Who's Speaking?: Audio-Supervised Classification of Active Speakers in Video.
Punarjay ChakravartySayeh MirzaeiTinne TuytelaarsHugo Van hammePublished in: ICMI (2015)
Keyphrases
- supervised classification
- audio video
- multimedia
- scene change detection
- multimedia processing
- digital video
- supervised learning
- unsupervised clustering
- video sequences
- video content analysis
- multimedia information
- video streams
- unsupervised learning
- audio files
- visual data
- video data
- video content
- video files
- digital audio
- unsupervised classification
- supervised classifiers
- audio signals
- media streams
- lecture videos
- audio features
- audio stream
- speech recognition
- audio visual
- broadcast news
- video frames
- multimedia data
- land cover classification
- video analysis
- machine learning
- video clips
- video retrieval
- object recognition
- land cover
- audio content
- computer vision
- image segmentation
- training data
- data sets