activity
20212024
most citedStackMix and Blot Augmentations for Handwritten Text Recognition

12 citations · 19 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG2024

Additive regularization schedule for neural architecture search

Mark Potanin, Kirill Vayser, Vadim Strijov

Neural network structures have a critical impact on the accuracy and stability of forecasting. Neural architecture search procedures help design an optimal neural network according…

cs.LG2023★ 4 cited

Startup success prediction and VC portfolio simulation using CrunchBase data

Mark Potanin, Andrey Chertok, Konstantin Zorin +1

Predicting startup success presents a formidable challenge due to the inherently volatile landscape of the entrepreneurial ecosystem. The advent of extensive databases like Crunchb…

cs.CV2021

Handwritten text generation and strikethrough characters augmentation

Alex Shonenkov, Denis Karachev, Max Novopoltsev +3

We introduce two data augmentation techniques, which, used with a Resnet-BiLSTM-CTC network, significantly reduce Word Error Rate (WER) and Character Error Rate (CER) beyond best-r…

cs.CV2021

Many Heads but One Brain: Fusion Brain -- a Competition and a Single Multimodal Multitask Architecture

Daria Bakshandaeva, Denis Dimitrov, Vladimir Arkhipkin +8

Supporting the current trend in the AI community, we present the AI Journey 2021 Challenge called Fusion Brain, the first competition which is targeted to make the universal archit…

cs.CV2021★ 12 cited

StackMix and Blot Augmentations for Handwritten Text Recognition

Alex Shonenkov, Denis Karachev, Maxim Novopoltsev +2

This paper proposes a handwritten text recognition(HTR) system that outperforms current state-of-the-artmethods. The comparison was carried out on three of themost frequently used…

cs.CV2021★ 3 cited

Digital Peter: Dataset, Competition and Handwriting Recognition Methods

Mark Potanin, Denis Dimitrov, Alex Shonenkov +3

This paper presents a new dataset of Peter the Great's manuscripts and describes a segmentation procedure that converts initial images of documents into the lines. The new dataset…