Combining Visual and Textual Features for Semantic Segmentation of Historical Newspapers

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.

Recent progress in computer vision has been driven by a simple yet transformative observation: the potential of 30-year-old neural networks can be unlocked by massively scaling their parameters and the amount of human-labeled training data. This breakthrou ...

Electrical stimulation of the visual nervous system could improve the quality of life of patients affected by acquired blindness by restoring some visual sensations, but requires careful optimization of stimulation parameters to produce useful perceptions. ...

Deep learning has shown remarkable potential for industrial applications, particularly in predictive maintenance and condition monitoring. A key challenge in this domain is prognostics, specifically predicting the Remaining Useful Life (RUL) of assets - a ...

Semi-supervised semantic segmentation methods leverage unlabeled data by pseudo-labeling them. Thus the success of these methods hinges on the reliability of the pseudo-labels. Existing methods mostly choose high-confidence pixels in an effort to avoid err ...

Data augmentation is vital in deep learning for enhancing model robustness by artificially expanding training datasets. However, advanced methods like CutMix blend images and assign labels based on pixel ratios, often introducing label noise by neglecting ...

Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...

Multi-Object Tracking (MOT) is a fundamental computer vision task that involves detecting objects of interest in video frames and associating detections of the same object across time to form trajectories. For association, appearance cues, extracted throug ...

Viewers of 360-degree videos are provided with both visual modality to characterize their surrounding views and audio modality to indicate the sound direction. Though both modalities are important for saliency prediction, little work has been done by joint ...

Proteins are the molecular machines of life, driving essential biological processes such as enzymatic catalysis, cellular signaling, and immune responses. The ability to design entirely new proteins with desired structures and functions has immense implica ...

Modern computing has enhanced our understanding of how social interactions shape collective behaviour in animal societies. Although analytical models dominate in studying collective behaviour, this study introduces a deep learning model to assess social in ...

Low-light photography produces images with low signal-to-noise ratios due to limited photons. In such conditions, common approximations like the Gaussian noise model fall short, and many denoising techniques fail to remove noise effectively. Although deep- ...

This book has been designed for instructors in higher education or adult training who wish to develop a new course or revise an existing one. It adopts a practical, visual, and modular approach based on the principle of constructive alignment. At its heart ...

Machine learning models (e.g., neural networks) achieve high accuracy in wind power forecasting, but they are usually regarded as black boxes that lack interpretability. To address this issue, the paper proposes a glass-box model that combines high accurac ...

Deep learning has emerged as a promising avenue for automatic mapping, demonstrating high efficacy in land cover categorization through various semantic segmentation models. Nonetheless, the practical deployment of these models encounters important challen ...

This thesis focuses on understanding and improving the reasoning capabilities of neural networks. It develops theoretical results and empirical analyses to uncover reasoning potential and limitations, leveraging these insights to guide the design of improv ...

Monitoring forests, in particular their response to climate and land use change, requires studying long time scales. While efficient deep learning methods have been developed to process short time series of satellite imagery, leveraging long time series of ...

The current machine learning paradigm relies on continuous representations and fixed neural network architectures to approximate environmental structures, leading to challenges with continual learning, internal structure design, and goal-directed behavior ...

In the last few years, stroke ranked as the second most common cause of death and is the third most significant condition affecting disability-adjusted life years (DALYs) worldwide. Being the most prevalent and quality of life impacting post-stroke symptom ...

The evolution of airborne mapping witnesses the introduction of hybrid lidar-camera systems to enhance data collection, i.e. to obtain simultaneously high-density point-cloud and texture. Yet, the common adjustment of both optical data streams is a nontriv ...

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

Combining Visual and Textual Features for Semantic Segmentation of Historical Newspapers

Chat with Graph Search

Exploiting Representation Similarities in Self-Supervised Learning for Vision Tasks

Decoding electroencephalographic responses to visual stimuli compatible with electrical stimulation

Overcoming Distribution Shifts and Imbalance Challenges in Representation Learning for Deep Regression Models

Weighting Pseudo-labels via High-Activation Feature Index Similarity and Object Detection for Semi-supervised Segmentation

SaliencyMix plus : Noise-Minimized Image Mixing Method With Saliency Map in Data Augmentation

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Person Re-Identification and its Application to Multi-Object Tracking

SVGC-AVA: 360-Degree Video Saliency Prediction With Spherical Vector-Based Graph Convolution and Audio-Visual Attention

Computational design of complex protein folds and soluble analogs of membrane proteins

Predicting the long-term collective behaviour of fish pairs with deep learning

Dark Noise Diffusion: Noise Synthesis for Low-Light Image Denoising

Course Design - A Visual and Modular Approach

Explainable modeling for wind power forecasting: A Glass-Box model with high accuracy

Land Cover Mapping From Multiple Complementary Experts Under Heavy Class Imbalance

Learning to Reason with Neural Networks: Principles and Methods

Multi-temporal forest monitoring in the Swiss Alps with knowledge-guided deep learning

Modelleyen: Continual Learning and Planning via Structured Modelling of Environment Dynamics

Probing and modulating inter-areal coupling in the cortical visual motion processing pathway with non-invasive brain stimulation

On the Perspectives of Image-to-Lidar Constraints in Dynamic Network Optimisation

Aggregating Spatial and Photometric Context for Photometric Stereo