Deep Learning Pipeline for Spotting Macro- and Micro-expressions in Long Video Sequences Based on Action Units and Optical Flow.
Bo YangJianming WuKazushi IkedaGen HattoriMasaru SuganoYusuke IwasawaYutaka MatsuoPublished in: Pattern Recognit. Lett. (2023)
Keyphrases
- deep learning
- action units
- optical flow
- long video sequences
- image sequences
- facial expressions
- video sequences
- video frames
- dynamic scenes
- facial actions
- d scene
- motion segmentation
- moving objects
- particle filter
- unsupervised learning
- machine learning
- motion model
- human activities
- motion estimation
- camera motion
- flow field
- background subtraction
- facial features
- computer vision
- spatio temporal
- human faces
- object tracking
- face recognition
- structure from motion
- video data
- feature points
- face images
- three dimensional
- maximum likelihood
- d objects