Boosting-based transfer learning for multi-view head-pose classification from surveillance videos.
Radu L. VieriuAnoop Kolar RajagopalSubramanian RamanathanOswald LanzElisa RicciNicu SebeKalpathi RamakrishnanPublished in: EUSIPCO (2012)
Keyphrases
- multi view
- transfer learning
- multi view learning
- co training
- d objects
- surveillance videos
- single view
- multiple views
- text classification
- labeled data
- machine learning
- semi supervised
- semi supervised learning
- machine learning algorithms
- learning algorithm
- unlabeled data
- camera calibration
- feature selection
- multiple cameras
- learning tasks
- three dimensional
- supervised learning
- dynamic scenes
- multi camera
- pose estimation
- support vector
- reinforcement learning
- feature extraction
- video data
- active learning
- labeled and unlabeled data
- real time
- decision trees
- class labels
- pairwise
- viewpoint
- multi task learning
- support vector machine
- data mining
- data sets
- multi task
- event detection
- object tracking
- text categorization
- feature vectors
- feature space
- object recognition