Temporal spotting of human actions from videos containing actor's unintentional motions.
Keita HaraKazuaki NakamuraNoboru BabaguchiPublished in: ICME (2015)
Keyphrases
- human actions
- human motion
- spatio temporal
- video sequences
- space time
- motion recognition
- action recognition
- space time interest points
- spatial temporal
- motion history images
- motion features
- recognition of human actions
- temporal sequences
- motion sequences
- image sequences
- temporal information
- human object interactions
- action classification
- motion capture data
- spatial and temporal
- motion patterns
- dynamic scenes
- human activities
- activity recognition
- motion trajectories
- view invariant
- motion capture
- moving objects
- motion primitives
- temporal domain
- human body
- recognizing actions
- action sequences
- body parts
- action detection
- action recognition in videos
- recognizing human actions
- computer vision
- video data
- visual features
- video frames
- image classification
- video shots
- dynamic textures
- d objects
- three dimensional