Representing actions with Kernels

A long standing research goal is to create robots capable of interacting with humans in dynamic environments. To realise this a robot needs to understand and interpret the underlying meaning and intentions of a human action through a model of its sensory data. The visual domain provides a rich description of the environment and data is readily available in most system through inexpensive cameras. However, such data is very high-dimensional and extremely redundant making modeling challenging.

Authors

• Guoliang Luo
• Niklas Bergström
• Carl Henrik Ek
• Danica Kragic

Keywords

• Kernel
• Image segmentation
• Semantics
• Robustness
• Data models
• Feature extraction
• Visualization
• Real Scenarios
• Semantic Information
• Real-world Scenarios
• Support Vector Machine
• Similarity Measure
• Feature Space
• Kernel Function
• Segmentation Algorithm
• Exact Match
• Types Of Noise
• Action Classes
• Image Edge
• Kernel Methods
• Markov Random Field
• Objects In The Scene
• Segmentation Errors
• Semantic Context
• Paradigmatic Model
• Sequence Graph
• Scene Graph
• Semantic Graph
• Kernel Approach
• Changes In Interactions
• Discrimination Method
• Data-driven Models
• Representative Sequences