Multi-level Attention network using text, audio and video for Depression Prediction.
Anupama RaySiddharth KumarRutvik ReddyPrerana MukherjeeRitu GargPublished in: CoRR (2019)
Keyphrases
- multimedia
- audio content
- audio video
- video content analysis
- prediction accuracy
- multimedia processing
- information retrieval
- closed captions
- text graphics
- visual data
- radial basis function network
- text detection
- audio signals
- natural language descriptions
- video content
- content based video retrieval
- prediction model
- video data
- real time
- audio files
- digital audio
- audio stream
- scene change detection
- video search
- digital video
- event detection
- network structure
- text mining
- multimedia information
- online video
- video analysis
- video clips
- video material
- visual information
- story segmentation
- video sequences
- metadata
- media streams
- keywords
- peer to peer
- semantic information
- multimedia data
- text to speech
- lecture videos