Self-supervised object detection from audio-visual correspondence.
Triantafyllos AfourasYuki M. AsanoFrancois FaganAndrea VedaldiFlorian MetzePublished in: CVPR (2022)
Keyphrases
- visual correspondence
- object detection
- multimedia
- mutual information
- multi class
- computer vision
- object classification
- audio visual
- face detection
- background subtraction
- object recognition
- scene understanding
- object class
- pedestrian detection
- audio video
- object segmentation
- audio signals
- object categories
- machine learning
- audio features
- deformable part models
- music score
- cepstral features
- audio signal
- multimedia information
- human detection
- scene recognition
- signal processing
- pattern recognition
- audio stream
- pairwise
- emotion recognition
- broadcast news
- object detectors
- audio files
- image parsing
- digital audio
- face recognition
- image processing