Unveiling the Power of Deep Tracking

@inproceedings{Bhat2018UnveilingTP,
  title={Unveiling the Power of Deep Tracking},
  author={Goutam Bhat and Joakim Johnander and Martin Danelljan and Fahad Shahbaz Khan and Michael Felsberg},
  booktitle={ECCV},
  year={2018}
}
In the field of generic object tracking numerous attempts have been made to exploit deep features. Despite all expectations, deep trackers are yet to reach an outstanding level of performance compared to methods solely based on handcrafted features. In this paper, we investigate this key issue and propose an approach to unlock the true potential of deep features for tracking. We systematically study the characteristics of both deep and shallow features, and their relation to tracking accuracy… 
Cascaded Correlation Refinement for Robust Deep Tracking
TLDR
A cascaded correlation refinement approach that cascades multiple stages of correlation refinement to progressively refine target localization so that the localized object could be used to learn an accurate on-the-fly model for improving the reliability of model update.
Release the Power of Online-Training for Robust Visual Tracking
TLDR
This paper proposes to improve the tracking accuracy via online training by squeezing redundant training data by analyzing the dataset distribution in low-level feature space and design statistic-based losses to increase the inter-class distance while decreasing the intra-class variance of high-level semantic features.
Hybrid Cascade Filter With Complementary Features for Visual Tracking
TLDR
This letter proposes a hybrid cascade filter to fuse handcrafted and deep features for exploiting their strengths, and complements the deep representation with handcrafted features to achieve better localization accuracy, as well as build a hybrids cascade structure using multiple observation models to achievebetter robustness.
Residual Attention SiameseRPN for Visual Tracking
TLDR
This work proposes a residual attention SiameseRPN visual tracking method for accurate object state estimation, which introduces the correlation filter in aSiamese network framework and a novel loss function is presented to enhance the discriminative capability.
Advances in Deep Learning Methods for Visual Tracking: Literature Review and Fundamentals
TLDR
This paper provides a comprehensive review of state-of-the-art single-object tracking algorithms based on deep learning, and introduces basic knowledge of deep visual tracking, including fundamental concepts, existing algorithms, and previous reviews.
SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks
TLDR
This work proves the core reason Siamese trackers still have accuracy gap comes from the lack of strict translation invariance, and proposes a new model architecture to perform depth-wise and layer-wise aggregations, which not only improves the accuracy but also reduces the model size.
Robust Visual Object Tracking with Two-Stream Residual Convolutional Networks
TLDR
Inspired by the human “visual tracking” capability which leverages motion cues to distinguish the target from the background, a Two-Stream Residual Convolutional Network (TS-RCN) for visual tracking is proposed, which successfully exploits both appearance and motion features for model update.
Robust Deep Tracking with Two-step Augmentation Discriminative Correlation Filters
TLDR
A two-step augmentation discriminative correlation filters (TADCF) approach to improve robustness and generalization of the learned model and performs favorably against state-of-the-art trackers.
TLPG-Tracker: Joint Learning of Target Localization and Proposal Generation for Visual Tracking
TLDR
This paper proposes an efficient two-stage architecture which makes full use of the complementarity of two subtasks to achieve robust localization and high-quality proposals generation of the target jointly.
ATOM: Accurate Tracking by Overlap Maximization
TLDR
This work proposes a novel tracking architecture, consisting of dedicated target estimation and classification components, and introduces a classification component that is trained online to guarantee high discriminative power in the presence of distractors.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 47 REFERENCES
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.
Deep-LK for Efficient Adaptive Object Tracking
TLDR
It is demonstrated that there is a theoretical relationship between Siamese regression networks like GOTURN and the classical Inverse Compositional Lucas & Kanade (IC-K) algorithm, and a novel framework for object tracking inspired by the IC-LK framework is proposed, which is referred to as Deep-K.
Discriminative Scale Space Tracking
TLDR
This paper proposes a novel scale adaptive tracking approach by learning separate discriminative correlation filters for translation and scale estimation in a tracking-by-detection framework that obtains the top rank in performance by outperforming 19 state-of-the-art trackers on OTB and 37 state of theart tracker on VOT2014.
End-to-End Flow Correlation Tracking with Spatial-Temporal Attention
TLDR
The FlowTrack is proposed, which focuses on making use of the rich flow information in consecutive frames to improve the feature representation and the tracking accuracy and is the first work to jointly train flow and tracking task in deep learning framework.
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.
Learning Background-Aware Correlation Filters for Visual Tracking
TLDR
This work proposes a Background-Aware CF based on hand-crafted features (HOG] that can efficiently model how both the foreground and background of the object varies over time, and superior accuracy and real-time performance of the method compared to the state-of-the-art trackers.
ECO: Efficient Convolution Operators for Tracking
TLDR
This work revisit the core DCF formulation and introduces a factorized convolution operator, which drastically reduces the number of parameters in the model, and a compact generative model of the training sample distribution that significantly reduces memory and time complexity, while providing better diversity of samples.
Hedged Deep Tracking
TLDR
A novel CNN based tracking framework is proposed, which takes full advantage of features from different CNN layers and uses an adaptive Hedge method to hedge several CNN based trackers into a single stronger one.
Staple: Complementary Learners for Real-Time Tracking
TLDR
It is shown that a simple tracker combining complementary cues in a ridge regression framework can operate faster than 80 FPS and outperform not only all entries in the popular VOT14 competition, but also recent and far more sophisticated trackers according to multiple benchmarks.
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.
...
1
2
3
4
5
...