activity
20182022
most citedAdvanced Hough-based method for on-device document localization

15 citations · 38 across the 8 of their papers we have counts for

collaborators

17 papers

cs.LG20222 cited

Fast matrix multiplication for binary and ternary CNNs on ARM CPU

Anton Trusov, Elena Limonova, Dmitry Nikolaev +1

Low-bit quantized neural networks are of great interest in practical applications because they significantly reduce the consumption of both memory and computational resources. Bina…

cs.CV202115 cited

Advanced Hough-based method for on-device document localization

D. V. Tropin, A. M. Ershov, D. P. Nikolaev +1

The demand for on-device document recognition systems increases in conjunction with the emergence of more strict privacy and security requirements. In such systems, there is no dat…

cs.CV20211 cited

ProLab: perceptually uniform projective colour coordinate system

Ivan A. Konovalenko, Anna A. Smagina, Dmitry P. Nikolaev +1

In this work, we propose proLab: a new colour coordinate system derived as a 3D projective transformation of CIE XYZ. We show that proLab is far ahead of the widely used CIELAB coo…

cs.CV20201 cited

Illumination Estimation Challenge: experience of past two years

Egor Ershov, Alex Savchik, Ilya Semenkov +15

Illumination estimation is the essential step of computational color constancy, one of the core parts of various image processing pipelines of modern digital cameras. Having an acc…

cs.CV2020

ResNet-like Architecture with Low Hardware Requirements

Elena Limonova, Daniil Alfonso, Dmitry Nikolaev +1

One of the most computationally intensive parts in modern recognition systems is an inference of deep neural networks that are used for image classification, segmentation, enhancem…

cs.CV2020

Fast Implementation of 4-bit Convolutional Neural Networks for Mobile Devices

Anton Trusov, Elena Limonova, Dmitry Slugin +2

Quantized low-precision neural networks are very popular because they require less computational resources for inference and can provide high performance, which is vital for real-t…