Scale Invariant Action Recognition Using Compound Features Mined from Dense Spatio-temporal Corners.
Andrew GilbertJohn IllingworthRichard BowdenPublished in: ECCV (1) (2008)
Keyphrases
- scale invariant
- spatio temporal
- keypoints
- object class recognition
- scale space
- feature detectors
- scale invariant features
- invariant features
- translation and scale invariant
- image features
- feature vectors
- natural images
- feature extraction
- feature transformation
- image sequences
- scale invariance
- feature detection
- affine invariant
- human actions
- multiscale
- texture images
- shape features
- classification accuracy
- machine learning