Search Results for author: Marcel Worring

Found 31 papers, 11 papers with code

LifeLonger: A Benchmark for Continual Disease Classification

no code implementations12 Apr 2022 Mohammad Mahdi Derakhshani, Ivona Najdenkoska, Tom van Sonsbeek, XianTong Zhen, Dwarikanath Mahapatra, Marcel Worring, Cees G. M. Snoek

Task and class incremental learning of diseases address the issue of classifying new samples without re-training the models from scratch, while cross-domain incremental learning addresses the issue of dealing with datasets originating from different institutions while retaining the previously obtained knowledge.

Classification class-incremental learning +1

Inside Out Visual Place Recognition

1 code implementation26 Nov 2021 Sarah Ibrahimi, Nanne van Noord, Tim Alpherts, Marcel Worring

Additionally, we introduce a new training protocol Inside Out Data Augmentation to adapt Visual Place Recognition methods for localizing indoor images, demonstrating the potential of Inside Out Visual Place Recognition.

Data Augmentation Visual Place Recognition

Multi-Task Neural Processes

no code implementations10 Nov 2021 Jiayi Shen, XianTong Zhen, Marcel Worring, Ling Shao

Our multi-task neural processes methodologically expand the scope of vanilla neural processes and provide a new way of exploring task relatedness in function spaces for multi-task learning.

Bayesian Inference Brain Image Segmentation +2

Variational Multi-Task Learning with Gumbel-Softmax Priors

1 code implementation NeurIPS 2021 Jiayi Shen, XianTong Zhen, Marcel Worring, Ling Shao

Multi-task learning aims to explore task relatedness to improve individual tasks, which is of particular significance in the challenging scenario that only limited data is available for each task.

Bayesian Inference Multi-Task Learning

The Dawn of Quantum Natural Language Processing

2 code implementations13 Oct 2021 Riccardo Di Sipio, Jia-Hong Huang, Samuel Yen-Chi Chen, Stefano Mangini, Marcel Worring

In this paper, we discuss the initial attempts at boosting understanding human language based on deep-learning models with quantum computing.

Sentiment Analysis

Adaptive Neural Message Passing for Inductive Learning on Hypergraphs

no code implementations22 Sep 2021 Devanshu Arya, Deepak K. Gupta, Stevan Rudinac, Marcel Worring

Most hypergraph learning approaches convert the hypergraph structure to that of a graph and then deploy existing geometric deep learning methods.

Variational Topic Inference for Chest X-Ray Report Generation

no code implementations15 Jul 2021 Ivona Najdenkoska, XianTong Zhen, Marcel Worring, Ling Shao

The topics are inferred in a conditional variational inference framework, with each topic governing the generation of a sentence in the report.

Text Generation Variational Inference

Longer Version for "Deep Context-Encoding Network for Retinal Image Captioning"

no code implementations30 May 2021 Jia-Hong Huang, Ting-Wei Wu, Chao-Han Huck Yang, Marcel Worring

Automatically generating medical reports for retinal images is one of the promising ways to help ophthalmologists reduce their workload and improve work efficiency.

Image Captioning Medical Report Generation

Graph Neural Networks for Knowledge Enhanced Visual Representation of Paintings

no code implementations17 May 2021 Athanasios Efthymiou, Stevan Rudinac, Monika Kackovic, Marcel Worring, Nachoem Wijnberg

We propose ArtSAGENet, a novel multimodal architecture that integrates Graph Neural Networks (GNNs) and Convolutional Neural Networks (CNNs), to jointly learn visual and semantic-based artistic representations.

Art Analysis Multi-Task Learning +1

Contextualized Keyword Representations for Multi-modal Retinal Image Captioning

no code implementations26 Apr 2021 Jia-Hong Huang, Ting-Wei Wu, Marcel Worring

A traditional medical image captioning model creates a medical description only based on a single medical image input.

Image Captioning

GPT2MVS: Generative Pre-trained Transformer-2 for Multi-modal Video Summarization

no code implementations26 Apr 2021 Jia-Hong Huang, Luka Murn, Marta Mrak, Marcel Worring

Traditional video summarization methods generate fixed video representations regardless of user interest.

Video Summarization

NLQuAD: A Non-Factoid Long Question Answering Data Set

1 code implementation EACL 2021 Amir Soleimani, Christof Monz, Marcel Worring

We introduce NLQuAD, the first data set with baseline methods for non-factoid long question answering, a task requiring document-level language understanding.

Question Answering

Variational Knowledge Distillation for Disease Classification in Chest X-Rays

no code implementations19 Mar 2021 Tom van Sonsbeek, XianTong Zhen, Marcel Worring, Ling Shao

It is challenging to incorporate this information into disease classification due to the high reliance on clinician input in EHRs, limiting the possibility for automated diagnosis.

