Example-based Learning for View-based Human Face Detection

By Kah Kay Sung, Tomaso A. Poggio. 1994

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation (2013, methodology): “Our method achieves similar performance (53.3% mAP) on VOC 2011/12 test.”
Mixtures of trees for object recognition (2001, unknown): “Template-based approaches (e.g., to detect frontal views of faces [8] [11] and pedestrians [7]) are not general because they do not allow object parts to move with respect to each other.”
Constructing models for content-based image retrieval (2001, background): “Related work Sung and Poggio [17] model a face as a rigid global patch and the distribution of these patches is learnt from a large collection of face images.”
Efficient visual event detection using volumetric features (2005, methodology): “Sung and Poggio [17] propose a bootstrapping method which we use to generate more negative examples after training each node.”
Face Recognition (2018, unknown): “For example, [Sung and Poggio, 1998] used a combination of statistical measures and a multi-layer perceptron network for face detection.”
Object detection using feature subset selection (2004, methodology): “[63] developed a system composed of two parts, (i) a distribution-based model for face/non-face representations and (ii) a multilayer NN for classi1cation.”
A Bayesian approach to unsupervised one-shot learning of object categories (2003, background): “These have to be collected, and sometimes manually segmented and aligned [2, 3, 4, 5, 6, 7] – a tedious and expensive task.”
Face Photo-Sketch Synthesis and Recognition (2012, methodology): “Methods directly using traditional photo-based face recognition techniques such as the eigenface method [1] and the elastic graph matching method [2] were tested on two very small sketch data sets with only 7 and 13 sketches, respectively.”
Convolutional face finder: a neural architecture for fast and robust face detection (2004, background): “It automatically derives problem-specific feature extractors , from a large training set of face and nonface patterns, without making any assumptions about the features to extract or the areas of the face patterns to analyze.”
Online domain adaptation of a pre-trained cascade of classifiers (2011, unknown): “This differs from the typical approach of applying a classifier to each of these regions independently [12, 13, 15, 17].”