Any plans on including Finnish, Swedish and other nordic languages in the near future?

A.I or API on the recognition of facial expression and/or motion language (Sign Language) in Korean ..Korean Sign Language if possible I am willing to provide you with data,

In case using Video Indexer in org, we'd like to set co-owner and/or feature to transfer to next owner.

We would like to have privacy option "Public" and "Private" such as sharing within group. Much nicer if could be shared in org account/security group.

We'd like to share account with several users, so that it would be nice to be able to add by group (such as AD security group if it is org account), not individually

Video Edit page doesn't show all subtitles and ocrs. As screenshot shows, video info tells 4 ocr exists, but it shows only 3 (because of area height)

https://docs.microsoft.com/en-us/azure/cognitive-services/video-indexer/video-indexer-embed-widgets

The steps to embed private videos appears outdated. Got a "not authorized" error even though the access token is valid.

The steps described in the API portal seems up to date though, as it worked perfectly.

now it's just a manual file upload but I would like to work with YouTube as a data source

Do you have use cases for scouting reports for coaches?

For instance, in basketball, I want to tag all plays when the opponent's star player went left and pulled up for a jump shot. I also want to tag all plays when the opponent's star player went left and drove to the basket.

I want all this analysis and tagging to be done in the background so that coaches and players can simply look for this and rewatch the videos during halftime.

Hello! Tell me how you can search the image (face photo) in a video file (archive video), analog AWS rekognition face-search

Gostaria de suporte para aprender mais - pode er em telefone Brasil - 19 933074346 ou http://bit.ly/WhatsappGiacomoNerone

I've tried the indexer with videos from Vimeo, such as, for instance I searched the Vimeo site for 'neural networks' and found this URL: https://vimeo.com/195917263
The indexer gives an error message "There is some problem with the input values."

My own product would benefit if Video Indexer analyzed prosody. "Prosody" is the speed of speech, and the intonation. If I knew, for example, that between 5 seconds and 10 seconds the speaker was speaking fast, that can help my application. If I know that he is speaking a dull, emotionless way, that can also help. If I know that the volume (and / or pitch) of his tone is rising, that also helps. Sentiment analysis is good, but its on a more abstract level. I believe that Carnegie Mellon has developed a prosody detector.

The insights structure in the videoindex has a version, but there is not information on the changes between the versions.
A changelog would be nice.

How long is breakdown data from REST API retained in Video Indexer service and it is there a cost to store this data?

What about thumbnail images generated (available from thumbnailUrl)? How long are they stored/available and are there any cost to have them accessible for long term periods?

PS: I understand that Face API images are available only for 24h after the process generation

VI supports only one arabic dialect i.e. ar-eg. VI should also support other arabian dialects like gulf dialect ar-ae. Is there any plan for supporting different arabic dialects?

Add the ability to manually add custom tags to videos to allow for videos to be categorised or searched by tag.
There is currently no way to manually organise certain videos into categories/tags.

The tag meta-data may not be directly related to the content of the video e.g. you may want to create a tag to present all videos with a particular theme or to indentify all videos 'owned' by a rights holder.

Allow Tag more Person

Hi, I have been trying to upload videos into the indexer but it keeps getting hanged at 95% and restarting at 0%. The video is around 500MB (4 hours long) and video with smaller size (50MB) gets uploaded and indexed.
Please help.

if there is more than one person speaking at the same time, video indexer only resolves transcription for one (random) speaker. ideally, it needs to detect many speakers at the same time, and return what is each one speaking