Affiliation:
1. Guangxi Key Lab of Multi-source Information Mining & Security, Guangxi Normal University, Guilin, China
2. Department of the Computer Science and Technology, Huaqiao University, Xiamen, China
Abstract
Occlusion is known as one of the most challenging factors in long-term tracking because of its unpredictable shape. Existing works devoted into the design of loss functions, training strategies or model architectures, which are considered to have not directly touched the key point. Alternatively, we came up with a direct and natural idea that is discarding things that covers the target. We propose a novel occluder-aware representation learning framework to develop this idea. First, we design a local occluders detection module (LODM) to localize the occluders, which works on the principle that discriminates the non-noumenal part from a target based on the general knowledge of this category. An extra dataset and a clustering strategy is proposed to support this general knowledge. Second, we devise a feature reconstruction module to guide the occluder-aware representation learning. With the help of above methods, our localizing occluders tracker, called LOTracker, can learn an occluder-free representation and promote the performance that tracks with occlusion scenarios. Extensive experimental results show that our LOTracker achieves a state-of-the-art performance in multiple benchmarks such as LaSOT, VOTLT2018, VOTLT2019, and OxUvALT.
Funder
Project of Guangxi Science and Technology
National Natural Science Foundation of China
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Networks and Communications,Hardware and Architecture
Reference36 articles.
1. Fully-Convolutional Siamese Networks for Object Tracking
2. Goutam Bhat, Martin Danelljan, Luc Van Gool, and Radu Timofte. 2019. Learning discriminative model prediction for tracking. In Proc. ICCV.
3. High toughness high hardness iron based PTAW weld materials
4. Hanting Chen, Yunhe Wang, Chunjing Xu, Boxin Shi, and Chang Xu. [n.d.]. AdderNet: Do we really need multiplications in deep learning?. In CVPR 2019.
5. Kenan Dai, Yunhua Zhang, Dong Wang, Jianhua Li, Huchuan Lu, and Xiaoyun Yang. 2020. High-performance long-term tracking with meta-updater. In Proc. CVPR.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献