Classification General Classification +1

Variational Multi-Task Learning

no code implementations1 Jan 2021 Jiayi Shen, XianTong Zhen, Marcel Worring, Ling Shao

Multi-task learning aims to improve the overall performance of a set of tasks by leveraging their relatedness.

Bayesian Inference Multi-Task Learning

Detecting CNN-Generated Facial Images in Real-World Scenarios

no code implementations12 May 2020 Nils Hulzebosch, Sarah Ibrahimi, Marcel Worring

Artificial, CNN-generated images are now of such high quality that humans have trouble distinguishing them from real images.

II-20: Intelligent and pragmatic analytic categorization of image collections

1 code implementation5 May 2020 Jan Zahálka, Marcel Worring, Jarke J. van Wijk

Analytic categorization, however, is not machine classification (the difference between the two is called the pragmatic gap): a human adds/redefines/deletes categories of relevance on the fly to build insight, whereas the machine classifier is rigid and non-adaptive.

Query-controllable Video Summarization

1 code implementation7 Apr 2020 Jia-Hong Huang, Marcel Worring

In this work, we introduce a method which takes a text-based query as input and generates a video summary corresponding to it.

Frame Video Summarization

Fusing Structural and Functional MRIs using Graph Convolutional Networks for Autism Classification

no code implementations MIDL 2019 Devanshu Arya, Richard Olij, Deepak K. Gupta, Ahmed El Gazzar, Guido van Wingen, Marcel Worring, Rajat Mani Thomas

We alleviate the use of such non-imaging metadata and propose a fully imaging-based approach where information from structural and functional Magnetic Resonance Imaging (MRI) data are fused to construct the edges and nodes of the graph.

Disease Prediction

Assessing the Robustness of Visual Question Answering Models

no code implementations30 Nov 2019 Jia-Hong Huang, Modar Alfadly, Bernard Ghanem, Marcel Worring

In this work, we propose a new method that uses semantically related questions, dubbed basic questions, acting as noise to evaluate the robustness of VQA models.

Question Answering Visual Question Answering +1

4-Connected Shift Residual Networks

1 code implementation22 Oct 2019 Andrew Brown, Pascal Mettes, Marcel Worring

Interestingly, when incorporating shifts to all point-wise convolutions in residual networks, 4-connected shifts outperform 8-connected shifts.

BERT for Evidence Retrieval and Claim Verification

2 code implementations7 Oct 2019 Amir Soleimani, Christof Monz, Marcel Worring

Motivated by the promising performance of pre-trained language models, we investigate BERT in an evidence retrieval and claim verification pipeline for the FEVER fact extraction and verification challenge.

HyperLearn: A Distributed Approach for Representation Learning in Datasets With Many Modalities

no code implementations19 Sep 2019 Devanshu Arya, Stevan Rudinac, Marcel Worring

Encoding multimedia items into a continuous low-dimensional semantic space such that both types of relations are captured and preserved is extremely challenging, especially if the goal is a unified end-to-end learning framework.

Representation Learning

Interactive Search and Exploration in Online Discussion Forums Using Multimodal Embeddings

no code implementations7 May 2019 Iva Gornishka, Stevan Rudinac, Marcel Worring

In this paper we present a novel interactive multimodal learning system, which facilitates search and exploration in large networks of social multimedia users.

Multimodal Classification of Urban Micro-Events

no code implementations30 Apr 2019 Maarten Sukel, Stevan Rudinac, Marcel Worring

In this paper we explore several methods of creating such a classifier, including early, late, hybrid fusion and representation learning using multimodal graphs.

Classification General Classification +1

Learning Task Relatedness in Multi-Task Learning for Images in Context

no code implementations5 Apr 2019 Gjorgji Strezoski, Nanne van Noord, Marcel Worring

When task relations are explicitly defined based on domain knowledge multi-task learning (MTL) offers such concurrent solutions, while exploiting relatedness between multiple tasks performed over the same dataset.

Multi-Task Learning

Many Task Learning with Task Routing

1 code implementation ICCV 2019 Gjorgji Strezoski, Nanne van Noord, Marcel Worring

Typical multi-task learning (MTL) methods rely on architectural adjustments and a large trainable parameter set to jointly optimize over several tasks.

Multi-Task Learning

OmniArt: Multi-task Deep Learning for Artistic Data Analysis

no code implementations2 Aug 2017 Gjorgji Strezoski, Marcel Worring

Vast amounts of artistic data is scattered on-line from both museums and art applications.

Multi-Task Learning

Unsupervised, Efficient and Semantic Expertise Retrieval

1 code implementation23 Aug 2016 Christophe Van Gysel, Maarten de Rijke, Marcel Worring

We compare our model to state-of-the-art unsupervised statistical vector space and probabilistic generative approaches.

Feature Engineering

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