Human Face Detection in Visual Scenes

By Henry A. Rowley, Shumeet Baluja, Takeo Kanade. 1995

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

Network In Network (2013, background): “However, they are both designed for specific problems and both contain only one layer of the sliding network structure.”
Rethinking ImageNet Pre-Training (2018, background): “, [31, 38, 45])—a fact that is somewhat overlooked today.”
Measuring Robustness to Natural Distribution Shifts in Image Classification (2020, methodology): “In the context of training sets, adversarial filtering is similar to hard negative mining, which is often used to generate training data for detection models [17, 30, 69, 83].”
Feature Pyramid Networks for Object Detection (2016, background): “Before HOG and SIFT, early work on face detection with ConvNets [38, 32] computed shallow networks over image pyramids to detect faces across scales.”
Focal Loss for Dense Object Detection (2017, background): “ping [17], [18] or hard examplemining [16], [19], [20].”
Finding Pictures of Objects in Large Collections of Images (1996, methodology): “The main features on a human face appear in much the same form in most images, enabling techniques based on principal component analysis or neural networks proposed by, for example, Pentland et al. (1994), Sung and Poggio (1994), Rowley et al. (1996), and Burel and Carel (1994).”
Face recognition: a convolutional neural-network approach (1997, background): “as described in [37], each of the input planes to the convolutional network was divided into 2 2 segments (the input planes are 23 28).”
Emergence of categorical face perception after extended early-onset blindness (2017, methodology): “One hundred eighty false-alarm images were selected using the Pittsburgh Pattern Recognition face-detection algorithm (43).”
LabelMe: Online Image Annotation and Applications (2010, unknown): “D”
Aligning 3D models to RGB-D images of cluttered scenes (2015, background): “A large body of work in computer vision has focused on the problem of object detection, where the ﬁnal output is a bounding box around the object, [6, 7, 8, 26, 39].”
Detecting Faces in Images: A Survey (2002, background): “On a small test set of 42 images, they report a detection rate similar to [126].”
Imbalance Problems in Object Detection: A Review (2019, background): “– Bootstraping [55] – SSD [19] – Online Hard Example Mining [24] – IoU-based Sampling [29]”
Inferring 3D Object Pose in RGB-D Images (2015, background): “A large body of work in computer vision has focused on the problem of object detection, where the final output is a bounding box around the object, overlapping with the actual extent of the object by more than 50% [7, 37, 6, 8, 25].”
Focal Loss for Dense Object Detection (2017, methodology): “This inefficiency is a classic problem in object detection that is typically addressed via techniques such as bootstrapping [32, 28] or hard example mining [36, 8, 30].”
A Fast and Accurate Face Detector Based on Neural Networks (2001, methodology): “The use of ensemble of networks to reduce the false alarm rate was shown in [ 29 ].”
Efficient Subwindow Search: A Branch and Bound Framework for Object Localization (2009, unknown): “In the field of object localization with bounding boxes, sliding window approaches have been the method of choice for many years [8], [9], [10], [11], [12].”
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].”