Slow-Fast Auditory Streams for Audio Recognition.
Evangelos KazakosArsha NagraniAndrew ZissermanDima DamenPublished in: ICASSP (2021)
Keyphrases
- signal processing
- cross modal
- visual information
- environmental sounds
- object recognition
- recognition rate
- recognition accuracy
- visual recognition
- automatic recognition
- feature extraction
- multi stream
- visual speech
- image recognition
- recognition algorithm
- audio stream
- multimedia
- real time
- video files
- pattern recognition
- recognition process
- visual data
- information processing
- multi modal
- data streams
- stream processing
- music information retrieval
- audio visual
- action recognition
- media streams
- automatic transcription