Audio-visual atoms for generic video concept classification.
Wei JiangCourtenay V. CottonShih-Fu ChangDan EllisAlexander C. LouiPublished in: ACM Trans. Multim. Comput. Commun. Appl. (2010)
Keyphrases
- audio visual
- visual data
- video summarization
- multimedia
- multi modal
- meeting room
- multi stream
- pattern recognition
- visual information
- audio visual content
- audio features
- image classification
- machine learning
- temporal context
- text classification
- audio visual speech recognition
- video sequences
- emotion recognition
- feature vectors
- feature selection
- video data
- video streams
- sports video
- feature extraction
- space time
- high level
- multimodal fusion
- video frames
- video content
- training set
- feature space
- person authentication
- dimensionality reduction