Leveraging Self-Supervised Training for Unintentional Action Recognition.
Enea DukaAnna KuklevaBernt SchielePublished in: ECCV Workshops (4) (2022)
Keyphrases
- action recognition
- bag of words
- human detection
- human actions
- activity recognition
- computer vision
- action classification
- spatial temporal
- recognition of human actions
- recognizing human actions
- bag of features
- video dataset
- action primitives
- independent subspace analysis
- body parts
- training examples
- recognizing actions
- training set
- view invariant action recognition
- depth sensors
- view invariant
- depth cameras
- mid level
- feature vectors