Attempting to Aggregate Perceptual Constructs From Deep Neural Networks for Video and Audio Interaction Representation.
Marc-Antoine MaheuxGuillaume AuclairPhilippe WarrenDominic LétourneauFrançois MichaudPublished in: RO-MAN (2023)
Keyphrases
- neural network
- multimedia
- audio video
- scene change detection
- digital video
- temporal structure
- video sequences
- audio features
- real time
- audio signals
- pattern recognition
- visual data
- video frames
- multimedia processing
- video streams
- human visual system
- video analysis
- human computer interaction
- audio stream
- multimedia information
- video signals
- fuzzy logic
- media streams
- perceptual information
- video content analysis
- closed captions
- video database
- sensory inputs
- perceptual quality
- video retrieval
- neural network model
- video content
- back propagation
- video data
- signal processing
- low level
- artificial neural networks