Marcus Liwicki

research

∙ 05/04/2023

Towards End-to-End Semi-Supervised Table Detection with Deformable Transformer

Table detection is the task of classifying and localizing table objects ...

0 Tahira Shehzadi, et al. ∙

research

∙ 04/27/2023

Robust and Fast Vehicle Detection using Augmented Confidence Map

Vehicle detection in real-time scenarios is challenging because of the t...

0 Hamam Mokayed, et al. ∙

research

∙ 04/25/2023

NLP-LTU at SemEval-2023 Task 10: The Impact of Data Augmentation and Semi-Supervised Learning Techniques on Text Classification Performance on an Imbalanced Dataset

In this paper, we propose a methodology for task 10 of SemEval23, focusi...

0 Sana Sabah Al-Azzawi, et al. ∙

research

∙ 04/20/2023

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

This work presents a novel label-efficient selfsupervised representation...

0 Ekta Gupta, et al. ∙

research

∙ 04/19/2023

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

This work presents a novel domain adaption paradigm for studying contras...

0 Muskaan Chopra, et al. ∙

research

∙ 04/05/2023

Deep Perceptual Similarity is Adaptable to Ambiguous Contexts

The concept of image similarity is ambiguous, meaning that images that a...

0 Gustav Grund Pihlgren, et al. ∙

research

∙ 03/29/2023

WordStylist: Styled Verbatim Handwritten Text Generation with Latent Diffusion Models

Text-to-Image synthesis is the task of generating an image according to ...

11 Konstantina Nikolaidou, et al. ∙

research

∙ 03/04/2023

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

We study the influence of different activation functions in the output l...

0 Peyman Hosseini, et al. ∙

research

∙ 02/08/2023

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

Deep perceptual loss is a type of loss function in computer vision that ...

0 Gustav Grund Pihlgren, et al. ∙

research

∙ 01/28/2023

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

We evaluate five English NLP benchmark datasets (available on the superG...

0 Tosin Adewumi, et al. ∙

research

∙ 10/18/2022

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

This work presents a novel self-supervised representation learning metho...

0 Prakash Chandra Chhipa, et al. ∙

research

∙ 10/13/2022

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

This work aims to integrate two learning paradigms Multi-Task Learning (...

0 Richa Upadhyay, et al. ∙

research

∙ 10/11/2022

T5 for Hate Speech, Augmented Data and Ensemble

We conduct relatively extensive investigations of automatic hate speech ...

0 Tosin Adewumi, et al. ∙

research

∙ 07/06/2022

Identifying and Mitigating Flaws of Deep Perceptual Similarity Metrics

Measuring the similarity of images is a fundamental problem to computer ...

0 Oskar Sjögren, et al. ∙

research

∙ 05/07/2022

Vector Representations of Idioms in Conversational Systems

We demonstrate, in this study, that an open-domain conversational system...

0 Tosin Adewumi, et al. ∙

research

∙ 05/05/2022

Deep Neural Network approaches for Analysing Videos of Music Performances

This paper presents a framework to automate the labelling process for ge...

0 Foteini Simistira Liwicki, et al. ∙

research

∙ 05/02/2022

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

We survey SoTA open-domain conversational AI models with the purpose of ...

0 Tosin Adewumi, et al. ∙

research

∙ 04/28/2022

SemAttNet: Towards Attention-based Semantic Aware Guided Depth Completion

Depth completion involves recovering a dense depth map from a sparse map...

0 Danish Nazir, et al. ∙

research

∙ 04/17/2022

Ìtàkúròso: Exploiting Cross-Lingual Transferability for Natural Language Generation of Dialogues in Low-Resource, African Languages

We investigate the possibility of cross-lingual transfer from a state-of...

11 Tosin Adewumi, et al. ∙

research

∙ 04/15/2022

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

This paper describes the system used by the Machine Learning Group of LT...

0 Tosin Adewumi, et al. ∙

research

∙ 03/16/2022

A Survey of Historical Document Image Datasets

This paper presents a systematic literature review of image datasets for...

0 Konstantina Nikolaidou, et al. ∙

research

∙ 03/15/2022

Magnification Prior: A Self-Supervised Method for Learning Representations on Breast Cancer Histopathological Images

This work presents a novel self-supervised pre-training method to learn ...

0 Prakash Chandra Chhipa, et al. ∙

research

∙ 02/11/2022

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

We investigate the performance of a state-of-the art (SoTA) architecture...

0 Sana Sabah Sabry, et al. ∙

research

∙ 12/11/2021

Technical Language Supervision for Intelligent Fault Diagnosis in Process Industry

In the process industry, condition monitoring systems with automated fau...

0 Karl Löwenmark, et al. ∙

research

∙ 11/23/2021

Sharing to learn and learning to share - Fitting together Meta-Learning, Multi-Task Learning, and Transfer Learning : A meta review

Integrating knowledge across different domains is an essential feature o...

0 Richa Upadhyay, et al. ∙

research

∙ 10/12/2021

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

Building open-domain conversational systems (or chatbots) that produce c...

