Search Results for author: Marcus Liwicki

Found 81 papers, 38 papers with code

Giving each task what it needs -- leveraging structured sparsity for tailored multi-task learning

1 code implementation5 Jun 2024 Richa Upadhyay, Ronald Phlypo, Rajkumar Saini, Marcus Liwicki

A detailed performance analysis of the LOMT models, in contrast to the conventional MTL models, reveals that the LOMT models outperform for most task combinations.

feature selection Multi-Task Learning

Möbius Transform for Mitigating Perspective Distortions in Representation Learning

no code implementations7 Mar 2024 Prakash Chandra Chhipa, Meenakshi Subhash Chippa, Kanjar De, Rajkumar Saini, Marcus Liwicki, Mubarak Shah

In this work, we propose mitigating perspective distortion (MPD) by employing a fine-grained parameter control on a specific family of M\"obius transform to model real-world distortion without estimating camera intrinsic and extrinsic parameters and without the need for actual distorted data.

Crowd Counting object-detection +3

Less is More -- Towards parsimonious multi-task models using structured sparsity

1 code implementation23 Aug 2023 Richa Upadhyay, Ronald Phlypo, Rajkumar Saini, Marcus Liwicki

In this work, we introduce channel-wise l1/l2 group sparsity in the shared convolutional layers parameters (or weights) of the multi-task learning model.

L2 Regularization Multi-Task Learning

ReLU and Addition-based Gated RNN

no code implementations10 Aug 2023 Rickard Brännvall, Henrik Forsgren, Fredrik Sandin, Marcus Liwicki

It is demonstrated that the novel gating mechanism can capture long-term dependencies for a standard synthetic sequence learning task while significantly reducing computational costs such that execution time is reduced by half on CPU and by one-third under encryption.

Handwritten Text Recognition Privacy Preserving +1

Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Images

no code implementations23 Jun 2023 Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Marcus Liwicki, Muhammad Zeshan Afzal

Upon integrating query modifications in the DETR, we outperform prior works and achieve new state-of-the-art results with the mAP of 96. 9\%, 95. 7\% and 99. 3\% on TableBank, PubLaynet, PubTables, respectively.

Document Layout Analysis Object +2

Robust and Fast Vehicle Detection using Augmented Confidence Map

no code implementations27 Apr 2023 Hamam Mokayed, Palaiahnakote Shivakumara, Lama Alkhaled, Rajkumar Saini, Muhammad Zeshan Afzal, Yan Chai Hum, Marcus Liwicki

Vehicle detection in real-time scenarios is challenging because of the time constraints and the presence of multiple types of vehicles with different speeds, shapes, structures, etc.

Fast Vehicle Detection

Learning Self-Supervised Representations for Label Efficient Cross-Domain Knowledge Transfer on Diabetic Retinopathy Fundus Images

1 code implementation20 Apr 2023 Ekta Gupta, Varun Gupta, Muskaan Chopra, Prakash Chandra Chhipa, Marcus Liwicki

Most of the existing DR image classification methods are based on supervised learning which requires a lot of time-consuming and expensive medical domain experts-annotated data for training.

Classification Contrastive Learning +4

Domain Adaptable Self-supervised Representation Learning on Remote Sensing Satellite Imagery

1 code implementation19 Apr 2023 Muskaan Chopra, Prakash Chandra Chhipa, Gopal Mengi, Varun Gupta, Marcus Liwicki

The proposed approach investigates the knowledge transfer of selfsupervised representations across the distinct source and target data distributions in depth in the remote sensing data domain.

Contrastive Learning Domain Adaptation +2

Deep Perceptual Similarity is Adaptable to Ambiguous Contexts

1 code implementation5 Apr 2023 Gustav Grund Pihlgren, Fredrik Sandin, Marcus Liwicki

The concept of image similarity is ambiguous, and images can be similar in one context and not in another.

WordStylist: Styled Verbatim Handwritten Text Generation with Latent Diffusion Models

1 code implementation29 Mar 2023 Konstantina Nikolaidou, George Retsinas, Vincent Christlein, Mathias Seuret, Giorgos Sfikas, Elisa Barney Smith, Hamam Mokayed, Marcus Liwicki

Our proposed method is able to generate realistic word image samples from different writer styles, by using class index styles and text content prompts without the need of adversarial training, writer recognition, or text recognition.

