Video Indexer
Welcome to the Video Indexer Forum
Categories
API – Any ideas or feedback pertaining to features or enhancements to Video Indexer API.
General – Any general ideas or suggestions related to Video Indexer.
Portal – Any ideas or feedback regarding the web portal for Video Indexer
Video AI – Any ideas or suggestions regarding Video AI features in Video Indexer.
-
Give all emotions not just positive negative
Analyze each frame or one in x frames fully for the 7 emotions your old face emotion recognition gave.
Return a rolling average of the emotion data as well as JSON.The idea is that even if individual frames don;t give you great data a group may act as boosting and give better results.
2 votesMoving to under review per visual emotion detection.
-
Player widget timecode parameter
There is currently no way to make the player widget start from a specific timecode.
On the videoindexer website this functionality is used to jump to a specific point in time from a search result, however there is no parameter on the iframe embed to support this.
1 voteIndeed there was an issue with the t param.
The issue has been fixed, please retry -
CORS
Is CORS enabled for Video Indexer?
1 vote -
Overlapped Chinese Transcripts
when Chinese transcripts display, the characters overlapped
1 voteSeems to be ok in our testing.
User voice is not a support channel.
You may refer to our support via visupport[at]microsoft[dot]com -
Two languages of transcripts on screen
so far, only one language displays on screen. since we have Microsoft Translator, could we show two languages of transcripts in the meanwhile? like video is in English, we could see transcripts both in English and Chinese?
1 votethe VI player supports showing auto-translated captions across 54 languages, but only one language at a time.
If you’d like to show a few languages, you can opt to use the API and another player -
Upload hangs at 95% (Large files)
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.1 voteUser voice is not a support channel.
You may refer to our support via visupport[at]microsoft[dot]com
-
Extract numbers and text frame by frame and export
Would it be possible to extract text / numeric information and save it to a file? example video of stock market, with continuous numeric and text data, and export content to downloadable file
1 voteYou can get all of the information that VI managed to extract from the JSON index.
Please see API at https://aka.ms/viapi -
VTT output time code based on start time code in video file
My customer would like to have VTT file with offset calculated time code when start time code data is included in uploaded video file. Can you consider this kind of function in Video Indexer??
2 votes -
Autoscroll Lock
Every time you scroll or edit the transcript it disables the autoscroll and you have to turn it back on again. This is very annoying when editing long transcripts.
1 vote -
Ability to edit transcript timing.
When the autogenerated transcript is not correct you are able to edit the words, but there is no way to adjust the timing to make those words be in sync with the video. Please enable the ability to adjust the timing.
3 votes -
Please Add vocabulary adaptation library for various industries
We have integrated the API onto our platform and the accuracy of the transcript is important for the success of our pilot. While i read a few blog posts by Dr. Royi on bringing in our own vocabulary to the indexer, with upload option of words and sentences relevant to a specific industry, i was unable to get the desired results. Is there a way we can have some sort of vocabulary adaptation library available for various industries that can probably make the transcript a lot more accurate?
Also, it would help if there are are video tutorials available for…
1 votePlease refer to our support via visupport[at]microsoft[dot]com
-
Max characters per VTT line - can we control max characters per line in VTT file
For the best user experiences, a limitation of max number of characters per line in VTT file would be helpful for better reading and showing in the expected subtitling area in the video picture.
Can you give some control to limit max number of characters per line in VTT file?
6 votesThank you for your feedback, we are now reviewing the feature.
-
Merge Confidence data output into VTT file
Currently Azure Media Indexer (backend Speech-to-Text processor of Video Indexer) can output Confidence data in VTT file line by line. Could you please merge the confidence data into the output VTT file from Video Indexer?
1 vote -
processing stuck at 65%
I uploaded a video and its stuck at 65%. Any one can help here?
1 votePlease refer to our support via visupport[at]microsoft[dot]com
-
Allow bulk upload and bulk download in the Video Indexer web application
It would be fantastic to be able to bulk upload and then bulk download selected video clips in the web portal.
I am looking at using Video Indexer as a video library for my entire video library (3tb) and without this functionality it would take forever!
Thanks!6 votesBulk uploading/downloading can be achieved by integrating with the Video Indexer LogicApps: https://azure.microsoft.com/en-us/blog/logic-apps-flow-connectors-will-make-automating-video-indexer-simpler-than-ever/
-
support more than one speaker speaking at the same time
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
4 votes -
confidence level
For transcript (audio, OCR), how can I query a summary of confidence level for each? For content model customization of Brand and Language, same question? Lastly, how can I determine which group of language model text files was most pertinent? I wish to automate the workflow where I 1) submit language model txt file samples, 2) submit sample video files, 3) query confidence level, if lower than threshold, then 4) submit different language model txt file samples, and so on until confidence level is acceptable.
2 votesConfidence level is provided in the insights json as part of attributes
-
Are mixed languages supported?
Polyglotism: via API/Portal, please consider supporting multiple languages within 1 source video or audio input? IE: Within 1 video file, recognizable text and speech are in English and Spanish. In another, French and Italian. Thanks. Today, I run the video twice and semi-automatically merge the results, discarding the mistakes.
2 votesI’m happy to update that the feature is now available in public preview.
You can can more about it here- https://docs.microsoft.com/en-gb/azure/media-services/video-indexer/multi-language-identification-transcription -
Add technical data of video to breakdown
Add technical video metadata to breakdown, e.g. framerate, format, codecs, per track information, exact duration, resolution, aspect ratio, bitrate, start timecode ...
3 votes -
Ability to train face recognition prior to indexing (e.g. with images, similar to FACE API)
A way to train the face recognition with "known data" (e.g. images of people, like in FACE API).
This could be something like a corporate image database that can be referenced or the images uploaded.
Also a way to export the face training data would be nice.16 votesdone! see https://azure.microsoft.com/en-us/blog/people-recognition-enhancements-video-indexer/ for details
- Don't see your idea?