Semantic parsing for priming object detection in indoors RGB-D scenes.
Cesar Dario Cadena LermaJana KoseckáPublished in: Int. J. Robotics Res. (2015)
Keyphrases
- d scene
- semantic parsing
- object detection
- scene understanding
- dependency parsing
- single image
- question answering
- semantic role labeling
- depth map
- computer vision
- image based rendering
- semantic representation
- semantic roles
- context free grammars
- optical flow
- natural language processing
- view dependent
- natural language understanding
- object recognition
- background subtraction
- multi view
- statistical machine translation
- indoor scenes
- data points
- high dimensional
- feature vectors
- training data
- active learning
- domain specific
- image processing