Learning Dynamic Siamese Network for Visual Object Tracking

2017 ◽  
Author(s):  
Qing Guo ◽  
Wei Feng ◽  
Ce Zhou ◽  
Rui Huang ◽  
Liang Wan ◽  
...  
Keyword(s):  
Object Tracking ◽  
Visual Object ◽  
Visual Object Tracking ◽  
Siamese Network ◽  
Learning Dynamic

Attention shake siamese network with auxiliary relocation branch for visual object tracking

2020 ◽  
Vol 400 ◽  
pp. 53-72
Author(s):  
Jun Wang ◽  
Weibin Liu ◽  
Weiwei Xing ◽  
Liqiang Wang ◽  
Shunli Zhang
Keyword(s):  
Object Tracking ◽  
Visual Object ◽  
Visual Object Tracking ◽  
Siamese Network

Visual Object Tracking by Hierarchical Attention Siamese Network

2020 ◽  
Vol 50 (7) ◽  
pp. 3068-3080 ◽  
Author(s):  
Jianbing Shen ◽  
Xin Tang ◽  
Xingping Dong ◽  
Ling Shao
Keyword(s):  
Object Tracking ◽  
Visual Object ◽  
Visual Object Tracking ◽  
Siamese Network

scholarly journals Online Siamese Network for Visual Object Tracking

Sensors ◽  
2019 ◽  
Vol 19 (8) ◽  
pp. 1858 ◽  
Author(s):  
Shuo Chang ◽  
Wei Li ◽  
Yifan Zhang ◽  
Zhiyong Feng
Keyword(s):  
Object Tracking ◽  
Domain Knowledge ◽  
Face Verification ◽  
Visual Object ◽  
Visual Object Tracking ◽  
Discrimination Capability ◽  
Verification Algorithm ◽  
Siamese Network ◽  
Comparable Performance ◽  
The Face

Offline-trained Siamese networks are not robust to the environmental complication in visual object tracking. Without online learning, the Siamese network cannot learn from instance domain knowledge and adapt to appearance changes of targets. In this paper, a new lightweight Siamese network is proposed for feature extraction. To cope with the dynamics of targets and backgrounds, the weight in the proposed Siamese network is updated in an online manner during the tracking process. In order to enhance the discrimination capability, the cross-entropy loss is integrated into the contrastive loss. Inspired by the face verification algorithm DeepID2, the Bayesian verification model is applied for candidate selection. In general, visual object tracking can benefit from face verification algorithms. Numerical results suggest that the newly developed algorithm achieves comparable performance in public benchmarks.

scholarly journals ACSiamRPN: Adaptive Context Sampling for Visual Object Tracking

Electronics ◽  
2020 ◽  
Vol 9 (9) ◽  
pp. 1528
Author(s):  
Xiaofei Qin ◽  
Yipeng Zhang ◽  
Hang Chang ◽  
Hao Lu ◽  
Xuedian Zhang
Keyword(s):  
Object Tracking ◽  
Long Range ◽  
Global Maximum ◽  
Visual Object ◽  
Visual Object Tracking ◽  
Siamese Network ◽  
Information Embedding ◽  
Selection Step ◽  
Block Based ◽  
The Impact

In visual object tracking fields, the Siamese network tracker, based on the region proposal network (SiamRPN), has achieved promising tracking effects, both in speed and accuracy. However, it did not consider the relationship and differences between the long-range context information of various objects. In this paper, we add a global context block (GC block), which is lightweight and can effectively model long-range dependency, to the Siamese network part of SiamRPN so that the object tracker can better understand the tracking scene. At the same time, we propose a novel convolution module, called a cropping-inside selective kernel block (CiSK block), based on selective kernel convolution (SK convolution, a module proposed in selective kernel networks) and use it in the region proposal network (RPN) part of SiamRPN, which can adaptively adjust the size of the receptive field for different types of objects. We make two improvements to SK convolution in the CiSK block. The first improvement is that in the fusion step of SK convolution, we use both global average pooling (GAP) and global maximum pooling (GMP) to enhance global information embedding. The second improvement is that after the selection step of SK convolution, we crop out the outermost pixels of features to reduce the impact of padding operations. The experiment results show that on the OTB100 benchmark, we achieved an accuracy of 0.857 and a success rate of 0.643. On the VOT2016 and VOT2019 benchmarks, we achieved expected average overlap (EAO) scores of 0.394 and 0.240, respectively.

Sign in / Sign up

Export Citation Format

Share Document