Zero-Shot Captioning for Driver Status Reporting
Zero-shot image captioning for in-vehicle driver monitoring without task-specific labeled data — funded by Hyundai NGV
Funded by Hyundai NGV · 2024
Proposed a zero-shot image captioning method for in-vehicle driver monitoring to generate natural language descriptions of driver states, without requiring task-specific labeled data.
Key Contributions
- Designed zero-shot captioning pipeline for driver state reporting
- Operated without task-specific labeled data for driver status reporting agents
- Integrated into an in-vehicle monitoring agent framework