Visual Commonsense for Scene Understanding Using Perception, Semantic Parsing and Reasoning.
Somak AdityaYezhou YangChitta BaralCornelia FermüllerYiannis AloimonosPublished in: AAAI Spring Symposia (2015)
Keyphrases
- single image
- scene understanding
- d scene
- semantic parsing
- scene categorization
- knowledge base
- object recognition
- vision system
- object detection
- dependency parsing
- semantic representation
- semantic role labeling
- visual features
- low level
- video surveillance
- semantic roles
- high dimensional
- question answering
- natural language understanding
- visual motion
- text mining
- statistical machine translation
- computer vision
- real time