0 Tosin Adewumi, et al. ∙

research

∙ 04/29/2021

Current Status and Performance Analysis of Table Recognition in Document Images with Deep Neural Networks

The first phase of table recognition is to detect the tabular area in a ...

26 Khurram Azeem Hashmi, et al. ∙

research

∙ 04/25/2021

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

We present a fairly large, Potential Idiomatic Expression (PIE) dataset ...

0 Tosin P. Adewumi, et al. ∙

research

∙ 04/21/2021

Guided Table Structure Recognition through Anchor Optimization

This paper presents the novel approach towards table structure recogniti...

0 Khurram Azeem Hashmi, et al. ∙

research

∙ 11/15/2020

The Challenge of Diacritics in Yoruba Embeddings

The major contributions of this work include the empirical establishment...

0 Tosin P. Adewumi, et al. ∙

research

∙ 11/06/2020

Corpora Compared: The Case of the Swedish Gigaword Wikipedia Corpora

In this work, we show that the difference in performance of embeddings f...

0 Tosin P. Adewumi, et al. ∙

research

∙ 07/23/2020

Exploring Swedish English fastText Embeddings with the Transformer

In this paper, our main contributions are that embeddings from relativel...

0 Tosin P. Adewumi, et al. ∙

research

∙ 03/23/2020

Word2Vec: Optimal Hyper-Parameters and Their Impact on NLP Downstream Tasks

Word2Vec is a prominent tool for Natural Language Processing (NLP) tasks...

29 Tosin P. Adewumi, et al. ∙

research

∙ 03/16/2020

Pretraining Image Encoders without Reconstruction via Feature Prediction Loss

This work investigates three different loss functions for autoencoder-ba...

0 Gustav Grund Pihlgren, et al. ∙

research

∙ 03/03/2020

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

Recent advances in Deep Learning have led to a significant performance i...

0 Pedro Alonso, et al. ∙

research

∙ 01/10/2020

Improving Image Autoencoder Embeddings with Perceptual Loss

Autoencoders are commonly trained using element-wise loss. However, elem...

20 Gustav Grund Pihlgren, et al. ∙

research

∙ 06/11/2019

Improving Reproducible Deep Learning Workflows with DeepDIVA

The field of deep learning is experiencing a trend towards producing rep...

0 Michele Alberti, et al. ∙

research

∙ 06/11/2019

Survey of Artificial Intelligence for Card Games and Its Application to the Swiss Game Jass

In the last decades we have witnessed the success of applications of Art...

0 Joel Niklaus, et al. ∙

research

∙ 06/06/2019

Mr and Professor

In this paper, the authors propose to increase the efficiency of blockch...

0 Tosin P. Adewumi, et al. ∙

research

∙ 05/22/2019

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

Automatic analysis of scanned historical documents comprises a wide rang...

0 Linda Studer, et al. ∙

research

∙ 03/08/2019

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

We propose a Historical Document Reading Challenge on Large Chinese Stru...

0 Foteini Simistira Liwicki, et al. ∙

research

∙ 02/25/2019

Using Deep Object Features for Image Descriptions

Inspired by recent advances in leveraging multiple modalities in machine...

0 Ashutosh Mishra, et al. ∙

research

∙ 01/08/2019

A Comprehensive guide to Bayesian Convolutional Neural Network with Variational Inference

Artificial Neural Networks are connectionist systems that perform a give...

0 Kumar Shridhar, et al. ∙

research

∙ 11/05/2018

Leveraging Random Label Memorization for Unsupervised Pre-Training

We present a novel approach to leverage large unlabeled datasets by pre-...

0 Vinaychandran Pondenkandath, et al. ∙

research

∙ 10/17/2018

Offline Signature Verification by Combining Graph Edit Distance and Triplet Networks

Biometric authentication by means of handwritten signatures is a challen...

0 Paul Maergner, et al. ∙

research

∙ 10/16/2018

Subword Semantic Hashing for Intent Classification on Small Datasets

In this paper, we introduce the use of Semantic Hashing as embedding for...

0 Kumar Shridhar, et al. ∙

research

∙ 08/21/2018

Are You Tampering With My Data?

We propose a novel approach towards adversarial attacks on neural networ...

0 Michele Alberti, et al. ∙

research

∙ 05/21/2018

Bidirectional Learning for Robust Neural Networks

A multilayer perceptron can behave as a generative classifier by applyin...

0 Sidney Pontes-Filho, et al. ∙

research

∙ 04/23/2018

DeepDIVA: A Highly-Functional Python Framework for Reproducible Experiments

We introduce DeepDIVA: an infrastructure designed to enable quick and in...

0 Michele Alberti, et al. ∙

research

∙ 04/05/2018

Identifying Cross-Depicted Historical Motifs

Cross-depiction is the problem of identifying the same object even when ...

0 Vinaychandran Pondenkandath, et al. ∙

Marcus Liwicki

Featured Co-authors