Statistical Learning of Multi-view Face Detection

By S. Li, Long Zhu, ZhenQiu Zhang, Andrew Blake, HongJiang Zhang, Harry Shum. European Conference on Computer Vision, 2002

473 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/3c4fdffc12589f9f312a44802b8e2fe8311aa13e

How researchers see this paper

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

In Artificial Intelligence

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

High-Performance Rotation Invariant Multiview Face Detection (2007, methodology): “Compared with other related works listed in the last section, this determinative vector is much more versatile, neither restricted to be exclusive as Jones and Viola’s decision tree [10] nor to be uniform as Fleuret and Geman’s scalar tree [23] and Li et al.’s pyramid [9].”
Face Detection Based on Multi-Block LBP Representation (2007, background): “extended that work to multi-view faces using an extended set of Haar features and an improved boosting algorithm [5].”
On-line Boosting and Vision (2006, methodology): “, introducing FloatBoost (weak classifiers can be also removed from the strong classifier) [71], a vector boosting [52], or by using sequential decision making theory [120].”
A Survey of Recent Advances in Face Detection (2010, methodology): “It has been advocated in various works [46] [6] [101] [62] that RealBoost yields better performance than the original AdaBoost algo- rithm.”
A user attention model for video summarization (2002, methodology): “By employing a real time face detection module presented in [21], we obtain the face information in each frame, including the number of faces, and their poses, sizes, and positions.”
Learning object detection from a small number of examples: the importance of good features (2004, methodology): “For each such feature, we can create a second weak hypothesis by replacing the condition F (x) ≥ T with its dual F (x) T .”
A survey on face detection in the wild: Past, present and future (2015, methodology): “RepresentativeWorks General AdaBoost[17] boosting RealBoost[59] [60] [61] [62] schemes GentleBoost[107] [66] FloatBoost[59] Reuseprevious Boostingchain[110] nodes'results Nestedcascade[61] Introduce AsymmetricBoosting[111] [112] [113] asymmetry Linearasymmetricclassifier[116] SetintermediateFixednod”
Fast rotation invariant multi-view face detection based on real Adaboost (2004, methodology): “We call it Real Adaboost in order to distinguish it from what we call Discrete Adaboost, that is the original Adaboost algorithm [7] adopted in [2][5] using Boolean weak classifier.”
Gaze-based interaction for semi-automatic photo cropping (2006, background): “Both of these systems identify important image areas using a bottom-up computational model of visual salience based on low-level contrast measures [16], and an image-based face detection system [20].”
Joint Cascade Face Detection and Alignment (2014, background): “Many works are on multi-view face detection [10,17,27,7].”
FloatBoost learning and statistical face detection (2004, methodology): “The feature selection or weak classifier construction is based on stagewise approximation of pðxjy; wðM 1ÞÞ.”
Automatic thumbnail cropping and its effectiveness (2003, methodology): “For semantic attention models they use a face detection technique [15] and a text detection technique [6] to compute two different attention values.”
Convolutional face finder: a neural architecture for fast and robust face detection (2004, background): “Lately, very fast approaches based on coarse-to-fine search mechanisms and focus of attention have been proposed [25], [26], [27].”
Support vector tracking (2004, unknown): “Finally, several researchers [22], [9], [13], [14], [15], [20] perform object detection on every frame, ignoring object tracking all together.”
Crowd analysis: a survey (2008, background): “[59] proposes a pyramid structure that adopts coarse-to-fine”
A visual attention model for adapting images on small displays (2003, methodology): “By employing the face detection algorithm in [15], we obtain face information including the number of faces and the pose, region, and position of each face.”
Face Detection using Deep Learning: An Improved Faster RCNN Approach (2017, methodology): “An earlier version of this work was submitted to published in arXiv.org on 28 Jan 2017 ous computer vision tasks, ranging from image classification to object detection and semantic segmentation, etc.”
Human Detection Based on a Probabilistic Assembly of Robust Part Detectors (2004, methodology): “Such classifiers can be formed by a linear combination of weak classifiers, and trained with a learning algorithm to excellent classification results at a small computational cost [8,22].”