Text2Face: A Multi-Modal 3D Face Model.
Will RowanPatrik HuberNick E. PearsAndrew KeelingPublished in: CoRR (2023)
Keyphrases
- multi modal
- human faces
- facial expressions
- face model
- video search
- expression recognition
- multiple modalities
- face images
- audio visual
- high dimensional
- text retrieval
- information retrieval
- cross modal
- facial features
- pose and lighting
- multi modality
- uni modal
- semantic concepts
- text data
- image annotation
- face detection
- face recognition
- keypoints
- feature points
- keywords
- fusing multiple
- computer vision