Computer vision · Question 12 of 12
A team wants to categorize photos of building damage by type of damage and answer follow-up questions about them. Which statements are correct?
2 answers are correct. Hard Created with AI
Show answer
Answer
- B A multimodal model can categorize and answer follow-up questions
- C For consistent results, the categories should be specified in the prompt
Explanation
Multimodal models understand image content and questions together. Specifying the allowed categories in the prompt makes the results more consistent and easier to process further. OCR only reads text, and image generation creates new images.