MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets.
Sungjoo HaMartin KersnerBeomsu KimSeokjun SeoDongyoung KimPublished in: CoRR (2019)
Keyphrases
- video sequences
- video shots
- training set
- face images
- previously unseen
- human faces
- target recognition
- facial expressions
- facial images
- visual features
- neural network
- recognition algorithm
- key frames
- training examples
- shot boundary detection
- image details
- object tracking
- video data
- access control
- color images
- image sequences
- multimedia