Multi-label video categorization using visual and audio transcript features.
Jingmin ZhouAdam GaribaVida MovahediMariah Martin SheinAndre RosaRuiqi YuPublished in: CASCON (2021)
Keyphrases
- multi label
- text categorization
- multimedia
- visual data
- visual information
- class labels
- low level
- multi label classification
- audio features
- multi label learning
- image classification
- feature vectors
- visual concepts
- binary classification
- text classification
- feature selection
- image annotation
- video data
- graph cuts
- video sequences
- key frames
- image features
- automatic image annotation
- feature extraction
- visual speech
- training examples
- unsupervised learning
- feature set
- nearest neighbor
- data points
- classification accuracy
- training data
- multiple labels
- protein function prediction