Audio-Visual Feature Extraction for Semi-Automatic Annotation of Meetings.
Marián KépesiMichael NeffeTuan Van PhamMichael GrabnerHelmut GrabnerAndreas JuffingerPublished in: MMSP (2006)
Keyphrases
- audio visual
- automatic annotation
- visual information
- feature extraction
- multi modal
- image annotation
- visual data
- visual features
- content based retrieval
- image classification
- multimedia
- visual content
- semantic annotation
- principal component analysis
- feature space
- low level features
- low level
- eye movements
- image processing
- visual concepts
- feature vectors
- face recognition
- feature selection
- dimensionality reduction
- computer vision
- machine learning
- image collections
- data sets
- image features