Feature Disentanglement Network: Multi-Object Tracking Needs More Differentiated Features

doi:10.1145/3626825

	Feature Disentanglement Network: Multi-Object Tracking Needs More Differentiated Features
	Guo, Wen 1; Quan, Wuzhou 1; Gao, Junyu2 ; Zhang, Tianzhu3 ; Xu, Changsheng2
发表期刊	ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
ISSN	1551-6857
	2024-03-01
卷号	20 期号:3 页码:22
通讯作者	Guo, Wen(wguo@sdtbu.edu.cn)
摘要	To reduce computational redundancies, a common approach is to integrate detection and re-identification (Re-ID) into a single network in multi-object tracking (MOT), referred to as "tracking by detection." Most of the previous research has focused on resolving the conflict between the detection and Re-ID branches, considering it a simple coupling. In our work, we uncover that the entangled state between the detection and Re-ID tasks is much more complex than previous idea, resulting in a form of competition that degrades performance. To address the preceding issue, we propose a feature disentanglement network that deeply disentangles the intricately interwoven latent space of features and provides differentiated feature maps for each individual task. Furthermore, considering the demand for shallow semantic features in the feature re-ID branch, we also introduce a feature re-globalization module to enrich the shallow semantics. By integrating two distinct networks into a one-shot online MOT method, we develop a robust MOT tracker (named HDGTrack). We conduct extensive experiments on a number of benchmarks, and our experimental results demonstrate that our method significantly outperforms state-of-the-art MOT methods. Besides, HDGTrack is efficient and can run at 13.9 (MOT17) and 8.7 (MOT20) frames per second.
关键词	Multiple object tracking Feature disentanglement network one-shot tracking feature enhancement
DOI	10.1145/3626825
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62072286] ; National Natural Science Foundation of China[61572296] ; National Natural Science Foundation of China[61876100]
项目资助者	National Natural Science Foundation of China
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods
WOS记录号	WOS:001153381000023
出版者	ASSOC COMPUTING MACHINERY
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/55581
专题	多模态人工智能系统全国重点实验室
通讯作者	Guo, Wen
作者单位	1.Shandong Technol & Business Univ, Sch Informat & Elect Engn, 191 Binhaizhong Rd, Yantai 264005, Shandong, Peoples R China 2.Chinese Acad Sci CASIA, Inst Automat, State Key Lab Multimodal Artificial Intelligence, 95 Zhongguancun East Rd, Beijing, Peoples R China 3.Univ Sci & Technol China, Sch Informat Sci & Technol, 443 Huangshan Rd, Hefei 230027, Peoples R China
推荐引用方式 GB/T 7714	Guo, Wen,Quan, Wuzhou,Gao, Junyu,et al. Feature Disentanglement Network: Multi-Object Tracking Needs More Differentiated Features[J]. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,2024,20(3):22.
APA	Guo, Wen,Quan, Wuzhou,Gao, Junyu,Zhang, Tianzhu,&Xu, Changsheng.(2024).Feature Disentanglement Network: Multi-Object Tracking Needs More Differentiated Features.ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,20(3),22.
MLA	Guo, Wen,et al."Feature Disentanglement Network: Multi-Object Tracking Needs More Differentiated Features".ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 20.3(2024):22.