You must extract structured fields from video content. Which service fits?
Why C is the answer
Content Understanding
Content Understanding processes documents, images, video and audio into a user-defined format.
In detail
- Content Understanding extracts structured fields from video.
- Define the fields you need.
Use case
An illustrative scenario, not a real incident.
A training team needs topics and speakers from videos. Content Understanding extracts structured fields.
See it in different ways
flowchart TD
A{"What do you need?"} -->|"New image or video"| B["Generation model"]
A -->|"Change part of an image"| C["Inpainting with a mask"]
A -->|"Describe an image"| D["Multimodal model"]
A -->|"Structured output from video"| E["Content Understanding"]stateDiagram-v2 [*] --> Extract Extract --> Review: low confidence Extract --> Index: high confidence Review --> Index: corrected Index --> [*]
flowchart LR S0["Video"] --> S1["Content Understanding"] --> S2["Structured fields"]
Key point: Content Understanding handles video.
Why the other options are wrong
- A. A text-only summarization call
- A text-only call cannot read video.
- B. Azure Translator
- Translator works on text.
- D. Azure AI Search on its own
- Search does not extract from video by itself.