Commonsense Scene Semantics for Cognitive Robotics: Towards Grounding Embodied Visuo-Locomotive Interactions.
Jakob SuchanMehul BhattPublished in: ICCV Workshops (2017)
Keyphrases
- cognitive robotics
- cognitive science
- d scene
- cognitive systems
- multiple images
- scene understanding
- single image
- three dimensional
- input image
- formal semantics
- knowledge base
- atomic actions
- logic programming
- video sequences
- moving objects
- machine learning
- commonsense knowledge
- artificial intelligence
- cognitive processes
- semantic information
- image sequences
- dynamic scenes
- complex scenes
- intelligent agents
- neural network
- information processing
- object detection
- knowledge representation
- optical flow
- word meanings
- computer science