<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>MediaPipe on AmeyArc</title><link>https://amey-thakur.github.io/tags/mediapipe/</link><description>Recent content in MediaPipe on AmeyArc</description><generator>Hugo -- 0.152.2</generator><language>en-us</language><lastBuildDate>Mon, 31 Aug 2026 21:40:12 -0400</lastBuildDate><atom:link href="https://amey-thakur.github.io/tags/mediapipe/index.xml" rel="self" type="application/rss+xml"/><item><title>Frame-Synchronous Hand Gesture Detection by Projected Winding Order</title><link>https://amey-thakur.github.io/posts/2026-08-31-frame-synchronous-hand-gesture-detection-by-projected-winding-order/</link><pubDate>Mon, 31 Aug 2026 21:40:12 -0400</pubDate><guid>https://amey-thakur.github.io/posts/2026-08-31-frame-synchronous-hand-gesture-detection-by-projected-winding-order/</guid><description>A gesture recogniser that drives an interface is judged by whether it eventually fires. One that drives a visual effect inside a recording is judged by when it fires, because the viewer sees the gesture and its consequence in the same footage and will attribute one to the other only if they coincide. For the rotation of an open hand about its long axis, the instant can be obtained directly and exactly from projective geometry, with no classifier, no training data and no calibration. This is the full write-up of the paper.</description></item></channel></rss>