A critical essay on LinkedIn's performative culture, particularly mocking repetitive computer vision projects. The author demonstrates how easily such projects can be created, building a YOLO detector for LinkedIn posts in just 90 minutes to prove the low barrier to entry for 'impressive-looking' but ultimately useless projects.
Hiera-Hand is a hand-action recognition AI algorithm that tracks people in videos, localizes their hands, and classifies each hand's action as grasp, hold, operate, or release. The standalone demo uses YOLO pose detection and a fine-tuned Hiera-Base model to process video frames at 224×224 resolution with temporal context windows.