Answering Visual What-If Questions: From Actions to Predicted Scene Descriptions.
Misha WagnerHector BaseviRakshith ShettyWenbin LiMateusz MalinowskiMario FritzAles LeonardisPublished in: ECCV Workshops (1) (2018)
Keyphrases
- observed scene
- visual data
- visual input
- visual environment
- visual scene
- high level
- scene categorization
- visual information
- visual features
- multiple images
- three dimensional
- d scene
- dynamic scenes
- spatial layout
- scene analysis
- video sequences
- scene understanding
- visual appearance
- answering queries
- complex scenes
- scene recognition
- scene classification
- spatial relations
- single image
- input image
- correct answers
- multiple objects
- real world objects
- query answering
- reasoning about actions
- vision system
- moving objects
- symbolic description