Audio-driven Neural Gesture Reenactment with Video Motion Graphs.
Yang ZhouJimei YangDingzeyu LiJun SaitoDeepali AnejaEvangelos KalogerakisPublished in: CoRR (2022)
Keyphrases
- visual data
- space time
- multimedia
- video signals
- audio video
- scene change detection
- spatial and temporal
- key frames
- multimedia processing
- video scene
- object motion
- input video
- video recordings
- video data
- video sequences
- temporal filtering
- video content analysis
- hand gestures
- visual information
- image sequences
- visual cues
- motion features
- video analysis
- static images
- digital video
- motion history images
- moving camera
- gesture recognition
- digital audio
- broadcast news
- human motion
- audio files
- camera motion
- mouth region
- dynamic scenes
- motion estimation
- video summarization
- motion patterns
- audio signals
- network architecture
- audio visual
- optical flow
- visual input
- neural network
- motion capture data
- temporal continuity
- action recognition
- motion model
- moving objects
- motion analysis
- temporal segmentation
- spatio temporal
- video files
- audio stream
- video frames
- video streams
- hand motion
- multimedia data
- video surveillance
- surveillance videos
- motion trajectories
- video objects
- body movements
- dynamic textures
- soccer video
- hidden markov models