CV-C3D: Action Recognition on Compressed Videos with Convolutional 3D Networks.
Samuel Felipe dos SantosNicu SebeJurandy AlmeidaPublished in: SIBGRAPI (2019)
Keyphrases
- action recognition
- human actions
- action classification
- video dataset
- recognition of human actions
- recognizing human actions
- view invariant
- ucf sports
- bag of words
- human activities
- motion features
- spatio temporal interest points
- static images
- recognizing actions
- action detection
- space time interest points
- action recognition in videos
- spatial temporal
- computer vision
- mid level features
- human detection
- activity recognition
- body parts
- human object interactions
- bag of features
- motion history images
- human pose
- motion capture data
- multi view
- video clips
- video surveillance
- video content
- optical flow
- feature vectors
- video sequences