Many-to-Many Audio Spectrogram Tansformer: Transformer for Sound Event Localization and Detection.
Sooyoung ParkYoungho JeongTaejin LeePublished in: DCASE (2021)
Keyphrases
- soccer video
- event detection
- multimedia
- accurate localization
- object detection
- detection accuracy
- detection method
- false alarms
- activity detection
- automatic detection
- false positives
- detection algorithm
- signal processing
- detection rate
- visual data
- fuzzy logic
- audio visual
- multimedia information
- audio signal
- video recordings
- abnormal behavior
- image sequences