Results 11 to 20 of about 361,179 (336)
Receptive Field Structures for Recognition [PDF]
Neural Computation, 2006 Localized operators, like Gabor wavelets and difference-of-gaussian filters, are considered useful tools for image representation. This is due to their ability to form a sparse code that can serve as a basis set for high-fidelity reconstruction of natural images.
Pawan Sinha, Benjamin Balas
openaire +3 more sources
Structured Receptive Fields in CNNs [PDF]
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016 Reason for update: i) Fix Reference for "Deep roto-translation scattering for object classification" by Oyallon and Mallat. ii) Fixed two minor typos. iii) Removed implicit assumption in equation (4) where scale is represented with diffusion time and adapted to rest of paper where scale is represented with standard deviation, to avoid possible ...
Jacobsen, J.-H. +3 more
openaire +4 more sources
Multi-Scale Receptive Field Detection Network
IEEE Access, 2019 Deep convolutional neural networks have contributed much to various computer vision problems including object detection. However, there are still many problems to be solved.
Haoren Cui, Zhihua Wei
doaj +1 more source
Perisaccadic remapping and rescaling of visual responses in macaque superior colliculus. [PDF]
PLoS ONE, 2012 Visual neurons have spatial receptive fields that encode the positions of objects relative to the fovea. Because foveate animals execute frequent saccadic eye movements, this position information is constantly changing, even though the visual world is ...
Jan Churan +2 more
doaj +1 more source
Shifting Receptive Fields [PDF]
Neuron, 2001 The very notion of a receptive field implies a defined, static region of sensitivity—for visual neurons, a region in retinotopic space. Other factors besides retinal stimulation (such as attentional state) may modulate neural responses, but the shape and position of the receptive field should remain fixed, permanently constrained by anatomical ...
openaire +3 more sources
Auto-Selecting Receptive Field Network for Visual Tracking
IEEE Access, 2019 Recently, Convolutional Neural Networks (CNNs) have shown tremendous potential in the visual tracking community. It is well-known that the receptive field is a critical factor for CNN affecting performance.
Junfei Zhuang +4 more
doaj +1 more source
Dilated Deep Residual Network for Image Denoising [PDF]
, 2017 Variations of deep neural networks such as convolutional neural network (CNN) have been successfully applied to image denoising. The goal is to automatically learn a mapping from a noisy image to a clean image given training data consisting of pairs of ...
Hu, Kaoning +2 more
core +3 more sources
Transformable Dilated Convolution by Distance for LiDAR Semantic Segmentation
IEEE Access, 2022 LiDAR semantic segmentation is essential in autonomous vehicle safety. A rotating 3D LiDAR projects more laser points onto nearby objects and fewer points onto farther objects.
Jae-Seol Lee, Tae-Hyoung Park
doaj +1 more source
Information Optimization in Coupled Audio-Visual Cortical Maps [PDF]
, 2002 Barn owls hunt in the dark by using cues from both sight and sound to locate their prey. This task is facilitated by topographic maps of the external space formed by neurons (e.g., in the optic tectum) that respond to visual or aural signals from a ...
A. Zee +10 more
core +3 more sources
Mapping sequences can bias population receptive field estimates
NeuroImage, 2020 Population receptive field (pRF) modelling is a common technique for estimating the stimulus-selectivity of populations of neurons using neuroimaging. Here, we aimed to address if pRF properties estimated with this method depend on the spatio-temporal ...
Elisa Infanti, D. Samuel Schwarzkopf
doaj +1 more source