QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation.
Sicheng YangZhiyong WuMinglei LiZhensong ZhangLei HaoWeihong BaoHaolin ZhuangPublished in: CoRR (2023)
Keyphrases
- multimodal interfaces
- hand gestures
- hand motion
- image sequences
- feature points
- motion analysis
- optical flow
- hand movements
- body movements
- speech recognition
- matching algorithm
- human motion
- gesture recognition
- space time
- motion patterns
- motion model
- human movement
- matching process
- fourier domain
- image matching
- motion field
- quantization error
- computer vision
- multi stream
- hidden markov models
- motion estimation
- speech signal
- camera motion
- audio visual
- multi view
- human computer interaction
- human hand
- spatio temporal
- keypoints