Predicting tongue motion in unlabeled ultrasound videos using convolutional LSTM neural network.
Chaojie ZhaoPeng ZhangJian ZhuChengrui WuHuaimin WangKele XuPublished in: CoRR (2019)
Keyphrases
- neural network
- motion analysis
- ultrasound images
- motion features
- recurrent neural networks
- image sequences
- periodic motion
- recognition of human actions
- moving camera
- ultrasound probe
- video representation
- static images
- network architecture
- video sequences
- space time
- key frames
- input video
- dynamic scenes
- optical flow
- artificial neural networks
- motion model
- video content
- motion estimation
- adjacent frames
- motion patterns
- temporal domain
- motion parameters
- motion capture data
- motion detection
- temporal coherence
- labeled data
- spatio temporal
- neural network model
- moving objects
- video clips
- human motion
- motion cues
- video analysis
- back propagation
- motion trajectories
- recognizing human actions
- supervised learning
- traffic scenes
- video stabilization
- successive frames
- video scene
- motion segmentation
- video surveillance
- spatial and temporal
- camera motion
- action recognition
- video data
- semi supervised learning
- unsupervised learning
- training data
- computer vision
- deep learning
- video objects
- object motion
- active contour model
- human actions
- computer aided