A deep multimodal network based on bottleneck layer features fusion for action recognition.
Tej SinghDinesh Kumar VishwakarmaPublished in: Multim. Tools Appl. (2021)
Keyphrases
- action recognition
- human actions
- bag of features
- static images
- bag of words
- human detection
- feature extraction
- feature vectors
- mid level
- spatial temporal
- computer vision
- action classification
- activity recognition
- view invariant
- deformable part models
- human movements
- recognizing actions
- recognition of human actions
- action recognition in videos
- view invariant action recognition
- motion features
- feature space
- video clips
- key frames
- depth sensors
- human activities
- multiple views
- low level
- three dimensional