Spatio-temporal Video Autoencoder for Human Action Recognition.
Anderson Carlos Sousa e SantosHélio PedriniPublished in: VISIGRAPP (5: VISAPP) (2019)
Keyphrases
- human actions
- spatio temporal
- action recognition
- spatial and temporal
- space time
- video representation
- spatial temporal
- video sequences
- video frames
- video data
- spatio temporally
- video database
- temporal structure
- temporal domain
- video content
- human activities
- video analysis
- activity recognition
- video shots
- video segmentation
- video streams
- real time
- dynamic textures
- image sequences
- dynamic scenes
- human motion
- key frames
- temporal information
- moving objects
- multimedia
- learning algorithm
- video clips
- video surveillance
- visual features
- digital video
- artificial neural networks
- video processing
- three dimensional
- temporal segmentation
- real time video
- online video
- temporal filtering