FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos.
Yan WangYixuan SunYiwen HuangZhongying LiuShuyong GaoWei ZhangWeifeng GeWenqiang ZhangPublished in: CVPR (2022)
Keyphrases
- facial expression recognition
- dynamic textures
- video sequences
- facial expressions
- expression recognition
- dynamic scenes
- human actions
- human computer interaction
- facial expression analysis
- photo collections
- human faces
- moving camera
- visual data
- video data
- local binary pattern
- d scene
- feature extraction
- moving objects
- video frames
- facial features
- face recognition
- video images
- expression classification
- recognizing facial expressions
- video surveillance
- facial images
- action recognition
- space time
- face images
- object tracking
- multi view
- depth images
- scene structure
- input image
- optical flow
- multiscale
- image sequences
- three dimensional