NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario.
Tianwen QianJingjing ChenLinhai ZhuoYang JiaoYu-Gang JiangPublished in: CoRR (2023)
Keyphrases
- question answering
- multi modal
- autonomous driving
- cross modal
- video search
- grand challenge
- information retrieval
- qa clef
- question classification
- single modality
- information extraction
- natural language
- natural language processing
- answer extraction
- low level
- passage retrieval
- open domain question answering
- qa systems
- audio visual
- visual information
- cross language
- stereo vision
- sentence retrieval
- syntactic information
- high dimensional
- semantic roles
- candidate answers
- multiple modalities
- visual features
- feature selection