Weakly-supervised Audio-visual Sound Source Detection and Separation.
Tanzila RahmanLeonid SigalPublished in: CoRR (2021)
Keyphrases
- sound source
- audio visual
- weakly supervised
- multi modal
- object detectors
- visual information
- multimedia
- visual data
- object detection
- topic models
- semi supervised
- image processing
- image classification
- named entities
- speech signal
- information retrieval
- machine learning
- bounding box
- low level
- pattern recognition
- feature extraction
- real environment