CREST: Convolutional Residual Learning for Visual Tracking

@article{Song2017CRESTCR,
  title={CREST: Convolutional Residual Learning for Visual Tracking},
  author={Yibing Song and Chao Ma and Lijun Gong and Jiawei Zhang and Rynson W. H. Lau and Ming-Hsuan Yang},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={2574-2583}
}
Discriminative correlation filters (DCFs) have been shown to perform superiorly in visual tracking. They only need a small set of training samples from the initial frame to generate an appearance model. However, existing DCFs learn the filters separately from feature extraction, and update these filters using a moving average operation with an empirical weight. These DCF trackers hardly benefit from the end-to-end training. In this paper, we propose the CREST algorithm to reformulate DCFs as a… Expand
Learning Non-local Representation for Visual Tracking
TLDR
A tracking architecture to fuse the local and global response map for visual tracking in an accuracy and robust way is proposed and achieves state-of-the-art performance on three popular benchmarks: OTB-2013, OTB 2015 and VOT2016. Expand
A Robust Visual Tracking Algorithm Based on Spatial-Temporal Context Hierarchical Response Fusion
TLDR
The hierarchical features of convolutional neural networks (CNNs) are utilized and a spatial-temporal context correlation filter onconvolutional layers is learned to estimate scale from the best confidence results and a re-detection activation discrimination method is proposed to improve the robustness of visual tracking in the case of tracking failure. Expand
Learning target-focusing convolutional regression model for visual object tracking
TLDR
A target-focusing convolutional regression model for visual object tracking tasks (called TFCR) that can effectively balance the disequilibrium of positive and negative samples by reducing some effects of the negative samples that act on the object appearance model. Expand
Visual object tracking with adaptive structural convolutional network
TLDR
This paper proposes an adaptive structural convolutional filter model to enhance the robustness of deep regression trackers (named: ASCT), and develops an end-to-end trainable network comprising feature extraction, decision making, and model updating modules for effective training. Expand
Residual Attention Convolutional Network for Online Visual Tracking
TLDR
A residual attention module is proposed to the one layer convolutional network to inhibit the descent of discriminative ability caused by over fitness to achieve favorable performance compared with the state-of-art trackers. Expand
Augmenting cascaded correlation filters with spatial-temporal saliency for visual tracking
TLDR
The experimental results show that the proposed visual tracking approach achieves state-of-the-art performance and performs extremely well in tracking nonrigid, fast moving, or occluded objects. Expand
DSNet: Deep and Shallow Feature Learning for Efficient Visual Tracking
TLDR
A deep and shallow feature learning network is presented to learn the multi-level same-resolution compressed (MSC) features for efficient online tracking, in an end-to-end offline manner and shows that the learned MSC features have the appealing advantage of allowing the equipped DCF-based tracking methods to perform favorably against the state-of-the-art methods while running at high frame rates. Expand
Learning Spatial-Channel Attention for Visual Tracking
TLDR
This work leverages spatial attention and channel attention to enhance features of objects without much extra computational cost and proposes inter-instance loss to make the tracker be aware of not only target-background classification but also instances classification across multi-domains. Expand
Scale estimation-based visual tracking with optimized convolutional activation features
TLDR
This paper proposes an algorithm which, by interpreting scale correlation filters as the corresponding function of convolution filters in deep neural networks, exploits multilevel CNNs activation features into a new tracking framework and test the proposed tracking method on large-scale benchmark sequences. Expand
Visual Tracking by Structurally Optimizing Pre-Trained CNN
TLDR
Experimental results on challenging benchmarks show that the proposed channel pruning method can enhance the tracking performance and reduce the computational requirements. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 56 REFERENCES
Convolutional Features for Correlation Filter Based Visual Tracking
TLDR
The results suggest that activations from the first layer provide superior tracking performance compared to the deeper layers, and show that the convolutional features provide improved results compared to standard hand-crafted features. Expand
DeepTrack: Learning Discriminative Feature Representations by Convolutional Neural Networks for Visual Tracking
TLDR
A model-free tracker that outperforms the existing state-of-the-art algorithms and rarely loses the track of the target object is proposed and a class-specific version of the proposed method that is tailored for tracking of a particular object class such as human faces is introduced. Expand
Learning a Deep Compact Image Representation for Visual Tracking
TLDR
Comparison with the state-of-the-art trackers on some challenging benchmark video sequences shows that the deep learning tracker is more accurate while maintaining low computational cost with real-time performance when the MATLAB implementation of the tracker is used with a modest graphics processing unit (GPU). Expand
Learning Spatially Regularized Correlation Filters for Visual Tracking
TLDR
The proposed SRDCF formulation allows the correlation filters to be learned on a significantly larger set of negative training samples, without corrupting the positive samples, and an optimization strategy is proposed, based on the iterative Gauss-Seidel method, for efficient online learning. Expand
Hierarchical Convolutional Features for Visual Tracking
TLDR
This paper adaptively learn correlation filters on each convolutional layer to encode the target appearance and hierarchically infer the maximum response of each layer to locate targets. Expand
Visual Tracking with Fully Convolutional Networks
TLDR
An in-depth study on the properties of CNN features offline pre-trained on massive image data and classification task on ImageNet shows that the proposed tacker outperforms the state-of-the-art significantly. Expand
Fully-Convolutional Siamese Networks for Object Tracking
TLDR
A basic tracking algorithm is equipped with a novel fully-convolutional Siamese network trained end-to-end on the ILSVRC15 dataset for object detection in video and achieves state-of-the-art performance in multiple benchmarks. Expand
Learning to Track at 100 FPS with Deep Regression Networks
TLDR
This work proposes a method for offline training of neural networks that can track novel objects at test-time at 100 fps, which is significantly faster than previous methods that use neural networks for tracking, which are typically very slow to run and not practical for real-time applications. Expand
STCT: Sequentially Training Convolutional Networks for Visual Tracking
TLDR
The proposed sequential training method for convolutional neural networks to effectively transfer pre-trained deep features for online applications is applied to visual tracking problem by transferring deep features trained on massive annotated visual data and is shown to significantly improve tracking performance. Expand
Transfer Learning Based Visual Tracking with Gaussian Processes Regression
TLDR
This paper directly analyze this probability of target appearance as exponentially related to the confidence of a classifier output using Gaussian Processes Regression (GPR), and introduces a latent variable to assist the tracking decision. Expand
...
1
2
3
4
5
...