SpotFormer: Multi-Scale Spatio-Temporal Transformer for Facial Expression Spotting.
Yicheng DengHideaki HayashiHajime NagaharaPublished in: CoRR (2024)
Keyphrases
- facial expressions
- spatio temporal
- multiscale
- facial expression recognition
- video sequences
- expression recognition
- human faces
- face recognition
- spatial and temporal
- facial images
- face images
- facial features
- space time
- moving objects
- local binary pattern
- facial expression analysis
- image sequences
- automatic facial expression recognition
- image processing
- scale space
- human actions
- cohn kanade
- person independent
- motion patterns
- wavelet transform
- face model
- recognition of facial expressions
- facial gestures
- human computer interaction
- emotion recognition
- head motion
- three dimensional
- facial animation
- facial actions
- image segmentation
- facial action units