A general framework for object detection

By Constantine Papageorgiou, Michael Oren, Tomaso A. Poggio. 1998

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): “Detection pipelines generally start by extracting a set of robust features from input images (Haar [25], SIFT [23], HOG [4], convolutional features [6]).”
FindIt: Generalized Localization with Natural Language Queries (2022, background): “A highly related semantic localization task is object detection (DET), which seeks to detect all objects from a predefined set of classes without text inputs [60,71,77,80,18,68].”
Integral histogram: a fast way to extract histograms in Cartesian spaces (2005, background): “Histograms are among the most common features used in many computer vision tasks from object based retrieval [1], [2], to segmentation [3], [5] to detection [4], [6] to tracking [7].”
A statistical approach to 3d object detection applied to faces and cars (2000, methodology): “est operator” or some other automatic method to select a small set of features to use [81][39][ 82 ].”
Detecting Pedestrians Using Patterns of Motion and Appearance (2003, unknown): “al [9].”
Automatic detection of microaneurysms in color fundus images (2007, background): “As for large window sizes, this operator would be very slow, it is advantageous to make use of integral images (Papageorgiou et al., 1998; Viola and Jones, 2004).”
Moving Object Detection by Detecting Contiguous Outliers in the Low-Rank Representation (2011, methodology): “Generally, the classiﬁer is built by ofﬂine learning on separate datasets [3], [4] or by online learning initialized with a manually labeled frame at the start of a video [5], [6].”
Robust Real-Time Face Detection (2001, unknown): “For a similar recognition problem Papageorgiou et al. (1998) proposed a scheme for feature selection based on feature variance.”
Supervised classification and mathematical optimization (2013, background): “…of gene expression data [102] [245], homology detection [143], protein-protein interaction prediction [28] [171], abnormal brain activity classification [55] and cancer diagnosis [110] [165]; Machine Vision [75] [188]; Agriculture [179]; or Chemistry [60], to cite a few fields and references.”
An extended set of Haar-like features for rapid object detection (2002, methodology): “Not used, but used in [3,2,4] (a) (b) (c) (d)”
A Fast and Accurate Face Detector Based on Neural Networks (2001, methodology): “This model can be built with different methods: neural networks [6], [38], [12], [33], [20], [36], [29], [30], [13], [14], principal components analysis [35], [11], [15], [17], [18], [26], Kullback distance and maximum-likelihood method [10], Support Vector Machines [27], [ 28 ], etc.”
Support vector machines: hype or hallelujah? (2000, background): “3D object recognition [47] is another successful area of application including 3D face recognition, pedestrian recognition [44], etc.”
Joint Haar-like features for face detection (2005, methodology): “Instead, Papageorgiou et al. [6] used Haar-like features, which are similar to Haar basis functions.”
Robust Real-time Object Detection (2001, methodology): “The simple features used are reminiscent of Haar basis functions which have been used by Papageorgiou et al. [8].”
A comprehensive survey of recent trends in deep learning for digital images augmentation (2021, background): “DL is the secret to computer vision (Ponce and Forsyth 2012), image classifications, object recognition (Papageorgiou et al. 1998), image segmentation (Pal and Pal 1993), and more.”
FloatBoost learning and statistical face detection (2004, methodology): “A coarse-to-fine view-partition strategy is used and this leads to a detector-pyramid architecture consisting of several levels from the coarse level on the top to the fine level at the bottom.”