Reconstructed Slides: Building AI Agents that actually automate Knowledge Work - Jerry Liu, LlamaIndex

Source Video

Building AI Agents that actually automate Knowledge Work - Jerry Liu, LlamaIndex

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: full [0, 0, 960, 540] score 160.13

• Source frame: slide-002.jpg
• Crop: full [0, 0, 960, 540] score 176.6

• Source frame: slide-003.jpg
• Crop: full [0, 0, 960, 540] score 176.32

• Source frame: slide-004.jpg
• Crop: full [0, 0, 960, 540] score 176.6

• Source frame: slide-005.jpg
• Crop: full [0, 0, 960, 540] score 176.15

• Source frame: slide-006.jpg
• Crop: full [0, 0, 960, 540] score 158.37

• Source frame: slide-007.jpg
• Crop: full [0, 0, 960, 540] score 176.75

• Source frame: slide-008.jpg
• Crop: full [0, 0, 960, 540] score 158.81

Dense Scene-Detected Slide Candidates

• youtube jVGCulhBRZI dense slides