 Ranked #1 on HTR on IAM

Data Augmentation Denoising +5

Lon-ea at SemEval-2023 Task 11: A Comparison of Activation Functions for Soft and Hard Label Prediction

1 code implementation4 Mar 2023 Peyman Hosseini, Mehran Hosseini, Sana Sabah Al-Azzawi, Marcus Liwicki, Ignacio Castro, Matthew Purver

We study the influence of different activation functions in the output layer of deep neural network models for soft and hard label prediction in the learning with disagreement task.

A Systematic Performance Analysis of Deep Perceptual Loss Networks: Breaking Transfer Learning Conventions

1 code implementation8 Feb 2023 Gustav Grund Pihlgren, Konstantina Nikolaidou, Prakash Chandra Chhipa, Nosheen Abid, Rajkumar Saini, Fredrik Sandin, Marcus Liwicki

In recent years, deep perceptual loss has been widely and successfully used to train machine learning models for many computer vision tasks, including image synthesis, segmentation, and autoencoding.

Depth Estimation Depth Prediction +6

Bipol: Multi-axes Evaluation of Bias with Explainability in Benchmark Datasets

2 code implementations28 Jan 2023 Tosin Adewumi, Isabella Södergren, Lama Alkhaled, Sana Sabah Sabry, Foteini Liwicki, Marcus Liwicki

Hence, we also contribute a new, large Swedish bias-labelled dataset (of 2 million samples), translated from the English version and train the SotA mT5 model on it.

Bias Detection Natural Language Inference +1

Depth Contrast: Self-Supervised Pretraining on 3DPM Images for Mining Material Classification

1 code implementation18 Oct 2022 Prakash Chandra Chhipa, Richa Upadhyay, Rajkumar Saini, Lars Lindqvist, Richard Nordenskjold, Seiichi Uchida, Marcus Liwicki

This work presents a novel self-supervised representation learning method to learn efficient representations without labels on images from a 3DPM sensor (3-Dimensional Particle Measurement; estimates the particle size distribution of material) utilizing RGB images and depth maps of mining material on the conveyor belt.

Linear evaluation Material Classification +3

Multi-Task Meta Learning: learn how to adapt to unseen tasks

1 code implementation13 Oct 2022 Richa Upadhyay, Prakash Chandra Chhipa, Ronald Phlypo, Rajkumar Saini, Marcus Liwicki

In particular, it focuses simultaneous learning of multiple tasks, an element of MTL and promptly adapting to new tasks, a quality of meta learning.

Depth Estimation Edge Detection +4

T5 for Hate Speech, Augmented Data and Ensemble

no code implementations11 Oct 2022 Tosin Adewumi, Sana Sabah Sabry, Nosheen Abid, Foteini Liwicki, Marcus Liwicki

Our motivation is to determine which of the recent SoTA models is best for automatic hate speech detection and what advantage methods like data augmentation and ensemble may have on the best model, if any.

Data Augmentation Explainable artificial intelligence +2

Identifying and Mitigating Flaws of Deep Perceptual Similarity Metrics

1 code implementation6 Jul 2022 Oskar Sjögren, Gustav Grund Pihlgren, Fredrik Sandin, Marcus Liwicki

This work investigates the most common DPS metric, where deep features are compared by spatial position, along with metrics comparing the averaged and sorted deep features.

Vector Representations of Idioms in Conversational Systems

no code implementations7 May 2022 Tosin Adewumi, Foteini Liwicki, Marcus Liwicki

We experiment with three instances of the SoTA dialogue model, Dialogue Generative Pre-trained Transformer (DialoGPT), for conversation generation.

Information Retrieval Machine Translation +1

Deep Neural Network approaches for Analysing Videos of Music Performances

no code implementations5 May 2022 Foteini Simistira Liwicki, Richa Upadhyay, Prakash Chandra Chhipa, Killian Murphy, Federico Visi, Stefan Östersjö, Marcus Liwicki

While this idea was proposed in a previous study, this paper introduces several novelties: (i) Presents a novel method to overcome the class imbalance challenge and make learning possible for co-existent gestures by batch balancing approach and spatial-temporal representations of gestures.

State-of-the-art in Open-domain Conversational AI: A Survey

no code implementations2 May 2022 Tosin Adewumi, Foteini Liwicki, Marcus Liwicki

Results of the survey show that progress has been made with recent SoTA conversational AI, but there are still persistent challenges that need to be solved, and the female gender is more common than the male for conversational AI.

