Reconstructing Signing Avatars From Video Using Linguistic Priors.
Maria-Paola FortePeter KulitsChun-Hao HuangVasileios ChoutasDimitrios TzionasKatherine J. KuchenbeckerMichael J. BlackPublished in: CoRR (2023)
Keyphrases
- video sequences
- video data
- multimedia
- video streams
- video frames
- natural language processing
- virtual environment
- virtual world
- video content
- space time
- natural language
- video database
- event detection
- real time video
- video clips
- real time
- spatial and temporal
- multimedia data
- bayesian framework
- video analysis
- event recognition
- temporal information
- virtual reality
- moving objects
- video surveillance
- generative model
- multi view
- prior knowledge