Conditional Video Generation Using Action-Appearance Captions.
Shohei YamamotoAntonio Tejero-de-PablosYoshitaka UshikuTatsuya HaradaPublished in: CoRR (2018)
Keyphrases
- video content
- human actions
- action classification
- action recognition
- video streams
- video sequences
- visual features
- object motion
- video database
- video data
- action detection
- appearance features
- temporal information
- news video
- multimedia
- space time
- static images
- dynamic textures
- recognizing human actions
- video analysis
- key frames
- appearance model
- video frames
- video surveillance
- dynamic scenes
- video shots
- image search
- video clips
- video images
- spatial and temporal
- spatio temporal