Investigating OCR-Sensitive Neurons to Improve Entity Recognition in Historical Documents

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

The image compression field is witnessing a shift in paradigm thanks to the rise of neural network-based models. In this context, the JPEG committee is in the process of standardizing the first learning-based image compression standard, known as JPEG AI. W ...

We propose two deep learning models that fully automate shape parameterization for aerodynamic shape optimization. Both models are optimized to parameterize via deep geometric learning to embed human prior knowledge into learned geometric patterns, elimina ...

The success of self-supervised learning in computer vision and natural language processing has motivated pretraining methods on tabular data. However, most existing tabular self-supervised learning models fail to leverage information across multiple data t ...

IntroductionThis study presents COVID-Twitter-BERT (CT-BERT), a transformer-based model that is pre-trained on a large corpus of COVID-19 related Twitter messages. CT-BERT is specifically designed to be used on COVID-19 content, particularly from social me ...

Cross-field transport of particles in the boundary region of magnetically confined fusion plasmas is dominated by turbulence. Blobs, intermittent turbulent structures with large amplitude and a filamentary shape appearing in the scrape-off layer (SOL), are ...

Learning how to reach a reward over long series of actions is a remarkable capability of humans, and potentially guided by multiple parallel learning modules. Current brain imaging of learning modules is limited by (i) simple experimental paradigms, (ii) e ...

The defective regimes in metal-based Laser Powder Bed Fusion (LPBF) processes can be minimized by deploying in-situ monitoring strategies comprising Machine learning (ML) algorithms and sensing techniques. So far, algorithms trained for monitoring a partic ...

Perceiving humans in the context of Intelligent Transportation Systems (ITS) often relies on multiple cameras or expensive LiDAR sensors. In this work, we present a new cost-effective vision-based method that perceives humans' locations in 3D and their bod ...

Aging civil infrastructures are closely monitored by engineers for damage and critical defects. As the manual inspection of such large structures is costly and time-consuming, we are working towards fully automating the visual inspections to support the pr ...

The brain operates through the synaptic interaction of distant neurons within flexible, often heterogeneous, distributed systems. Histological studies have detailed the connections between distant neurons, but their functional characterization deserves fur ...

Accurate characterization of in utero human brain maturation is critical as it involves complex and interconnected structural and functional processes that may influence health later in life. Magnetic resonance imaging is a powerful tool to investigate equ ...

Entity linking is an important problem with many applications. Most previous solutions were designed for settings where annotated training data is available, which is, however, not the case in numerous domains. We propose a light-weight and scalable entity ...

We present a method for making neural network predictions robust to shifts from the training data distribution. The proposed method is based on making predictions via a diverse set of cues (called 'middle domains') and ensembling them into one strong predi ...

Learning-based algorithms have gained great popularity in communications since they often outperform even carefully engineered solutions by learning from training samples. In this paper, we show that the selection of appropriate training examples can be im ...

This work provides an additional step in the theoretical understanding of neural networks. We consider neural networks with one hidden layer and show that when learning symmetric functions, one can choose initial conditions so that standard SGD training ef ...

Due to its convenience, biometric authentication, especial face authentication, has become increasingly mainstream and thus is now a prime target for attackers. Presentation attacks and face morphing are typical types of attack. Previous research has shown ...

HMMs have been the one of the first models to be applied for sign recognition and have become the baseline models due to their success in modeling sequential and multivariate data. Despite the extensive use of HMMs for sign recognition, determining the HMM ...

Natural language generation (NLG) is an essential component of task-oriented dialog systems. Despite the recent success of neural approaches for NLG, they are typically developed in an offline manner for particular domains. To better fit real-life applicat ...

Many factors influence learners' performance on an activity beyond the knowledge required. Learners' on-task effort has been acknowledged for strongly relating to their educational outcomes, reflecting how actively they are engaged in that activity. Howeve ...

Classical semantic segmentation methods, including the recent deep learning ones, assume that all classes observed at test time have been seen during training. In this paper, we tackle the more realistic scenario where unexpected objects of unknown classes ...

Investigating OCR-Sensitive Neurons to Improve Entity Recognition in Historical Documents

Chat with Graph Search

On the impact of learning-based image compression on computer vision tasks

Automatic Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning

XTab: Cross-table Pretraining for Tabular Transformers

COVID-Twitter-BERT: A natural language processing model to analyse COVID-19 content on Twitter

Estimating cross-field particle transport at the outer midplane of TCV by tracking filaments with machine learning

Brain signals of a Surprise-Actor-Critic model: Evidence for multiple learning modules in human decision making

Deep transfer learning of additive manufacturing mechanisms across materials in metal-based laser powder bed fusion process

Perceiving Humans: from Monocular 3D Localization to Social Distancing

Active Learning for Imbalanced Civil Infrastructure Data

The functional characterization of callosal connections

A Fetal Brain magnetic resonance Acquisition Numerical phantom (FaBiAN)

Low-Rank Subspaces for Unsupervised Entity Linking

Robustness via Cross-Domain Ensembles

Training Channel Selection for Learning-based 1-bit Precoding in Massive MU-MIMO

On Symmetry and Initialization for Neural Networks

Generating Master Faces for Use in PerformingWolf Attacks on Face Recognition Systems

An HMM Approach with Inherent Model Selection for Sign Language and Gesture Recognition

Continual Learning for Natural Language Generation in Task-oriented Dialog Systems

Predicting learners' effortful behaviour in adaptive assessment using multimodal data

Detecting the Unexpected via Image Resynthesis