ScanQA: 3D Question Answering for Spatial Scene Understanding.
Daichi AzumaTaiki MiyanishiShuhei KuritaMotoaki KawanabePublished in: CVPR (2022)
Keyphrases
- question answering
- scene understanding
- object recognition
- object detection
- vision system
- d scene
- natural language processing
- information extraction
- information retrieval
- video surveillance
- qa clef
- natural language
- question classification
- syntactic information
- passage retrieval
- natural language questions
- machine learning
- cross language
- question answering systems
- three dimensional
- answering questions
- data mining
- answer validation
- semantic roles
- text classification
- computer vision