Multimodal object recognition from visual and audio sequences.
Weipeng HeHaojun GuanJianwei ZhangPublished in: MFI (2015)
Keyphrases
- object recognition
- cross modal
- visual information
- multimodal information
- audio visual
- visual data
- multimedia
- multi modal
- visual speech
- visual recognition
- hidden markov models
- selective attention
- computer vision
- biologically motivated
- multimodal fusion
- single modality
- visual processing
- visual learning
- low level
- object detection
- visual features
- natural images
- category level
- d objects
- image understanding
- image representation
- video indexing and retrieval
- multimodal interaction
- image features
- multi stream
- video data
- visual cues
- relevance feedback
- semantic context
- audio video
- visual scene
- audio features
- signal processing
- polyphonic music
- cognitive vision
- multimedia databases
- image retrieval