Slow-Fast Auditory Streams For Audio Recognition.
Evangelos KazakosArsha NagraniAndrew ZissermanDima DamenPublished in: CoRR (2021)
Keyphrases
- visual information
- signal processing
- environmental sounds
- recognition rate
- cross modal
- audio stream
- recognition accuracy
- data streams
- object recognition
- pattern recognition
- video files
- visual speech
- feature extraction
- multi stream
- information processing
- real time
- handwritten characters
- automatic transcription
- multimedia
- computer vision
- recognition algorithm
- visual recognition
- recognition process
- activity recognition
- visual features
- character recognition
- automatic recognition
- emotion recognition
- transactional data
- multi modal
- audio video
- image classification
- feature vectors
- data sets