FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos.
Yan WangYixuan SunYiwen HuangZhongying LiuShuyong GaoWei ZhangWeifeng GeWenqiang ZhangPublished in: CoRR (2022)
Keyphrases
- facial expression recognition
- video sequences
- facial expressions
- dynamic textures
- human computer interaction
- dynamic scenes
- moving camera
- facial expression analysis
- human actions
- expression recognition
- photo collections
- d scene
- human faces
- video images
- expression classification
- feature extraction
- video frames
- moving objects
- recognizing facial expressions
- local binary pattern
- video data
- face recognition
- camera motion
- three dimensional
- facial features
- space time
- facial actions
- facial images
- human activities
- visual data
- human motion
- face detection
- face images
- image retrieval
- image sequences