Metric-Free Exploration for Topological Mapping by Task and Motion Imitation in Feature Space.
Yuhang HeIrving FangYiming LiRushi Bhavesh ShahChen FengPublished in: CoRR (2023)
Keyphrases
- feature space
- high dimensional feature space
- embedding space
- motion estimation
- motion analysis
- motion model
- image sequences
- dot product
- camera motion
- space time
- training set
- moving objects
- optical flow
- high dimensionality
- motion capture
- geometric structure
- high dimensional
- motion segmentation
- kernel function
- dissimilarity measure
- topological map
- metric learning
- riemannian manifolds
- feature selection
- motion detection
- hyperplane
- classification accuracy
- input space
- motion field
- metric space
- image retrieval
- image representation
- low dimensional
- feature vectors
- evaluation metrics
- graph cuts
- distance measure
- dimensionality reduction
- support vector
- reinforcement learning
- multi dimensional scaling