CASIA OpenIR  > 多模态人工智能系统全国重点实验室  > 视频内容安全
ZoomTrack: Target-aware Non-uniform Resizing for Efficient Visual Tracking
Kou, Yutong1,2; Gao, Jin1,2; Li, Bing1,5; Wang, Gang4; Hu, Weiming1,2,3; Wang, Yizheng4; Li, Liang4
2023
Conference NameThirty-seventh Conference on Neural Information Processing Systems
Conference DateSunday Dec 10 through Saturday Dec 16
Conference PlaceNew Orleans, United States
Abstract

Recently, the transformer has enabled the speed-oriented trackers to approach state-of-the-art (SOTA) performance with high-speed thanks to the smaller input size or the lighter feature extraction backbone, though they still substantially lag behind their corresponding performance-oriented versions. In this paper, we demonstrate that it is possible to narrow or even close this gap while achieving high tracking speed based on the smaller input size. To this end, we non-uniformly resize the cropped image to have a smaller input size while the resolution of the area where the target is more likely to appear is higher and vice versa. This enables us to solve the dilemma of attending to a larger visual field while retaining more raw information for the target despite a smaller input size. Our formulation for the non-uniform resizing can be efficiently solved through quadratic programming (QP) and naturally integrated into most of the crop-based local trackers. Comprehensive experiments on five challenging datasets based on two kinds of transformer trackers, \ie, OSTrack and TransT, demonstrate consistent improvements over them. In particular, applying our method to the speed-oriented version of OSTrack even outperforms its performance-oriented counterpart by 0.6% AUC on TNL2K, while running 50% faster and saving over 55% MACs. Codes and models are available at https://github.com/Kou-99/ZoomTrack.

Indexed ByEI
Sub direction classification目标检测、跟踪与识别
planning direction of the national heavy laboratory实体人工智能系统感认知
Paper associated data
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/57502
Collection多模态人工智能系统全国重点实验室_视频内容安全
Corresponding AuthorGao, Jin
Affiliation1.State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), CASIA
2.School of Artificial Intelligence, University of Chinese Academy of Sciences
3.School of Information Science and Technology, ShanghaiTech University
4.Beijing Institute of Basic Medical Sciences
5.People AI, Inc
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Kou, Yutong,Gao, Jin,Li, Bing,et al. ZoomTrack: Target-aware Non-uniform Resizing for Efficient Visual Tracking[C],2023.
Files in This Item: Download All
File Name/Size DocType Version Access License
2891_zoomtrack_targe(2115KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Kou, Yutong]'s Articles
[Gao, Jin]'s Articles
[Li, Bing]'s Articles
Baidu academic
Similar articles in Baidu academic
[Kou, Yutong]'s Articles
[Gao, Jin]'s Articles
[Li, Bing]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Kou, Yutong]'s Articles
[Gao, Jin]'s Articles
[Li, Bing]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 2891_zoomtrack_target_aware_non_uni.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.