Ethics

ML_LTU at SemEval-2022 Task 4: T5 Towards Identifying Patronizing and Condescending Language

no code implementations SemEval (NAACL) 2022 Tosin Adewumi, Lama Alkhaled, Hamam Mokayed, Foteini Liwicki, Marcus Liwicki

This paper describes the system used by the Machine Learning Group of LTU in subtask 1 of the SemEval-2022 Task 4: Patronizing and Condescending Language (PCL) Detection.

A Survey of Historical Document Image Datasets

no code implementations16 Mar 2022 Konstantina Nikolaidou, Mathias Seuret, Hamam Mokayed, Marcus Liwicki

However, because of the very large variety of the actual data (e. g., scripts, tasks, dates, support systems, and amount of deterioration), the different formats for data and label representation, and the different evaluation processes and benchmarks, finding appropriate datasets is a difficult task.

Document Classification

HaT5: Hate Language Identification using Text-to-Text Transfer Transformer

no code implementations11 Feb 2022 Sana Sabah Sabry, Tosin Adewumi, Nosheen Abid, György Kovacs, Foteini Liwicki, Marcus Liwicki

We investigate the performance of a state-of-the art (SoTA) architecture T5 (available on the SuperGLUE) and compare with it 3 other previous SoTA architectures across 5 different tasks from 2 relatively diverse datasets.

Data Augmentation Explainable artificial intelligence +2

Technical Language Supervision for Intelligent Fault Diagnosis in Process Industry

no code implementations11 Dec 2021 Karl Löwenmark, Cees Taal, Stephan Schnabel, Marcus Liwicki, Fredrik Sandin

In the process industry, condition monitoring systems with automated fault diagnosis methods assist human experts and thereby improve maintenance efficiency, process sustainability, and workplace safety.

Contrastive Learning Model Optimization +1

Småprat: DialoGPT for Natural Language Generation of Swedish Dialogue by Transfer Learning

no code implementations12 Oct 2021 Tosin Adewumi, Rickard Brännvall, Nosheen Abid, Maryam Pahlavan, Sana Sabah Sabry, Foteini Liwicki, Marcus Liwicki

Perplexity score (an automated intrinsic language model metric) and surveys by human evaluation were used to assess the performances of the fine-tuned models, with results that indicate that the capacity for transfer learning can be exploited with considerable success.

Chatbot Language Modelling +2

Potential Idiomatic Expression (PIE)-English: Corpus for Classes of Idioms

2 code implementations LREC 2022 Tosin P. Adewumi, Roshanak Vadoodi, Aparajita Tripathy, Konstantina Nikolaidou, Foteini Liwicki, Marcus Liwicki

The challenges with NLP systems with regards to tasks such as Machine Translation (MT), word sense disambiguation (WSD) and information retrieval make it imperative to have a labelled idioms dataset with classes such as it is in this work.

Information Retrieval Machine Translation +5

The Challenge of Diacritics in Yoruba Embeddings

1 code implementation15 Nov 2020 Tosin P. Adewumi, Foteini Liwicki, Marcus Liwicki

The major contributions of this work include the empirical establishment of a better performance for Yoruba embeddings from undiacritized (normalized) dataset and provision of new analogy sets for evaluation.

Corpora Compared: The Case of the Swedish Gigaword & Wikipedia Corpora

no code implementations6 Nov 2020 Tosin P. Adewumi, Foteini Liwicki, Marcus Liwicki

In this work, we show that the difference in performance of embeddings from differently sourced data for a given language can be due to other factors besides data size.

Exploring Swedish & English fastText Embeddings for NER with the Transformer

1 code implementation23 Jul 2020 Tosin P. Adewumi, Foteini Liwicki, Marcus Liwicki

To achieve a good network performance in natural language processing (NLP) downstream tasks, several factors play important roles: dataset size, the right hyper-parameters, and well-trained embeddings.

named-entity-recognition Named Entity Recognition +1

Pretraining Image Encoders without Reconstruction via Feature Prediction Loss

1 code implementation16 Mar 2020 Gustav Grund Pihlgren, Fredrik Sandin, Marcus Liwicki

To evaluate this method we perform experiments on three standard publicly available datasets (LunarLander-v2, STL-10, and SVHN) and compare six different procedures for training image encoders (pixel-wise, perceptual similarity, and feature prediction losses; combined with two variations of image and feature encoding/decoding).

