Deep trajectory representation-based clustering for motion pattern extraction in videos.
Jonathan BoyleTahir NawazJames M. FerrymanPublished in: AVSS (2017)
Keyphrases
- pattern extraction
- temporal structure
- recognition of human actions
- recognizing human actions
- video representation
- configuration space
- action recognition
- motion trajectories
- video sequences
- temporal segmentation
- post processing
- human actions
- human motion
- motion primitives
- data pre processing
- space time
- action recognition in videos
- human activities
- spatio temporal
- motion analysis
- pattern discovery
- video data
- dynamic scenes
- key frames
- temporal relations
- video content
- text mining
- motion estimation
- moving objects
- dynamic textures
- motion model
- video scene
- camera motion
- image sequences
- spatial relations