Dense Slides: From Text to Vision to Voice Exploring Multimodality with Open AI: Romain Huet
Source Video
From Text to Vision to Voice Exploring Multimodality with Open AI: Romain Huet
Method
This deck is slide-only. The existing captured video frame set supplies candidate frames, then local OpenCV rejects sponsor/title/speaker-only frames, crops visible slide surfaces, deduplicates, and saves the cropped slide images.
Cropped Visible Slides
- Source scene image:
frame-00017.jpg - Crop:
visible-slide-crop[0, 37, 960, 503]score175.92 - Slide-only rule:
visual-bright-slide
- Source scene image:
frame-00023.jpg - Crop:
visible-slide-crop[0, 37, 960, 503]score175.89 - Slide-only rule:
visual-bright-slide
- Source scene image:
frame-00024.jpg - Crop:
visible-slide-crop[0, 37, 960, 503]score176.13 - Slide-only rule:
visual-bright-slide