HyperEmbed: Tradeoffs Between Resources and Performance in NLP Tasks with Hyperdimensional Computing enabled Embedding of n-gram Statistics

no code implementations3 Mar 2020 Pedro Alonso, Kumar Shridhar, Denis Kleyko, Evgeny Osipov, Marcus Liwicki

The embedding achieved on par F1 scores while decreasing the time and memory requirements by several times compared to the conventional n-gram statistics, e. g., for one of the classifiers on a small dataset, the memory reduction was 6. 18 times; while train and test speed-ups were 4. 62 and 3. 84 times, respectively.

Improving Image Autoencoder Embeddings with Perceptual Loss

1 code implementation10 Jan 2020 Gustav Grund Pihlgren, Fredrik Sandin, Marcus Liwicki

Autoencoders are trained to embed images from three different computer vision datasets using perceptual loss based on a pretrained model as well as pixel-wise loss.

Trainable Spectrally Initializable Matrix Transformations in Convolutional Neural Networks

2 code implementations12 Nov 2019 Michele Alberti, Angela Botros, Narayan Schuez, Rolf Ingold, Marcus Liwicki, Mathias Seuret

In this work, we investigate the application of trainable and spectrally initializable matrix transformations on the feature maps produced by convolution operations.

Handwriting Recognition

Labeling, Cutting, Grouping: an Efficient Text Line Segmentation Method for Medieval Manuscripts

1 code implementation11 Jun 2019 Michele Alberti, Lars Vögtlin, Vinaychandran Pondenkandath, Mathias Seuret, Rolf Ingold, Marcus Liwicki

We measured the performance of our method on a recent dataset of challenging medieval manuscripts and surpassed state-of-the-art results by reducing the error by 80. 7%.

Denoising Segmentation +1

A Comprehensive Study of ImageNet Pre-Training for Historical Document Image Analysis

no code implementations22 May 2019 Linda Studer, Michele Alberti, Vinaychandran Pondenkandath, Pinar Goktepe, Thomas Kolonko, Andreas Fischer, Marcus Liwicki, Rolf Ingold

Automatic analysis of scanned historical documents comprises a wide range of image analysis tasks, which are often challenging for machine learning due to a lack of human-annotated learning samples.

General Classification Image Classification +5

ICDAR 2019 Historical Document Reading Challenge on Large Structured Chinese Family Records

1 code implementation8 Mar 2019 Rajkumar Saini, Derek Dobson, Jon Morrey, Marcus Liwicki, Foteini Simistira Liwicki

We propose a Historical Document Reading Challenge on Large Chinese Structured Family Records, in short ICDAR2019 HDRC CHINESE.

Using Deep Object Features for Image Descriptions

no code implementations25 Feb 2019 Ashutosh Mishra, Marcus Liwicki

The decoder model learns to extract descriptions for the image from scratch by decoding the joint representation of the object visual features and their object classes conditioned by the encoder component.

Decoder Language Modelling +3

A Comprehensive guide to Bayesian Convolutional Neural Network with Variational Inference

6 code implementations8 Jan 2019 Kumar Shridhar, Felix Laumann, Marcus Liwicki

In this paper, Bayesian Convolutional Neural Network (BayesCNN) using Variational Inference is proposed, that introduces probability distribution over the weights.

Bayesian Inference General Classification +4

Leveraging Random Label Memorization for Unsupervised Pre-Training

no code implementations5 Nov 2018 Vinaychandran Pondenkandath, Michele Alberti, Sammer Puran, Rolf Ingold, Marcus Liwicki

We present a novel approach to leverage large unlabeled datasets by pre-training state-of-the-art deep neural networks on randomly-labeled datasets.

Action Recognition Memorization +2

Offline Signature Verification by Combining Graph Edit Distance and Triplet Networks

1 code implementation17 Oct 2018 Paul Maergner, Vinaychandran Pondenkandath, Michele Alberti, Marcus Liwicki, Kaspar Riesen, Rolf Ingold, Andreas Fischer

Biometric authentication by means of handwritten signatures is a challenging pattern recognition task, which aims to infer a writer model from only a handful of genuine signatures.

Metric Learning

Subword Semantic Hashing for Intent Classification on Small Datasets

3 code implementations16 Oct 2018 Kumar Shridhar, Ayushman Dash, Amit Sahu, Gustav Grund Pihlgren, Pedro Alonso, Vinaychandran Pondenkandath, Gyorgy Kovacs, Foteini Simistira, Marcus Liwicki

In this paper, we introduce the use of Semantic Hashing as embedding for the task of Intent Classification and achieve state-of-the-art performance on three frequently used benchmarks.

