Exploiting temporal information to detect conversational groups in videos and predict the next speaker.
Lucrezia TosatoVictor FortierIsabelle BlochCatherine PelachaudPublished in: Pattern Recognit. Lett. (2024)
Keyphrases
- temporal information
- video sequences
- video database
- temporal domain
- spatial and temporal information
- temporal data
- video clips
- temporal reasoning
- spatial information
- temporal events
- spatial temporal
- temporal dimension
- temporal patterns
- temporal relations
- temporal expressions
- video frames
- multi modal
- temporal constraints
- contextual information
- temporal knowledge
- temporal context
- visual information
- temporal queries
- automatic speech recognition
- video shots
- space time
- audio visual
- video content
- human activities
- temporal databases
- search engine