Reconstructed Slides: Reinforcement Learning for Agents - Will Brown, ML Researcher at Morgan Stanley
Source Video
Reinforcement Learning for Agents - Will Brown, ML Researcher at Morgan Stanley
Method
This deck is reconstructed from the existing video frame captures by detecting likely slide regions with OpenCV, cropping/upscaling those regions, deduplicating similar crops, and OCRing the cropped slide images locally. It is a cleaner companion to the full-stage frame deck.
Reconstructed Slides
- Source frame:
slide-001.jpg - Crop:
contour[0, 0, 960, 540]score179.52
- Source frame:
slide-002.jpg - Crop:
contour[0, 0, 960, 540]score177.21
- Source frame:
slide-003.jpg - Crop:
full[0, 0, 960, 540]score178.93
- Source frame:
slide-004.jpg - Crop:
full[0, 0, 960, 540]score165.77
- Source frame:
slide-005.jpg - Crop:
contour[0, 0, 960, 540]score177.12
- Source frame:
slide-006.jpg - Crop:
full[0, 0, 960, 540]score165.08
- Source frame:
slide-007.jpg - Crop:
full[0, 0, 960, 540]score165.91
- Source frame:
slide-008.jpg - Crop:
contour[0, 0, 960, 540]score178.22
- Source frame:
slide-009.jpg - Crop:
full[0, 0, 960, 540]score167.29
- Source frame:
slide-010.jpg - Crop:
full[0, 0, 960, 540]score176.86
- Source frame:
slide-011.jpg - Crop:
contour[0, 0, 960, 540]score177.39
- Source frame:
slide-012.jpg - Crop:
full[0, 0, 960, 540]score170.96
- Source frame:
slide-013.jpg - Crop:
contour[0, 0, 960, 540]score176.27
- Source frame:
slide-014.jpg - Crop:
full[0, 0, 960, 540]score176.35
- Source frame:
slide-015.jpg - Crop:
contour[0, 0, 960, 540]score177.08
- Source frame:
slide-016.jpg - Crop:
full[0, 0, 960, 540]score178.5
- Source frame:
slide-017.jpg - Crop:
contour[0, 0, 960, 540]score178.56
- Source frame:
slide-018.jpg - Crop:
full[0, 0, 960, 540]score174.47
- Source frame:
slide-020.jpg - Crop:
contour[0, 0, 960, 540]score176.35
- Source frame:
slide-021.jpg - Crop:
full[0, 0, 960, 540]score179.1
- Source frame:
slide-022.jpg - Crop:
contour[0, 0, 960, 540]score179.49