Exploiting the Circulant Structure of Tracking-by-Detection with Kernels
Explore this paper's citation graph
Summary
Using the well-established theory of Circulant matrices, this work provides a link to Fourier analysis that opens up the possibility of extremely fast learning and detection with the Fast Fourier Transform, which can be done in the dual space of kernel machines as fast as with linear classifiers.
- Published
- 2012-10-07
- Cited by
- 2,360
- References
- 26
- Access
- Open access
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:14017201
References
- Distortion-invariant kernel correlation filters for general object recognition
- Visual object tracking using adaptive correlation filters
- Fast FFT-based distortion-invariant kernel filters for general object recognition
- Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
- Object tracking: A survey
- Recent advances and trends in visual tracking: A review
- Struck: Structured output tracking with kernels
- Exploiting spatial overlap to efficiently compute appearance distances between image windows
- Robust Object Tracking with Online Multiple Instance Learning
- Beyond sliding windows: Object localization by efficient subwindow search
- Average of Synthetic Exact Filters
- Robust Fragments-based Tracking using the Integral Histogram
- Globally optimal solution to multi-object tracking with merged measurements
- Incremental Learning for Robust Visual Tracking
- On-line Random Forests
- Support vector tracking
- Toeplitz And Circulant Matrices: A Review (Foundations and Trends(R) in Communications and Information Theory)
- Multiple kernels for object detection
- Toeplitz and Circulant Matrices: A Review
- SVM vs regularized least squares classification
Cited by
- NUS-PRO: A New Visual Tracking Challenge
- A computer-aided training (CAT) system for short track speed skating
- Ensemble-Based Tracking: Aggregating Crowdsourced Structured Time Series Data
- Object Tracking Algorithm Based on Dual Color Feature Fusion with Dimension Reduction
- Robust visual tracking via online multiple instance learning with Fisher information
- Visual Tracking via Random Walks on Graph Model
- Visual tracking using multi-channel correlation filters
- Robust Visual Tracking via Sparsity-Induced Subspace Learning
- Unsupervised and semi-supervised methods for human action analysis
- Tensor pooling for online visual tracking
- A rotation adaptive correlation filter for robust tracking
- Multi-invariance appearance model for object tracking
- Missile vision guidance based-on adaptive image filtering
- Visual Tracking Based on the Adaptive Color Attention Tuned Sparse Generative Object Model
- Fast and Robust Object Tracking via Probability Continuous Outlier Model
- Weighted Part Context Learning for Visual Tracking
- Tracking Randomly Moving Objects on Edge Box Proposals
- Fast Tracking via Spatio-Temporal Context Learning
- Color name TLD1
- Real-time tracking-by-learning with high-order regularization fusion for big video abstraction
Related papers
No related papers recorded.