Robust Real-Time Face Detection

By Paul A. Viola, Michael J. Jones. 2001

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

Cascade R-CNN: High Quality Object Detection and Instance Segmentation (2019, methodology): “This has some similarity to boostrapping methods commonly used to assemble datasets for object detection [13], [53].”
Learning Non-maximum Suppression (2017, background): “The de facto standard algorithm, GreedyNMS, has survived several generations of detectors, from Viola&Jones [32], over the deformable parts model (DPM) [7], to the current state-of-the-art R-CNN family [10, 9, 21].”
DeepSetNet: Predicting Sets with Deep Neural Networks (2016, background): “Traditional approaches follow the slidingwindow paradigm [44, 7, 46, 11, 2], where each possible (or rather plausible) image region is scored independently to contain a person or not.”
You Only Look Once: Unified, Real-Time Object Detection (2015, background): “Detectors for single classes like faces or people can be highly optimized since they have to deal with much less variation [36].”
Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors (2016, background): “The advantage of having a regular grid of anchors is that predictions for these boxes can be written as tiled predictors on the image with shared parameters (i.e., convolutions) and are reminiscent of traditional sliding window methods, e.g. [39].”
Learning to Segment Object Candidates (2015, background): “Until recently, the dominant paradigm in object detection was the sliding window framework: a classifier is applied at every object location and scale [4, 8, 32].”
What Makes for Effective Detection Proposals? (2015, background): “F”
Cascade R-CNN: Delving Into High Quality Object Detection (2017, methodology): “This is similar to boostrapping methods commonly used to assemble datasets in object detection literature [34, 9].”
Dynamic Neural Networks: A Survey (2021, background): “a cascaded [38] or parallel [39] structure, and selectively activating them conditioned on the input.”
A MultiPath Network for Object Detection (2016, neutral): “Until recently, the sliding window paradigm was dominant [6, 32], especially for face and pedestrian detection.”
The Open Images Dataset V4 (2018, methodology): “The advent of object detection came in the form classiﬁers applied densely to windows sliding over the image (e.g. based on boosting (Viola and Jones, 2001a,b) or Deformable Part Models (Felzenszwalb et al., 2010a,b)).”
Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics (2016, methodology): “[29] proposed a famous strategy for face detection by using a cascaded boosting classifier composed by a sequence”
CoupleNet: Coupling Global Structure with Local Parts for Object Detection (2017, neutral): “Before the arrival of CNN, visual tasks have been dominated by traditional paradigms [4, 6, 23, 26, 24].”
How to Represent Part-Whole Hierarchies in a Neural Network (2021, background): “For example, a pale vertical oval with a darker horizontal band slightly more than halfway up suggests one kind of face [Viola and Jones, 2004] so a convolutional net operating on coarse pixels can provide useful information to directly initialize the higher-level embeddings 18 .”
A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection (2016, methodology): “One of the earliest methods to achieve real-time detection with high accuracy was the cascaded detector of [1].”
Geometric context from a single image (2005, background): “For example, currently popular object detection algorithms [26, 32, 33] assume that all relevant information about an object is contained within a small window in the image plane (objects are found by exhaustively scanning over all locations and scales).”
The MegaFace Benchmark: 1 Million Faces for Recognition at Scale (2015, methodology): “It was collected by running Viola-Jones face detection [32] on Yahoo News photos.”
Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation (2015, methodology): “The ﬁrst one, popularized by the Viola-Jones face detection algorithm [1], formulates object localization as window classiﬁcation.”