Search Results for author: Pavel Král

Found 11 papers, 3 papers with code

Linear Transformations for Cross-lingual Sentiment Analysis

1 code implementation15 Sep 2022 Pavel Přibáň, Jakub Šmíd, Adam Mištera, Pavel Král

This paper deals with cross-lingual sentiment analysis in Czech, English and French languages.

Classification Sentiment Analysis

ICDAR 2021 Competition on Historical Map Segmentation

1 code implementation27 May 2021 Joseph Chazalon, Edwin Carlinet, Yizi Chen, Julien Perret, Bertrand Duménieu, Clément Mallet, Thierry Géraud, Vincent Nguyen, Nam Nguyen, Josef Baloun, Ladislav Lenc, Pavel Král

Task~2 consists in segmenting map content from the larger map sheet, and was won by the UWB team using a U-Net-like FCN combined with a binarization method to increase detection edge accuracy.

Contour Detection Document Layout Analysis +4

Re-ranking for Writer Identification and Writer Retrieval

no code implementations14 Jul 2020 Simon Jordan, Mathias Seuret, Pavel Král, Ladislav Lenc, Jiří Martínek, Barbara Wiermann, Tobias Schwinger, Andreas Maier, Vincent Christlein

We show that a re-ranking step based on k-reciprocal nearest neighbor relationships is advantageous for writer identification, even if only a few samples per writer are available.

Re-Ranking Retrieval

Cross-lingual Approaches for Task-specific Dialogue Act Recognition

no code implementations19 May 2020 Jiří Martínek, Christophe Cerisara, Pavel Král, Ladislav Lenc

In this paper we exploit cross-lingual models to enable dialogue act recognition for specific tasks with a small number of annotations.

Cross-Lingual Transfer Transfer Learning

Deep Generalized Max Pooling

1 code implementation14 Aug 2019 Vincent Christlein, Lukas Spranger, Mathias Seuret, Anguelos Nicolaou, Pavel Král, Andreas Maier

Global pooling layers are an essential part of Convolutional Neural Networks (CNN).

Czech Text Document Corpus v 2.0

no code implementations LREC 2018 Pavel Král, Ladislav Lenc

This paper introduces "Czech Text Document Corpus v 2. 0", a collection of text documents for automatic document classification in Czech language.

Classification Document Classification +1

Enhanced Local Binary Patterns for Automatic Face Recognition

no code implementations10 Feb 2017 Pavel Král, Ladislav Lenc, Antonín Vrba

This descriptor considers a local neighbourhood of a pixel to compute the feature vector values.

Face Recognition

Deep Neural Networks for Czech Multi-label Document Classification

no code implementations13 Jan 2017 Ladislav Lenc, Pavel Král

This paper is focused on automatic multi-label document classification of Czech text documents.

Classification Document Classification +1

Unsupervised Dialogue Act Induction using Gaussian Mixtures

no code implementations20 Dec 2016 Tomáš Brychcín, Pavel Král

This paper introduces a new unsupervised approach for dialogue act induction.

Cannot find the paper you are looking for? You can Submit a new open access paper.