Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Shonenkov, Alex"'
Autor:
Shonenkov, Alex, Kuznetsov, Andrey, Dimitrov, Denis, Shavrina, Tatyana, Chesakov, Daniil, Maltseva, Anastasia, Fenogenova, Alena, Pavlov, Igor, Emelyanov, Anton, Markov, Sergey, Bakshandaeva, Daria, Shybaeva, Vera, Chertok, Andrey
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-MT) on 16 datasets from different domains. Our best implementations ou
Externí odkaz:
http://arxiv.org/abs/2202.10784
Autor:
Novikov, Georgii, Bershatsky, Daniel, Gusak, Julia, Shonenkov, Alex, Dimitrov, Denis, Oseledets, Ivan
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 graph. Every modern neural network model has quite a few pointwise nonline
Externí odkaz:
http://arxiv.org/abs/2202.00441
Autor:
Shonenkov, Alex, Karachev, Denis, Novopoltsev, Max, Potanin, Mark, Dimitrov, Denis, Chertok, Andrey
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-reported results on handwriting text recognition (HTR) tasks. We apply
Externí odkaz:
http://arxiv.org/abs/2112.07395
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 ability of a pretrained big model ruDALL-E Malevich (XL) 1.3B parameter
Externí odkaz:
http://arxiv.org/abs/2112.02448
Autor:
Bakshandaeva, Daria, Dimitrov, Denis, Arkhipkin, Vladimir, Shonenkov, Alex, Potanin, Mark, Karachev, Denis, Kuznetsov, Andrey, Voronov, Anton, Davydova, Vera, Tutubalina, Elena, Petiushko, Aleksandr
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 architecture which could process different modalities (in this case, images,
Externí odkaz:
http://arxiv.org/abs/2111.10974
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 in HTR task datasets, namely Ben-tham, IAM, and Saint Gall. In additio
Externí odkaz:
http://arxiv.org/abs/2108.11667
Autor:
Potanin, Mark, Dimitrov, Denis, Shonenkov, Alex, Bataev, Vladimir, Karachev, Denis, Novopoltsev, Maxim
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 may be useful for researchers to train handwriting text recognition mo
Externí odkaz:
http://arxiv.org/abs/2103.09354
Autor:
Karachev Denis, Chertok Andrey, Novopoltsev Maxim, Potanin Mark, Dimitrov Denis, Shonenkov Alex, Bataev Vladimir
Publikováno v:
HIP@ICDAR
This paper presents a new dataset of Peter the Great’s manuscripts and describes a segmentation procedure that converts initial images of documents into lines. This new dataset may be useful for researchers to train handwriting text recognition mod
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a4d862e590805791cf9f1c55c6137e05
https://doi.org/10.1145/3476887.3476892
https://doi.org/10.1145/3476887.3476892
