SPECTRE: Visual Speech-Informed Perceptual 3D Facial Expression Reconstruction from Videos.
Panagiotis Paraskevas FilntisisGeorge RetsinasFoivos Paraperas PapantoniouAthanasios KatsamanisAnastasios RoussosPetros MaragosPublished in: CVPR Workshops (2023)
Keyphrases
- facial expressions
- video sequences
- facial expression recognition
- visual speech
- facial actions
- face images
- human faces
- video signals
- face recognition
- facial images
- expression recognition
- facial features
- video frames
- video content
- three dimensional
- video data
- space time
- head movements
- human visual system
- hidden markov models
- dynamic textures
- feature selection
- human actions
- computer vision
- frame rate
- moving camera
- key frames
- emotion recognition
- human activities
- motion estimation
- head motion
- high resolution
- image processing