How to point out which person in the video is you
Describe yourself to Vizard Agent by something visible and something positional, such as "the green belt, on the referee's left", rather than expecting it to recognise your face. Then say what counts as your moment: in most recordings you are on screen far more often than you are doing anything, and only the second kind is worth cutting.
What do you type into Vizard Agent?
Anchor your description to something that does not move. "On the left" stops meaning anything the moment the camera shifts; "on the referee's left" survives any camera move, because Vizard Agent can see the referee in the frame as well. Then name the actions that count, since being in frame is not a moment.
Prompt
What does Vizard Agent actually do?
Identification and selection run as two separate passes, because collapsing them into one is exactly what produces a highlight reel of somebody standing about. A kit colour plus a positional anchor can follow one person when the faces are turned away, and naming the kinds of action turns forty appearances into eight moments. In the session behind this article it:
- Measured a real competition recording, built a quick visual map of the whole session and reviewed the combined frames to see who was where.
- Found the active moments of the competitor in the green belt, then built a fuller frame map to place them in context.
- Pinned down the throws and the strongest groundwork sections specifically.
- Prepared the candidate frames and showed the selected actions as a preview before cutting anything.
- Cut the chosen moments to the music's beats.
When does this not work well?
Some recordings cannot be disambiguated at all. Two competitors in the same colour, a wide shot where everybody is a few pixels tall, or a camera that never once establishes the fixed reference you described will each defeat the method, and Vizard Agent will say so rather than guess. Sides that swap at half time also reverse your anchor.
Common questions
Why not just use my face? Because sport rarely shows it clearly. Vizard Agent uses kit and position instead.
What if several people wear the same colour? Give Vizard Agent a second detail, such as a number, a position or a hairstyle.
What if I change sides? Tell Vizard Agent when, and it switches the anchor at that point.