Viola-Jones Face Detection
Viola-Jones Face Detection, a talk delivered by Théo Wang on 17th November 2021 at Churchill College, Cambridge. Abstract: Facial detection is a complex Computer Vision problem involving various trade-offs. If solving it involves using Deep Learning today, it wasn't possible to do so with the limited compute power we had two decades ago. This talk will present arguably the most important machine learning algorithm in the area, the Viola Jones algorithm: the first real-time robust face detector. It is still used today in some cameras, as a preprocessing step in modern ML and still inspires the design of new ML algorithms. We will first cover the theoretical background related to ensemble learning and boosting. This will be followed by an overview of the approach taken by Viola and Jones in their paper. Finally, we will briefly talk about the recent advances in the area of facial detection.

Detecting Faces (Viola Jones Algorithm) - Computerphile

Cache-Oblivious Algorithms

Haar Features for Face Detection | Face Detection

1: Introduction to Neural Networks and Deep Learning; Training Deep NNs

Particle Swarm Optimisation

Lock-free programming

Teenager Disproves 4 Decades Old Belief in Computing

The Viola-Jones Algorithm

The Strange Math That Predicts (Almost) Anything

MAMBA from Scratch: Neural Nets Better and Faster than Transformers

The NTP algorithm

Facial Detection - Part 1

SIFT Detector | SIFT Detector

How convolutional neural networks work, in depth

Sorting networks

Haar Features. | In detail. | Viola Jones | Face Uncensored. | Face Detection.

Train Your Brain to Never Forget (5 Feynman Habits)

How computers learn to recognize objects instantly | Joseph Redmon

Visualizing transformers and attention | Talk for TNG Big Tech Day '24

