Keyphrases
- audio visual
- weakly supervised
- visual data
- multimedia
- multi modal
- video data
- relation extraction
- visual information
- object class
- video sequences
- superpixels
- topic models
- semi supervised
- object detectors
- natural language processing
- named entities
- video frames
- multimedia data
- object detection
- information extraction
- natural language
- multiscale
- key frames
- high dimensional
- object recognition