Multi-view motion modelled deep attention networks (M2DA-Net) for video based sign language recognition.
Suneetha M.Venkata Durga Prasad MareeduP. V. V. KishorePublished in: J. Vis. Commun. Image Represent. (2021)
Keyphrases
- multi view
- sign language recognition
- dynamic scenes
- single view
- sign language
- gesture recognition
- multiple views
- depth map
- motion model
- d objects
- motion analysis
- semi supervised
- three dimensional
- optical flow
- hand tracking
- image sequences
- camera calibration
- motion estimation
- hand gestures
- surface reconstruction
- space time
- motion segmentation
- human motion
- camera motion
- range images
- viewpoint
- computer vision