Towards textually describing complex video contents with audio-visual concept classifiers.
Chun Chet TanYu-Gang JiangChong-Wah NgoPublished in: ACM Multimedia (2011)
Keyphrases
- video content
- visual concepts
- classifier training
- video data
- multimedia
- training data
- video sequences
- image classification
- inter related
- visual information
- feature selection
- image annotation
- video streams
- machine learning algorithms
- training set
- support vector
- decision trees
- higher level
- multi modal
- video frames
- multi class
- training examples
- visual data
- feature extraction
- machine learning