Shuffle Transformer with Feature Alignment for Video Face Parsing.
Rui ZhangYang HanZilong HuangPei ChengGuozhong LuoGang YuBin FuPublished in: CoRR (2021)
Keyphrases
- video data
- video frames
- video content
- video streams
- multimedia
- closed captions
- face detection and tracking
- face images
- video sequences
- video analysis
- facial expressions
- natural language processing
- image features
- real time
- video clips
- face alignment
- word alignment
- multimedia data
- neural network
- fuzzy logic
- feature vectors
- human faces
- power system
- feature set
- event recognition
- video dataset
- natural language
- combining information from multiple
- fault diagnosis
- space time