Sparse representation with temporal max-smoothing for acoustic event detection.
Xugang LuPeng ShenYu TsaoChiori HoriHisashi KawaiPublished in: INTERSPEECH (2015)
Keyphrases
- event detection
- sparse representation
- composite events
- dictionary learning
- sparse coding
- temporal segmentation
- event recognition
- face recognition
- video event detection
- image patches
- video surveillance
- image classification
- activity recognition
- spatio temporal
- signal processing
- text streams
- high dimensional data
- compressive sensing
- image representation
- temporal databases
- object tracking
- sparse coefficients
- test images
- sports video
- dimensionality reduction
- space time
- text mining
- image data
- multiscale