Robust Real-time Object Detection

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

4,179 citations recorded by the source corpus.

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

You Only Look Once: Unified, Real-Time Object Detection (2015, methodology): “Then, classifiers [35, 21, 13, 10] or localizers [1, 31] are used to identify objects in the feature space.”
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)).”
AlterSGD: Finding Flat Minima for Continual Learning by Alternative Training (2021, background): “Recently, deep neural networks (DNNs) became the dominant paradigm in various real-world applications, for example, image classiﬁcation [12, 18, 17, 16, 19], semantic segmentation [43, 32, 27], object detection [39, 15, 38, 46, 35].”
Particular object retrieval with integral max-pooling of CNN activations (2015, methodology): “By approximating the maximum in this manner, we can now use integral images (Viola & Jones, 2001) to approximate the regional feature vector f R deﬁned on any rectangular region R .”
Sharing Visual Features for Multiclass and Multiview Object Detection (2007, methodology): “Various classifiers have been used, such as SVMs [26], naive Bayes [30], mixtures of Gaussians [12], boosted decision stumps [37], etc.”
Semi-Supervised Self-Training of Object Detection Models (2005, background): “Negative examples are assumed to be plentiful [23] and can be collected cheaply.”
Context-based vision system for place and object recognition (2003, background): “Another difference between our approach to object recognition and previous approaches is that we try to recognize a large set of object types (24) in a natural, unconstrained setting (images are collected by a wearable camera), as opposed to recognizing a small number of classes (such as faces and c”
Real or Fake? Learning to Discriminate Machine from Human Generated Text (2019, methodology): “Since the discriminator is learned after the generator has been trained, it learns from the residual error of the generator, and therefore, our training procedure is a particular instance of a “cascade” model (Viola & Jones, 2001) and “boosting” (Freund & Schapire, 1997).”
Vision-Based Traffic Sign Detection and Analysis for Intelligent Driver Assistance Systems: Perspectives and Survey (2012, methodology): “In addition, [34] used a color-based search method that, while closely related to, is not directly thresholding based.”
Age Synthesis and Estimation via Faces: A Survey (2010, methodology): “The faces are cropped automatically by a face detector [159] and resized to 60 60 gray-level patches.”
Fast Object Segmentation in Unconstrained Video (2013, methodology): “We propose an efficient algorithm which we call integral intersections, inspired by the use of integral images in [25].”
Privacy-CNH: A Framework to Detect Photo Privacy with Convolutional Neural Network using Hierarchical Features (2016, methodology): “We removed privacy sensitive data from the photos. works extract low-level image features such as color histogram and bag of visual words (BOVW) (Yang et al. 2007) features along with a face detector (Viola and Jones 2001) from the privacy dataset to develop a SVM (Burges 1998) classiﬁer.”
Non-maximum Suppression for Object Detection by Passing Messages Between Windows (2014, background): “The Viola-Jones detector [4] partitions those responses in disjoint sets, grouping together responses as soon as they overlap, and propose, for each group with enough windows, a window whose coordinates are the group average.”
Detection of traffic signs in real-world images: The German traffic sign detection benchmark (2013, methodology): “From the latter category, we consider a ViolaJones-type detector based on Haar-like features [10], linear discriminant analysis relying on HOG descriptors [11], and a color template matching approach.”
Autonomous convoy driving by night: The vehicle tracking system (2015, background): “Concerning the computational efficiency of hundreds of particles, it is advisable to calculate line integral images ([21], [22]) for analyzing the feature congruence.”
FrugalML: How to Use ML Prediction APIs More Accurately and Cheaply (2020, background): “Model Cascades: Cascades consisting of a sequence of models are useful to balance the quality and runtime of inference [49, 50, 24, 36, 48, 51, 54, 38].”
Learning Fast Classifiers for Image Spam (2007, methodology): “Viola and Jones (2002) use a method similar to JIT feature extraction for real time object detection.”
Demographic Estimation from Face Images: Human vs. Machine Performance (2015, methodology): “We use multi-class AdaBoost [40], [65] to select the demographic informative features.”