Whether Contribution of Features Differ Between Video-Mediated and In-Person Meetings in Important Utterance Estimation.
Fumio NiheiRyo IshiiYukiko I. NakanoAtsushi FukayamaTakao NakamuraPublished in: ICASSP (2023)
Keyphrases
- key frames
- video clips
- multimedia
- video sequences
- co occurrence
- speech recognition
- feature extraction
- video images
- video content
- temporal information
- video frames
- video data
- feature vectors
- spatial and temporal
- multimedia data
- event detection
- parameter estimation
- feature set
- low level
- video analysis
- appearance features