Coarse-to-Fine Face Detection

By Franccois Fleuret, Donald Geman. International Journal of Computer Vision, 2004

342 citations recorded by the source corpus.

Subfields: Biophysics, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/9b535f4edc4cbf8d4fb6182ec6b5c54db3c1cccb

How researchers see this paper

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

In Biophysics

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Fast Feature Pyramids for Object Detection (2014, background): “Cascades [27], [47], [48], [49], [50], coarse-to-fine search [51], distance transforms [52], etc., all focus on optimizing classification speed given precomputed image features.”
Crosstalk Cascades for Frame-Rate Pedestrian Detection (2012, background): “Finally, research on optimizing other types of classifiers [1,2,3,17,18,19] is of considerable interest, however, such methods have difficulty matching the speed achieved by boosted classifiers.”
FloatBoost learning and statistical face detection (2004, background): “strategy [46], [47], and generalizes the cascade structure of”
Fast multiple object tracking via a hierarchical particle filter (2005, background): “This coarse-to-fine cascade idea, where the first stages reject most incorrect matches, while retaining all correct and a few incorrect ones, has been successfully used in target recognition and face detection [39, 13, 22, 34, 30].”
High-Performance Rotation Invariant Multiview Face Detection (2007, methodology): “In [23], Fleuret and Geman employed a scalar tree detector (Fig.”
Image Parsing: Unifying Segmentation, Detection, and Recognition (2003, neutral): “There has also been impressive work using image features for face detection [3, 15, 17, 21, 22, 20] and for text detection and recognition [8, 16, 1].”
ACFNet: Attentional Class Feature Network for Semantic Segmentation (2019, background): “There are a lot of successful applications of using coarse-to-fine approaches, such as face detection [13], shape detection [1], face alignment [48] and optical flow [3].”
The Fastest Pedestrian Detector in the West (2010, background): “Through numerous strategies, including cascades [28], coarse-to-fine search [17], distance transforms [13], branch and bound search [19], and many others, the classification stage can be made quite fast.”
Towards Scalable Representations of Object Categories: Learning a Hierarchy of Parts (2007, background): “The learning algorithm proposed in [8], which acquires a hierarchy of local edge arrangements by correlation, is in concept similar to our learning method.”
A coarse-to-fine approach for fast deformable object detection (2011, background): “Traditionally, object detection has been accelerated by the use of cascades [25, 14, 15, 7, 1, 22, 9].”
Object Detection in 20 Years: A Survey (2019, neutral): “Cascaded detection is a commonly used technique [10], [125].”
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].”
50 Years of object recognition: Directions forward (2013, background): “As Amit and Geman [240] did, Piater clusters these features into compound features based on their geometric relations.”
Detecting and reading text in natural scenes (2004, positive): “Its performance on detecting faces [19] compares favorably with other successful algorithms for detecting faces [3, 15, 17, 21, 24].”
FREAK: Fast Retina Keypoint (2012, background): “Note that in the last decades, coarse-to-fine strategy has often been explored in detecting and matching objects [9, 2].”
Object Detection (2020, background): “An alternative is to create a coarse to fine decomposition of object poses [8].”