Self-taught learning of a deep invariant representation for visual tracking via temporal slowness principle

@article{Kuen2015SelftaughtLO,
  title={Self-taught learning of a deep invariant representation for visual tracking via temporal slowness principle},
  author={Jason Kuen and Kian Ming Lim and Chin Poo Lee},
  journal={Pattern Recognit.},
  year={2015},
  volume={48},
  pages={2964-2982}
}
Visual representation is crucial for visual tracking methodÂ?s performances. Conventionally, visual representations adopted in visual tracking rely on hand-crafted computer vision descriptors. These descriptors were developed generically without considering tracking-specific information. In this paper, we propose to learn complex-valued invariant representations from tracked sequential image patches, via strong temporal slowness constraint and stacked convolutional autoencoders. The deep slow… Expand
Learning temporally correlated representations using lstms for visual tracking
  • Qiaozhe Li, Xin Zhao, Kaiqi Huang
  • Computer Science
  • 2016 IEEE International Conference on Image Processing (ICIP)
  • 2016
TLDR
Experimental results not only show that the appearance and dynamic patterns of the objects can be characterized via temporally correlated feature learning, but also demonstrate that the proposed tracking algorithm performs favorably against the state-of-the-art methods. Expand
Deep mutual learning for visual object tracking
TLDR
Extensive experiments on the OTB2013, OTB2015, VOT2017 and LaSOT benchmarks demonstrate that the tracking performance can be improved effectively by using the proposed mutual-learning-based training methodology. 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
Network learns generic object tracking Neural Network Test : Frozen weights Current frame Network tracks novel objects ( no finetuning )
Machine learning techniques are often used in computer vision due to their ability to leverage large amounts of training data to improve performance. Unfortunately, most generic object trackers areExpand
Deep visual tracking: Review and experimental comparison
TLDR
The background of deep visual tracking is introduced, including the fundamental concepts of visual tracking and related deep learning algorithms, and the existing deep-learning-based trackers are categorize into three classes according to network structure, network function and network training. Expand
Visual tracking via ensemble autoencoder
TLDR
The authors present a novel online visual tracking algorithm via ensemble autoencoder (AE) based on the theory that the image resolution has an influence on vision procedures that performs favourably compared with some state-of-the-art methods. Expand
Robust visual tracking via combinative deep learning
TLDR
Different kinds of unlabelled datum are used to train network and initialize observation model, which uses the samples collected in the tracking to adjust dynamically so as to adapt to the target appearance and complex environment. Expand
Fast Compressive Tracking Parameters Optimization for Enhanced Visual Tracking
Visual tracking is a hot issue in computer vision with a wide range of applications such as intelligent video surveillance. Different types of state-ofthe-art methods such as self-expressive, sparseExpand
Deep Learning of Appearance Models for Online Object Tracking
TLDR
A deep learning based approach for vision based single target tracking by proposing a network architecture which takes the input video frames and directly computes the tracking score for any candidate target location by estimating the probability distributions of the positive and negative examples. Expand
Visual tracking by dynamic matching-classification network switching
TLDR
This work presents a novel real-time robust tracking method to take full use of the benefits from both kinds of networks, and proposes a matching-classification network switching (MCS) framework to integrate the matching, classification, verification networks and conduct dynamic switching among them. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 53 REFERENCES
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
Transferring Visual Prior for Online Object Tracking
TLDR
An algorithm that transfers visual prior learned offline for online object tracking from a collection of real-world images to an overcomplete dictionary to represent visual prior is proposed. Expand
Incremental Learning for Robust Visual Tracking
TLDR
A tracking method that incrementally learns a low-dimensional subspace representation, efficiently adapting online to changes in the appearance of the target, and includes a method for correctly updating the sample mean and a forgetting factor to ensure less modeling power is expended fitting older observations. Expand
Deep Learning of Invariant Features via Simulated Fixations in Video
TLDR
This work applies salient feature detection and tracking in videos to simulate fixations and smooth pursuit in human vision, and achieves state-of-the-art recognition accuracy 61% on STL-10 dataset. Expand
Real-time visual tracking via online weighted multiple instance learning
TLDR
The WMIL tracker integrates the sample importance into an efficient online learning procedure by assuming the most important sample is known when training the classifier, leading to a more robust and much faster tracker. Expand
Visual tracking via adaptive structural local sparse appearance model
TLDR
A simple yet robust tracking method based on the structural local sparse appearance model which exploits both partial information and spatial information of the target based on a novel alignment-pooling method and employs a template update strategy which combines incremental subspace learning and sparse representation. Expand
Real-Time Object Tracking Via Online Discriminative Feature Selection
TLDR
It is shown that integrating prior information of instance labels and the most correct positive instance into a supervised learning algorithm can handle visual drift more effectively and efficiently than the existing MIL tracker. 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 hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis
TLDR
This paper presents an extension of the Independent Subspace Analysis algorithm to learn invariant spatio-temporal features from unlabeled video data and discovered that this method performs surprisingly well when combined with deep learning techniques such as stacking and convolution to learn hierarchical representations. Expand
Real-Time Compressive Tracking
TLDR
A simple yet effective and efficient tracking algorithm with an appearance model based on features extracted from the multi-scale image feature space with data-independent basis that performs favorably against state-of-the-art algorithms on challenging sequences in terms of efficiency, accuracy and robustness. Expand
...
1
2
3
4
5
...