Audio-visual grouplet: temporal audio-visual interactions for general video concept classification.
Wei JiangAlexander C. LouiPublished in: ACM Multimedia (2011)
Keyphrases
- audio visual
- temporal segmentation
- temporal context
- visual data
- video summarization
- multi modal
- meeting room
- multimedia
- audio visual content
- visual information
- sports video
- multi stream
- audio features
- multimodal fusion
- pattern recognition
- temporal information
- joint optimization
- audio visual speech recognition
- spatial and temporal
- space time
- multimedia data
- image classification
- video sequences
- machine learning
- video data
- video streams
- contextual information
- feature vectors
- feature selection
- text classification
- image data
- feature extraction