Výsledky vyhľadávania - computer learning and pattern recognition::text/(document OR document) processing

PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks Autor Yu, Wenwen, Lu, Ning, Qi, Xianbiao, Gong, Ping, Xiao, Rong

“…Computer vision with state-of-the-art deep learning models has achieved huge success in the field of Optical Character Recognition (OCR…”
Získať plný text

Robust text line detection in historical documents: learning and evaluation methods Autor Boillet, Mélodie, Kermorvant, Christopher, Paquet, Thierry

“…Text line segmentation is one of the key steps in historical document understanding…”
Získať plný text

Hate speech recognition in multilingual text: hinglish documents Autor Yadav, Arun Kumar, Kumar, Mohit, Kumar, Abhishek, Shivani, Kusum, Yadav, Divakar

“… Sometimes users wield abusive or inflammatory language, that may provoke readers. This paper aims to evaluate various machine learning and deep learning techniques to detect hate speech on various social media platforms in the Hinglish…”
Získať plný text

Document-level sentiment classification: An empirical comparison between SVM and ANN Autor Moraes, Rodrigo, Valiati, João Francisco, Gavião Neto, Wilson P.

“…► SVM have been extensively and successfully used as a sentiment learning approach…”
Získať plný text

Deformity removal from handwritten text documents using variable cycle GAN Autor Nigam, Shivangi, Behera, Adarsh Prasad, Verma, Shekhar, Nagabhushan, P.

“…Text recognition systems typically work well for printed documents but struggle with handwritten documents due to different writing styles, background complexities, added noise of image acquisition…”
Získať plný text

Metric learning for text documents Autor Lebanon, G.

“…Many algorithms in machine learning rely on being given a good distance metric over the input space…”
Získať plný text

Evaluation of algorithms for Multi-Modality Whole Heart Segmentation: An open-access grand challenge Autor Zhuang, Xiahai, Li, Lei, Payer, Christian, Štern, Darko, Urschler, Martin, Heinrich, Mattias P., Oster, Julien, Wang, Chunliang, Smedby, Örjan, Bian, Cheng, Yang, Xin, Heng, Pheng-Ann, Mortazi, Aliasghar, Bagci, Ulas, Yang, Guanyu, Sun, Chenchen, Galisot, Gaetan, Ramel, Jean-Yves, Brouard, Thierry, Tong, Qianqian, Si, Weixin, Liao, Xiangyun, Zeng, Guodong, Shi, Zenglin, Zheng, Guoyan, Wang, Chengjia, MacGillivray, Tom, Newby, David, Rhode, Kawal, Ourselin, Sebastien, Mohiaddin, Raad, Keegan, Jennifer, Firmin, David, Yang, Guang

“…) challenge, in conjunction with MICCAI 2017.•This work introduces the related information to the challenge, discusses the results from the conventional methods and deep learning-based algorithms, and provides insights to the future research…”
Získať plný text

DANIEL: A fast Document Attention Network for Information Extraction and Labelling of handwritten documents Autor Constum, Thomas, Tranouez, Pierrick, Paquet, Thierry

“…: Document Layout Analysis, Handwritten Text Recognition, and Named Entity Recognition. Recent approaches have attempted to integrate these steps into a single process using fully end-to-end architectures…”
Získať plný text

A segmentation-free method for image retrieval and pattern spotting in historical documents using convolutional features Autor Curi, Zacarias, Nicolas, Stéphane, Tranouez, Pierrick, M. Saavedra, Jose, de Souza Britto Jr, Alceu, Heutte, Laurent

“…This paper describes a new segmentation-free method for retrieving images and spotting patterns in historical document image collections…”
Získať plný text

I2DFormer+: Learning Image to Document Summary Attention for Zero-Shot Image Classification Autor Naeem, Muhammad Ferjad, Xian, Yongqin, Gool, Luc Van, Tombari, Federico

“…Despite the tremendous progress in zero-shot learning (ZSL), the majority of existing methods still rely on human-annotated attributes, which are difficult to annotate and scale…”
Získať plný text

Multiple Document Datasets Pre-training Improves Text Line Detection With Deep Neural Networks Autor Boillet, Melodie, Kermorvant, Christopher, Paquet, Thierry

“…In this paper, we introduce a fully convolutional network for the document layout analysis task…”
Získať plný text

ROBDD-TrOCRBERTa: a novel robust-optimized blurred document text deblurring and completion with DCGAN-TrOCR and DistilRoBERTa Autor Ranjan, Arti, Ravinder, M.

“… because the quality of the text has deteriorated over time. The proposed Robust Optimized Blurred Document Text Deblurring and Text Recognition (ROBDD-TrOCRBERTa…”
Získať plný text

Contribution of recurrent connectionist language models in improving LSTM-based Arabic text recognition in videos Autor Yousfi, Sonia, Berrani, Sid-Ahmed, Garcia, Christophe

“…Unconstrained text recognition in videos is a very challenging task that begins to draw the attention of the OCR community…”
Získať plný text

Large text document summarization based on an enhanced fuzzy logic approach Autor Yadav, Avaneesh Kumar, Ranvijay, Ranvijay, Yadav, Rama Shankar, Kumar, Vivek

“… looking for. In this paper, we propose an extractive text summarization approach that utilizes fuzzy logic to determine the relevance and importance of sentences in a multi-document such as legal documents, news…”
Získať plný text

An end-to-end pipeline for historical censuses processing Autor Petitpierre, Rémi, Kramer, Marion, Rappo, Lucas

“…Censuses are structured documents of great value for social and demographic history, which became widespread from the nineteenth century…”
Získať plný text

EAML: ensemble self-attention-based mutual learning network for document image classification Autor Bakkali, Souhail, Ming, Zuheng, Coustaty, Mickaël, Rusiñol, Marçal

“… As many document types have a distinct visual style, learning only visual features with deep CNNs to classify document images has encountered the problem of low inter-class discrimination, and high…”
Získať plný text

A survey of historical document image datasets Autor Nikolaidou, Konstantina, Seuret, Mathias, Mokayed, Hamam, Liwicki, Marcus

“… Finding appropriate datasets for historical document analysis is a crucial prerequisite to facilitate research using different machine learning algorithms…”
Získať plný text

Learning to detect, localize and recognize many text objects in document images from few examples Autor Moysset, Bastien, Kermorvant, Christopher, Wolf, Christian

“… In this work, we particularly target the detection of text in document images and we propose a new neural model which directly predicts object coordinates…”
Získať plný text

In-domain versus out-of-domain transfer learning for document layout analysis: In-domain versus out-of-domain transfer learning Autor De Nardin, Axel, Zottin, Silvia, Piciarelli, Claudio, Foresti, Gian Luca, Colombi, Emanuela

“… on which to train deep learning models. A notable example is represented by the task of document layout analysis in handwritten documents, which requires pixel-precise…”
Získať plný text

Editorial for special issue on “advanced topics in document analysis and recognition” Autor Barney Smith, Elisa H., Liwicki, Marcus, Peng, Liangrui, Marinai, Simone

“…Where once OCR on machine printed Latin isolated characters was the main focus of document analysis research, topics of interest have developed to the point that recognition of handwritten text (HTR…”
Získať plný text