Chatbot General Classification +4

Are You Tampering With My Data?

1 code implementation21 Aug 2018 Michele Alberti, Vinaychandran Pondenkandath, Marcel Würsch, Manuel Bouillon, Mathias Seuret, Rolf Ingold, Marcus Liwicki

We propose a novel approach towards adversarial attacks on neural networks (NN), focusing on tampering the data used for training instead of generating attacks on trained models.

Uncertainty Estimations by Softplus normalization in Bayesian Convolutional Neural Networks with Variational Inference

5 code implementations15 Jun 2018 Kumar Shridhar, Felix Laumann, Marcus Liwicki

On multiple datasets in supervised learning settings (MNIST, CIFAR-10, CIFAR-100), this variational inference method achieves performances equivalent to frequentist inference in identical architectures, while the two desiderata, a measure for uncertainty and regularization are incorporated naturally.

Bayesian Inference General Classification +1

Bidirectional Learning for Robust Neural Networks

1 code implementation21 May 2018 Sidney Pontes-Filho, Marcus Liwicki

A multilayer perceptron can behave as a generative classifier by applying bidirectional learning (BL).

DeepDIVA: A Highly-Functional Python Framework for Reproducible Experiments

12 code implementations23 Apr 2018 Michele Alberti, Vinaychandran Pondenkandath, Marcel Würsch, Rolf Ingold, Marcus Liwicki

We introduce DeepDIVA: an infrastructure designed to enable quick and intuitive setup of reproducible experiments with a large range of useful analysis functionality.

Identifying Cross-Depicted Historical Motifs

no code implementations5 Apr 2018 Vinaychandran Pondenkandath, Michele Alberti, Nicole Eichenberger, Rolf Ingold, Marcus Liwicki

Cross-depiction is the problem of identifying the same object even when it is depicted in a variety of manners.

General Classification

Recognizing Challenging Handwritten Annotations with Fully Convolutional Networks

no code implementations1 Apr 2018 Andreas Kölsch, Ashutosh Mishra, Saurabh Varshneya, Muhammad Zeshan Afzal, Marcus Liwicki

This paper introduces a very challenging dataset of historic German documents and evaluates Fully Convolutional Neural Network (FCNN) based methods to locate handwritten annotations of any kind in these documents.

Data Augmentation Semantic Segmentation

A Pitfall of Unsupervised Pre-Training

no code implementations23 Nov 2017 Michele Alberti, Mathias Seuret, Rolf Ingold, Marcus Liwicki

Experimental results suggest that in fact, there is no correlation between the reconstruction score and the quality of features for a classification task.

Classification General Classification +1

Open Evaluation Tool for Layout Analysis of Document Images

1 code implementation23 Nov 2017 Michele Alberti, Manuel Bouillon, Rolf Ingold, Marcus Liwicki

This paper presents an open tool for standardizing the evaluation process of the layout analysis task of document images at pixel level.

Historical Document Image Segmentation with LDA-Initialized Deep Neural Networks

1 code implementation19 Oct 2017 Michele Alberti, Mathias Seuret, Vinaychandran Pondenkandath, Rolf Ingold, Marcus Liwicki

In this paper, we present a novel approach to perform deep neural networks layer-wise weight initialization using Linear Discriminant Analysis (LDA).

Image Segmentation Semantic Segmentation +1

Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification

5 code implementations11 Apr 2017 Muhammad Zeshan Afzal, Andreas Kölsch, Sheraz Ahmed, Marcus Liwicki

We present an exhaustive investigation of recent Deep Learning architectures, algorithms, and strategies for the task of document image classification to finally reduce the error by more than half.

Document Image Classification General Classification +2

Multilevel Context Representation for Improving Object Recognition

no code implementations19 Mar 2017 Andreas Kölsch, Muhammad Zeshan Afzal, Marcus Liwicki

In this work, we propose the combined usage of low- and high-level blocks of convolutional neural networks (CNNs) for improving object recognition.

