Original approach for the localisation of objects in images

By Régis Vaillant, C. Monrocq, Y. L. Cun. 1994

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

Fast R-CNN (2015, background): “The batch size and number of RoIs can change dynamically from batch to batch, as can the resolution of the input images: all conv layers reshape on-the-ﬂy in proportion to the input resolution [21].”
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks (2013, background): “Many authors have proposed to use ConvNets for detection and localization with a sliding window over multiple scales, going back to the early 1990’s for mult i-character strings [20], faces [30], and hands [22].”
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation (2013, methodology): “To adapt our CNN to the new task (detection) and the new domain (warped proposal windows), we continue stochastic gradient descent (SGD) training of the CNN parameters using only warped region proposals.”
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.”
Panoptic Segmentation (2018, neutral): “, [44, 46]) helped popularize bounding-box object detection.”
Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks (2015, methodology): “ConvNets with a small number of hidden layers have been used for object detection for the last two decades (e.g., from [39] to [34]).”
Deformable part models are convolutional neural networks (2014, methodology): “In the context of CNNs, this method dates back to (at least) early work on face detection in [31], and has been used in contemporary work including OverFeat [28], DetectorNet [3], and DenseNet [19].”
Focal Loss for Dense Object Detection (2017, neutral): “who applied convolutional neural networks to handwritten digit recognition [22], [23].”
Deep learning in neural networks: An overview (2014, methodology): “, 2013); compare earlier efficient methods for CNNs without MP (Vaillant et al., 1994).”
Recent advances in convolutional neural networks (2015, methodology): “In some early works [116], [118], [127], they use the sliding window based approaches to”
A ConvNet for the 2020s (2022, background): “For many decades, this has been the default use of ConvNets, generally on limited object categories such as digits [43], faces [58, 76] and pedestrians [19, 63].”
DenseBox: Unifying Landmark Localization with End to End Object Detection (2015, background): “Applying neural networks for face detection has a long history, and the early works date back to 1990s[38].”
DenseNet: Implementing Efficient ConvNet Descriptor Pyramids (2014, neutral): “densely computed CNNs on full images for robust face localization [19].”
Convolutional networks and applications in vision (2010, methodology): “Supervised ConvNets have also been used for object detection in images, including faces with record accuracy and real-time performance [14], [15], [16], [17], Google recently deployed a ConvNet to detect”
Object Recognition with Gradient-Based Learning (1999, methodology): “The idea has been applied to face location, [ 30 ], address block location on envelopes [33], and hand tracking in video [24].”
Large-scale Learning with SVM and Convolutional for Generic Object Categorization (2006, methodology): “Learning-based methods operating on raw pixels or lowlevel local features have been quite successful for such applications as face detection [31, 24, 33, 27].”
Focal Loss for Dense Object Detection (2017, methodology): “who applied convolutional neural networks to handwritten digit recognition [18, 35].”