Reading the Microsoft Video Indexer Data in axle

Once an asset has been analysed by MVI and the data has been downloaded into axle, you can view the data by clicking the asset to load the proxy player view for that asset. In addition to the comment and subclip tabs below the player, there will be tabs for Faces, Annotations, Transcript, and OCR. Select any tab to view the appropriate data.

Faces - The results of MVI's facial recognition. You can see a thumbnail of the face, the name associated with the face, and timecode markers where the face appeared in the video. Click the name to edit it. This will be uploaded back to MVI, so you can teach it to recognize specific faces.

Annotations - The results of MVI's object and keyword analysis.

Transcript - The results of MVI's speech-to-text transcription. You can edit the transcript, and export it out of axle.

OCR - The results of MVI's optical character recognition, i.e., reading text.