between the learning and extraction within the ReID task is unconsciously neglected because of treating them as two isolated stages. This leads to unreliable ReID embeddings and poses a challenge to target matching especially in complex and crowded scenarios. To this end, we propose a guided embedding enhancement multiple object tracker, named G2EMOT. It consists of three innovative designs aiming at improving the embedding representation capability for individual targets. First, based on the original feature map, a global instance-specific context decoupling (GICD) module is devised to facilitate the respective feature learning for detection and ReID branches. Then, a heatmap guided embedding enhancement (HGEE) module is introduced to connect the processes of embedding learning and extraction, ensuring that the detected target coordinates are accurately aligned with the discriminative ReID embeddings. Finally, to associate and stabilize matched targets, we present a novel two-gate guided embedding update (TG-GEU) strategy that dynamically updates ReID embeddings. With the proposed three components, G2EMOT achieves outstanding performance on popular MOT benchmarks, while outperforming the existing one-shot tracking methods by a large margin. In particular, it realizes IDF1 of 76.1% on MOT17 and IDF1 of 74.2% on MOT20. The source codes are released at https://github.com/ydhcg-BoBo/G2EMOT.

23 October 2019 in Virus Genes
Verified
Journal Article
Closed access
PDF file
CLChunjiang Li
Chunjiang Li
MIMakoto Ito
Makoto Ito
IKIchiro Kasajima
Ichiro Kasajima
NYNobuyuki Yoshikawa
Nobuyuki Yoshikawa

24 November 2014
Verified
Conference Paper
Closed access
PDF file
YLYuming Li
Yuming Li
CLChunjiang Li
Chunjiang Li
RZRan Zheng
Ran Zheng
XLXiao Li
Xiao Li
JYJun Yang
Jun Yang

9 November 2026
Verified
Conference Paper
Open access
CLChunjiang Li
Chunjiang Li
JLJunhua Liao
Junhua Liao
YZYuanyuan Zhang
Yuanyuan Zhang
LCLiangyin Chen
Liangyin Chen
YCYanru Chen
Yanru Chen