Feature Disentanglement Network: Multi-Object Tracking Needs More Differentiated Features
文献类型：期刊论文
| 作者 | Guo, Wen3; Quan, Wuzhou3; Gao, Junyu2 ; Zhang, Tianzhu1; Xu, Changsheng2
|
| 刊名 | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
 |
| 出版日期 | 2024-03-01 |
| 卷号 | 20期号:3页码:22 |
| ISSN号 | 1551-6857 |
| 关键词 | Multiple object tracking Feature disentanglement network one-shot tracking feature enhancement |
| DOI | 10.1145/3626825 |
| 通讯作者 | Guo, Wen(wguo@sdtbu.edu.cn) |
| 英文摘要 | 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. |
| 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] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| 出版者 | ASSOC COMPUTING MACHINERY |
| WOS记录号 | WOS:001153381000023 |
| 资助机构 | National Natural Science Foundation of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/55580]  |
| 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.Univ Sci & Technol China, Sch Informat Sci & Technol, 443 Huangshan Rd, Hefei 230027, 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.Shandong Technol & Business Univ, Sch Informat & Elect Engn, 191 Binhaizhong Rd, Yantai 264005, Shandong, 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. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。