Data Augmentation Object +2

TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network

4 code implementations19 Mar 2017 Ayushman Dash, John Cristian Borges Gamboa, Sheraz Ahmed, Marcus Liwicki, Muhammad Zeshan Afzal

In this work, we present the Text Conditioned Auxiliary Classifier Generative Adversarial Network, (TAC-GAN) a text to image Generative Adversarial Network (GAN) for synthesizing images from their text descriptions.

Diversity Generative Adversarial Network +2

A Pitfall of Unsupervised Pre-Training

no code implementations13 Mar 2017 Michele Alberti, Mathias Seuret, Rolf Ingold, Marcus Liwicki

Experimental results suggest that in fact, there is no correlation between the reconstruction score and the quality of features for a classification task.

Classification General Classification +1

PCA-Initialized Deep Neural Networks Applied To Document Image Analysis

no code implementations1 Feb 2017 Mathias Seuret, Michele Alberti, Rolf Ingold, Marcus Liwicki

In this paper, we present a novel approach for initializing deep neural networks, i. e., by turning PCA into neural layers.

Transfer Learning

Transforming Sensor Data to the Image Domain for Deep Learning - an Application to Footstep Detection

no code implementations4 Jan 2017 Monit Shah Singh, Vinaychandran Pondenkandath, Bo Zhou, Paul Lukowicz, Marcus Liwicki

Convolutional Neural Networks (CNNs) have become the state-of-the-art in various computer vision tasks, but they are still premature for most sensor data, especially in pervasive and wearable computing.

General Classification Transfer Learning

DIVA-HisDB: A Precisely Annotated Large Dataset of Challenging Medieval Manuscripts

no code implementations International Conference on Frontiers in Handwriting Recognition 2016 Fotini Simistira, Mathias Seuret, Nicole Eichenberger, Angelika Garz, Marcus Liwicki, Rolf Ingold

Layout analysis results of several representative baseline technologies are also presented in order to help researchers evaluate their methods and advance the frontiers of complex historical manuscripts analysis.

Binarization Document Layout Analysis +2

A Generic Method for Automatic Ground Truth Generation of Camera-captured Documents

no code implementations4 May 2016 Sheraz Ahmed, Muhammad Imran Malik, Muhammad Zeshan Afzal, Koichi Kise, Masakazu Iwamura, Andreas Dengel, Marcus Liwicki

The method is generic, language independent and can be used for generation of labeled documents datasets (both scanned and cameracaptured) in any cursive and non-cursive language, e. g., English, Russian, Arabic, Urdu, etc.

Optical Character Recognition (OCR)

Symbol Grounding Association in Multimodal Sequences with Missing Elements

no code implementations13 Nov 2015 Federico Raue, Andreas Dengel, Thomas M. Breuel, Marcus Liwicki

We evaluated the proposed extension in the following scenarios: missing elements in one modality (visual or audio) and missing elements in both modalities (visual and sound).

Dynamic Time Warping Missing Elements

Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation

no code implementations NeurIPS 2015 Marijn F. Stollenga, Wonmin Byeon, Marcus Liwicki, Juergen Schmidhuber

In contrast, Multi-Dimensional Recurrent NNs (MD-RNNs) can perceive the entire spatio-temporal context of each pixel in a few sweeps through all pixels, especially when the RNN is a Long Short-Term Memory (LSTM).

Brain Image Segmentation Image Segmentation +1

Scene Labeling With LSTM Recurrent Neural Networks

no code implementations CVPR 2015 Wonmin Byeon, Thomas M. Breuel, Federico Raue, Marcus Liwicki

This paper addresses the problem of pixel-level segmentation and classification of scene images with an entirely learning-based approach using Long Short Term Memory (LSTM) recurrent neural networks, which are commonly used for sequence classification.

Classification General Classification +4

Sparse Radial Sampling LBP for Writer Identification

no code implementations23 Apr 2015 Anguelos Nicolaou, Andrew D. Bagdanov, Marcus Liwicki, Dimosthenis Karatzas

In this paper we present the use of Sparse Radial Sampling Local Binary Patterns, a variant of Local Binary Patterns (LBP) for text-as-texture classification.

Binarization General Classification +1

Unconstrained On-line Handwriting Recognition with Recurrent Neural Networks

no code implementations NeurIPS 2007 Alex Graves, Marcus Liwicki, Horst Bunke, Jürgen Schmidhuber, Santiago Fernández

On-line handwriting recognition is unusual among sequence labelling tasks in that the underlying generator of the observed data, i. e. the movement of the pen, is recorded directly.

Handwriting Recognition Language Modelling

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