Support vector tracking
IEEE Transactions on Pattern Analysis and Machine IntelligencePublished 21 June 2004
Shai Avidan
Citations1,048
SJR quartileQ1
SJR score3.91
SNIP5.99
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Support Vector Tracking integrates the Support Vector Machine (SVM) classifier into an optic-flow-based tracker and maximizes the SVM classification score to account for large motions between successive frames.
Abstract
Support Vector Tracking (SVT) integrates the Support Vector Machine (SVM) classifier into an optic-flow-based tracker. Instead of minimizing an intensity difference function between successive frames, SVT maximizes the SVM classification score. To account for large motions between successive frames, we build pyramids from the support vectors and use a coarse-to-fine approach in the classification stage. We show results of using SVT for vehicle tracking in image sequences.
Keywords
Computer Science
Machine LearningSupport-vector networks
40,463 Citations1995Corinna Cortes, Vladimir Vapnik
High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated and the performance of the support- vector network is compared to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
The Nature of Statistical Learning Theory
39,279 Citations1995Vladimir Vapnik
Machine LearningSupport-Vector Networks
33,035 Citations1995Corinna Cortes, Vladimir Vapnik
High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated and the performance of the support- vector network is compared to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
Rapid object detection using a boosted cascade of simple features
18,097 Citations2005Paul Viola, Michael Jones
A machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates and the introduction of a new image representation called the "integral image" which allows the features used by the detector to be computed very quickly.
Data Mining and Knowledge DiscoveryA Tutorial on Support Vector Machines for Pattern Recognition
16,433 Citations1998Christopher J. C. Burges
There are several arguments which support the observed high accuracy of SVMs, which are reviewed and numerous examples and proofs of most of the key theorems are given.
Transductive Inference for Text Classification using Support Vector Machines
2,717 Citations1999Thorsten Joachims
An analysis of why TSVMs are well suited for text classi(cid:12)cation is presented, and an algorithm for training TSVMs e(cid:14)-ciently, handling 10,000 examples and more is proposed.
Training support vector machines: an application to face detection
2,496 Citations2002E. Osuna, Robert M. Freund +1 more
A decomposition algorithm that guarantees global optimality, and can be used to train SVM's over very large data sets is presented, and the feasibility of the approach on a face detection problem that involves a data set of 50,000 data points is demonstrated.
IEEE Transactions on Pattern Analysis and Machine IntelligenceExample-based learning for view-based human face detection
1,769 Citations1998Kah Kay Sung, Tomaso Poggio
An example-based learning approach for locating vertical frontal views of human faces in complex scenes and shows empirically that the distance metric adopted for computing difference feature vectors, and the "nonface" clusters included in the distribution-based model, are both critical for the success of the system.
International Journal of Computer VisionA Trainable System for Object Detection
1,282 Citations2000Constantine Papageorgiou, Tomaso Poggio
Lecture notes in computer scienceHierarchical model-based motion estimation
1,155 Citations1992James R. Bergen, P. Anandan +2 more
This paper describes a hierarchical estimation framework for the computation of diverse representations of motion information that constrains the overall structure of the motion estimated, a local model that is used in the estimation process, and a coarse-fine refinement strategy.
International Journal of Computer VisionEigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation
1,032 Citations1998Michael J. Black, Allan D. Jepson
A “subspace constancy assumption” is defined that allows techniques for parameterized optical flow estimation to simultaneously solve for the view of an object and the affine transformation between the eigenspace and the image.
Comparison of classifier methods: a case study in handwritten digit recognition
620 Citations2002Léon Bottou, Corinna Cortes +9 more
This paper compares the performance of several classifier algorithms on a standard database of handwritten digits by considering not only raw accuracy, but also training time, recognition time, and memory requirements.
Neural Information Processing SystemsEfficient Pattern Recognition Using a New Transformation Distance
464 Citations1992Patrice Simard, Yann LeCun +1 more
A new distance measure which can be made locally invariant to any set of transformations of the input and can be computed efficiently is proposed.
International Conference on Machine LearningSimplified support vector decision rules
429 Citations1996Christopher J. C. Burges
The results show that the method can decrease the computational complexity of the decision rule by a factor of ten with no loss in generalization perfor mance making the SVM test speed com petitive with that of other methods.
Lecture notes in computer scienceEigenTracking: Robust matching and tracking of articulated objects using a view-based representation
413 Citations1996Michael J. Black, Allan D. Jepson
Lecture notes in computer scienceStatistical Learning of Multi-view Face Detection
400 Citations2002Stan Z. Li, Long Zhu +4 more
FloatBoost incorporates the idea of Floating Search into AdaBoost to solve the non-monotonicity problem encountered in the sequential search of AdaBoost and leads to the first real-time multi-view face detection system in the world.
Econstor (Econstor)Combining statistical learning with a knowledge-based approach: A case study in intensive care monitoring
354 Citations1999Katharina Morik, Peter Brockhausen +1 more
Prior Knowledge in Support Vector Kernels
293 Citations1997Bernhard Schölkopf, Patrice Simard +2 more
It is shown that both invariances under group transformations and prior knowledge about locality in images can be incorporated by constructing appropriate kernel functions by exploring methods for incorporating prior knowledge in Support Vector learning machines.
Example Based Learning for View-Based Human Face Detection.
268 Citations1994Kah Kay Sung, Tomaso Poggio
IEEE Transactions on Pattern Analysis and Machine IntelligenceASSET-2: real-time motion segmentation and shape tracking
267 Citations1995Stephen M. Smith, J. Michael Brady
Hierarchical Model-Based Motion Estimation
185 Citations1993P. Anandan, James R. Bergen +2 more
Computationally efficient face detection
183 Citations2002Sami Romdhani, Philip H. S. Torr +2 more
A method of speeding up the non-linear support vector machine by considering the RV's sequentially, and if at any point a face is deemed too unlikely to cease the sequential evaluation, obviating the need to evaluate the remaining RVs.
Categorization by Learning and Combining Object Parts
120 Citations2001Bernd Heisele, T. Serre +3 more
An algorithm for automatically learning discriminative components of objects with SVM classifiers based on growing image parts by minimizing theoretical bounds on the error probability of an SVM, which suggests performance at significantly better level than other face detection systems.
Workshops in computingTracking and Recognition of Face Sequences
31 Citations1995Shaogang Gong, Αλεξάνδρα Ψαρρού +2 more
This work detects and track a moving head before segmenting face images from on-line camera inputs and measures temporal changes in the pattern vectors of eigenface projections of successive image frames of a face sequence and introduces the concept of “temporal signature” of aFace class.
Multiresolution Tangent Distance for Affine-invariant Classification
26 Citations1997Nuno Vasconcelos, Andrew Lippman
This work analyzes an invariant metric that has performed well for face or character recognition and studies its limitations when applied to regular images, showing that the most significant among these (convergence to local minima) can be drastically reduced by computing the distance in a multiresolution setting.