Audio-guided Video Interpolation via Human Pose Features.
Takayuki NakatsukaMasatoshi HamanakaShigeo MorishimaPublished in: VISIGRAPP (5: VISAPP) (2020)
Keyphrases
- multimedia
- static images
- human pose
- audio features
- video clips
- space time
- feature extraction
- low level
- action detection
- action recognition
- video data
- pose estimation
- human body
- feature set
- feature space
- benchmark datasets
- high resolution
- stereo matching
- prior knowledge
- body parts
- feature vectors
- spatio temporal
- video sequences