• Publications
  • Influence
Tracking-Learning-Detection
  • Zdenek Kalal
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine…
  • 1 July 2012
TLDR
We propose a novel tracking framework (TLD) that explicitly decomposes the long-term tracking task into tracking, learning, and detection. Expand
  • 2,486
  • 324
  • PDF
P-N learning: Bootstrapping binary classifiers by structural constraints
TLDR
This paper shows that the performance of a binary classifier can be significantly improved by the processing of structured unlabeled data, i.e. data are structured if knowing the label of one example restricts the labeling of others. Expand
  • 1,131
  • 181
  • PDF
Forward-Backward Error: Automatic Detection of Tracking Failures
TLDR
This paper proposes a novel method for tracking failure detection. Expand
  • 649
  • 75
  • PDF
Online learning of robust object detectors during unstable tracking
TLDR
We propose a new approach, called Tracking-Modeling-Detection (TMD) that closely integrates adaptive tracking with online learning of the object-specific detector. Expand
  • 223
  • 21
  • PDF
Face-TLD: Tracking-Learning-Detection applied to faces
TLDR
A novel system for long-term tracking of a human face in unconstrained videos is built on Tracking-Learning-Detection (TLD) approach. Expand
  • 176
  • 18
  • PDF
Weighted Sampling for Large-Scale Boosting
TLDR
We design a new general sampling strategy ”quasi-random weighted sampling + trimming” (QWS+) that includes well established strategies as special cases. Expand
  • 91
  • 3
  • PDF
Face detection with Waldboost algorithm
Face detection algorithms based on the work of Viola and Jones [11] train the classifier by processing training examples of face and non-face patterns. A general effort is to process a large numberExpand
  • 3
  • PDF