12 citations · 35 across the 10 of their papers we have counts for
12 papers
RusTitW: Russian Language Text Dataset for Visual Text in-the-Wild Recognition
Igor Markov, Sergey Nesteruk, Andrey Kuznetsov +1
Information surrounds people in modern life. Text is a very efficient type of information that people use for communication for centuries. However, automated text-in-the-wild recog…
RuCLIP -- new models and experiments: a technical report
Alex Shonenkov, Andrey Kuznetsov, Denis Dimitrov +10
In the report we propose six new implementations of ruCLIP model trained on our 240M pairs. The accuracy results are compared with original CLIP model with Ru-En translation (OPUS-…
Survey on Large Scale Neural Network Training
Julia Gusak, Daria Cherniuk, Alena Shilova +8
Modern Deep Neural Networks (DNNs) require significant memory to store weight, activations, and other intermediate tensors during training. Hence, many models do not fit one GPU de…
A new face swap method for image and video domains: a technical report
Daniil Chesakov, Anastasia Maltseva, Alexander Groshev +2
Deep fake technology became a hot field of research in the last few years. Researchers investigate sophisticated Generative Adversarial Networks (GAN), autoencoders, and other appr…
Few-Bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction
Georgii Novikov, Daniel Bershatsky, Julia Gusak +3
Memory footprint is one of the main limiting factors for large neural network training. In backpropagation, one needs to store the input to each operation in the computational grap…
Emojich -- zero-shot emoji generation using Russian language: a technical report
Alex Shonenkov, Daria Bakshandaeva, Denis Dimitrov +1
This technical report presents a text-to-image neural network "Emojich" that generates emojis using captions in Russian language as a condition. We aim to keep the generalization a…
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…
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…
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…
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…
Statistical estimation of the Kullback-Leibler divergence
Alexander Bulinski, Denis Dimitrov
Wide conditions are provided to guarantee asymptotic unbiasedness and L^2-consistency of the introduced estimates of the Kullback-Leibler divergence for probability measures in R^d…
Statistical estimation of the Shannon entropy
Alexander Bulinski, Denis Dimitrov
The behavior of the Kozachenko - Leonenko estimates for the (differential) Shannon entropy is studied when the number of i.i.d. vector-valued observations tends to infinity. The as…