Microsoft AI-102 Exam - Topic 1 Question 6 Discussion

Actual exam question for Microsoft's AI-102 exam

Question #: 6
Topic #: 1

You have a Video Indexer service that is used to provide a search interface over company videos on your company's website.

You need to be able to search for videos based on who is present in the video. What should you do?

ACreate a person model and associate the model to the videos.

BCreate person objects and provide face images for each object.

CInvite the entire staff of the company to Video Indexer.

DEdit the faces in the videos.

EUpload names to a language model.

Show Suggested Answer

Suggested Answer: A

Video Indexer supports multiple Person models per account. Once a model is created, you can use it by providing the model ID of a specific Person model when uploading/indexing or reindexing a video. Training a new face for a video updates the specific custom model that the video was associated with.

Note: Video Indexer supports face detection and celebrity recognition for video content. The celebrity recognition feature covers about one million faces based on commonly requested data source such as IMDB, Wikipedia, and top LinkedIn influencers. Faces that aren't recognized by the celebrity recognition feature are detected but left unnamed. Once you label a face with a name, the face and name get added to your account's Person model. Video Indexer will then recognize this face in your future videos and past videos.

https://docs.microsoft.com/en-us/azure/media-services/video-indexer/customize-person-model-with-api

by Blair at May 04, 2022, 02:10 AM

Limited Time Offer

25%

Off

Get Premium AI-102 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Bo

5 months ago

Not sure if editing faces is a good idea, seems risky.

upvoted 0 times

...

Veronika

5 months ago

Totally agree with A, it's efficient and effective.

upvoted 0 times

...

Darnell

5 months ago

Wait, inviting the whole staff? That sounds impractical!

upvoted 0 times

...

Socorro

5 months ago

I think B is better since it allows for more detailed identification.

upvoted 0 times

...

Ressie

5 months ago

Option A seems like the most straightforward solution.

upvoted 0 times

...

Levi

5 months ago

I feel like editing faces in the videos isn't really a solution for searching. It seems more like a workaround than a proper method.

upvoted 0 times

...

Lorrine

5 months ago

Inviting the entire staff seems like a silly option. I doubt that's what they want us to do here.

upvoted 0 times

...

Dorothea

5 months ago

I remember practicing a question about associating face images with person objects. That might be related to option B.

upvoted 0 times

...

Chanel

6 months ago

I think we need to create a person model, but I'm not entirely sure if that's the best approach for searching videos.

upvoted 0 times

...

Gilberto

6 months ago

This seems like a straightforward cost comparison question. I'll review the key factors to consider for public vs. private bond issuance and then decide which option makes the most financial sense.

upvoted 0 times

...