Results 11 to 20 of about 18,554 (48)
Towards dense object tracking in a 2D honeybee hive
, 2017 From human crowds to cells in tissue, the detection and efficient tracking of multiple objects in dense configurations is an important and unsolved problem.
Bozek, Katarzyna +3 more
core +2 more sources
Language Models for Image Captioning: The Quirks and What Works [PDF]
, 2015 Two recent approaches have achieved state-of-the-art results in image captioning. The first uses a pipelined process where a set of candidate words is generated by a convolutional neural network (CNN) trained on images, and then a maximum entropy (ME ...
Cheng, Hao +7 more
core +1 more source
U-Net: Convolutional Networks for Biomedical Image Segmentation
, 2015 There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available ...
Brox, Thomas +2 more
core +1 more source
Deep learning architectures for Computer Vision [PDF]
, 2016 Deep learning has become part of many state-of-the-art systems in multiple disciplines (specially in computer vision and speech processing). In this thesis Convolutional Neural Networks are used to solve the problem of recognizing people in images, both ...
Roig Marí, Carlos
core
DPC-Net: Deep Pose Correction for Visual Localization
, 2018 We present a novel method to fuse the power of deep networks with the computational efficiency of geometric and probabilistic localization algorithms. In contrast to other methods that completely replace a classical visual estimator with a deep network ...
Kelly, Jonathan, Peretroukhin, Valentin
core +1 more source
, 2009 (ABRIDGED) In previous work, two platforms have been developed for testing computer-vision algorithms for robotic planetary exploration (McGuire et al. 2004b,2005; Bartolo et al. 2007).
A. Bonnici +21 more
core +1 more source
Dipole and Quadrupole Moments in Image Processing [PDF]
, 2009 This paper proposes an algorithm for image processing, obtained by adapting to image maps the definitions of two well-known physical quantities. These quantities are the dipole and quadrupole moments of a charge distribution.
Sparavigna, Amelia
core +1 more source
Image Restoration using Total Variation Regularized Deep Image Prior
, 2018 In the past decade, sparsity-driven regularization has led to significant improvements in image reconstruction. Traditional regularizers, such as total variation (TV), rely on analytical models of sparsity.
Kamilov, Ulugbek S. +3 more
core +1 more source
Unsupervised feature learning by augmenting single images [PDF]
, 2014 When deep learning is applied to visual object recognition, data augmentation is often used to generate additional training data without extra labeling cost. It helps to reduce overfitting and increase the performance of the algorithm.
Brox, Thomas +2 more
core
Efficient and accurate inversion of multiple scattering with deep learning
, 2018 Image reconstruction under multiple light scattering is crucial in a number of applications such as diffraction tomography. The reconstruction problem is often formulated as a nonconvex optimization, where a nonlinear measurement model is used to account
Kamilov, Ulugbek S. +2 more
core +1 more source