Fully-Convolutional Siamese Networks for Object Tracking

@article{Bertinetto2016FullyConvolutionalSN,
  title={Fully-Convolutional Siamese Networks for Object Tracking},
  author={Luca Bertinetto and Jack Valmadre and Jo{\~a}o F. Henriques and Andrea Vedaldi and Philip H. S. Torr},
  journal={ArXiv},
  year={2016},
  volume={abs/1606.09549}
}
The problem of arbitrary object tracking has traditionally been tackled by learning a model of the object’s appearance exclusively online, using as sole training data the video itself. [...] Key Method In this paper we equip a basic tracking algorithm with a novel fully-convolutional Siamese network trained end-to-end on the ILSVRC15 dataset for object detection in video. Our tracker operates at frame-rates beyond real-time and, despite its extreme simplicity, achieves state-of-the-art performance in multiple…Expand
Learning Dynamic Siamese Network for Visual Object Tracking
TLDR
This paper proposes dynamic Siamese network, via a fast transformation learning model that enables effective online learning of target appearance variation and background suppression from previous frames, and presents elementwise multi-layer fusion to adaptively integrate the network outputs using multi-level deep features. Expand
Triplet Loss in Siamese Network for Object Tracking
TLDR
A novel triplet loss is proposed to extract expressive deep feature for object tracking by adding it into Siamese network framework instead of pairwise loss for training. Expand
A Deep Hyper Siamese Network for Real-Time Object Tracking
TLDR
A new nonpadding residual unit (NPRU) is designed and used to stack a 22-layer deep ResNet, referred as ResNet22, and it is used to build a deep hyper Siamese network, which can greatly enhance the tracking performance. Expand
Self-supervised Object Tracking with Cycle-consistent Siamese Networks
TLDR
This work proposes to integrate a Siamese region proposal and mask regression network in a cycle-consistent self-supervised framework for object tracking so that a fast and more accurate tracker can be learned without the annotation of each frame. Expand
Learning Robust Features for Planar Object Tracking
TLDR
A novel network architecture is employed, the efficient second-order minimization (ESM) layer, which performs the ESM algorithm on deep feature maps for improving the robustness of direct methods in visual tracking. Expand
SiamMT: Real-Time Arbitrary Multi-Object Tracking
TLDR
This work presents the architecture of SiamMT, a system capable of efficiently applying individual visual tracking techniques to multiple objects in real-time, and makes it the first deep-learning-based arbitrary multi-object tracker. Expand
Towards real-time object tracking with deep Siamese network and layerwise aggregation
  • Lasheng Yu, Yongpeng Zhao, Xiaopeng Zheng
  • Computer Science
  • Signal Image Video Process.
  • 2021
TLDR
A new nonpadding residual unit is designed and used to stack a 22-layer deep ResNet, referred as ResNet22, and this is used to build a deep Siamese network, which can greatly enhance the tracking performance. Expand
Robust real-time visual object tracking via multi-scale fully convolutional Siamese networks
TLDR
A realtime tracker which is robust to occlusions and deformations based on a Region-based, Multi-Scale Fully Convolutional Siamese Network (R-MSFCN), which outperforms state-of-the-art approaches. Expand
Robust Real-Time Visual Object Tracking via Multi-Scale Fully Convolutional Siamese Networks
TLDR
A realtime tracker which is robust to occlusions and deformations based on a Region-based, Multi-Scale Fully Convolutional Siamese Network (R- MSFCN), which outperforms state-of-the-art approaches. Expand
Dice Loss in Siamese Network for Visual Object Tracking
TLDR
A new objective function to optimize during training based on the Dice coefficient is introduced, which can handle the strong imbalance between foreground and background patches and use random nonlinear transformations and histogram matching to increase the data. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 52 REFERENCES
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
Once for All: A Two-Flow Convolutional Neural Network for Visual Tracking
  • Kai Chen, Wenbing Tao
  • Computer Science
  • IEEE Transactions on Circuits and Systems for Video Technology
  • 2018
TLDR
This paper proposes to track different objects in an object-independent approach with a novel two-flow convolutional neural network (YCNN) trained to measure the similarity between the two image patches, which will not be limited to any specific object. 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
Siamese Instance Search for Tracking
TLDR
It turns out that the learned matching function is so powerful that a simple tracker built upon it, coined Siamese INstance search Tracker, SINT, suffices to reach state-of-the-art performance. 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
Transferring Rich Feature Hierarchies for Robust Visual Tracking
TLDR
This work pre-training a CNN offline and then transferring the rich feature hierarchies learned to online tracking, and proposes to generate a probability map instead of producing a simple class label to fit the characteristics of object tracking. Expand
First Step toward Model-Free, Anonymous Object Tracking with Recurrent Neural Networks
TLDR
This paper empirically shows that the proposed tracking approach works well in various scenarios by generating artificial video sequences with varying conditions; the number of objects, amount of noise and the match between the training shapes and test shapes. Expand
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
Visual tracking with online Multiple Instance Learning
TLDR
It is shown that using Multiple Instance Learning (MIL) instead of traditional supervised learning avoids these problems, and can therefore lead to a more robust tracker with fewer parameter tweaks. 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
...
1
2
3
4
5
...