Cross-modal Learning of Graph Representations using Radar Point Cloud for Long-Range Gesture Recognition.
Souvik HazraHao FengGamze Naz KipritMichael StephanLorenzo ServadeiRobert WilleRobert WeigelAvik SantraPublished in: CoRR (2022)
Keyphrases
- long range
- gesture recognition
- point cloud
- cross modal
- visual recognition
- structure from motion
- conditional random fields
- multi modal
- stereo camera
- learning tasks
- supervised learning
- active learning
- computer vision
- learning algorithm
- information retrieval
- hidden markov models
- training set
- video sequences
- training data