Search Results for author:
Found 19 papers, 8 papers with code
Contextual Categorization Enhancement through LLMs Latent-Space
Managing the semantic quality of the categorization in large textual datasets, such as Wikipedia, presents significant challenges in terms of complexity and cost.
Impact of Ground Truth Quality on Handwriting Recognition
Handwriting recognition is a key technology for accessing the content of old manuscripts, helping to preserve cultural heritage.
Character Queries: A Transformer-based Approach to On-Line Handwritten Character Segmentation
On-line handwritten character segmentation is often associated with handwriting recognition and even though recognition models include mechanisms to locate relevant positions during the recognition process, it is typically insufficient to produce a precise segmentation.
Towards Resolving Word Ambiguity with Word Embeddings
While word embeddings carry semantic information, they fail to handle ambiguity well.
Mapping Researcher Activity based on Publication Data by means of Transformers
Based on this, we define a similarity metric between authors.
Hands-on detection for steering wheels with neural networks
In this paper the concept of a machine learning based hands-on detection algorithm is proposed.
Improving Image Tracing with Convolutional Autoencoders by High-Pass Filter Preprocessing
The process of transforming a raster image into a vector representation is known as image tracing.
The RPM3D project: 3D Kinematics for Remote Patient Monitoring
This project explores the feasibility of remote patient monitoring based on the analysis of 3D movements captured with smartwatches.
Analyzing Büchi Automata with Graph Neural Networks
B\"uchi Automata on infinite words present many interesting problems and are used frequently in program verification and model checking.
DIVA-DAF: A Deep Learning Framework for Historical Document Image Analysis
Pre-implemented tasks such as segmentation and classification can be easily used or customized.
Ranked #1 on
Semantic Segmentation
on DIVA-HisDB
Self-Rule to Multi-Adapt: Generalized Multi-source Feature Learning Using Unsupervised Domain Adaptation for Colorectal Cancer Tissue Detection
In this work, we propose Self-Rule to Multi-Adapt (SRMA), which takes advantage of self-supervised learning to perform domain adaptation, and removes the necessity of fully-labeled source datasets.
Transport Services: A Modern API for an Adaptive Internet Transport Layer
Transport services (TAPS) is a working group of the Internet's standardization body, the Internet Engineering Task Force (IETF).
Networking and Internet Architecture
Learning Graph Edit Distance by Graph Neural Networks
The emergence of geometric deep learning as a novel framework to deal with graph-based representations has faded away traditional approaches in favor of completely new methodologies.
Automatic Creation of Text Corpora for Low-Resource Languages from the Internet: The Case of Swiss German
This paper presents SwissCrawl, the largest Swiss German text corpus to date.
Alleviating Sequence Information Loss with Data Overlapping and Prime Batch Sizes
We denote this a token order imbalance (TOI) and we link the partial sequence information loss to a diminished performance of the system as a whole, both in text and speech processing tasks.
Ranked #30 on
Language Modelling
on WikiText-2
Graph-Based Offline Signature Verification
Graphs provide a powerful representation formalism that offers great promise to benefit tasks like handwritten signature verification.
A Comprehensive Study of ImageNet Pre-Training for Historical Document Image Analysis
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.
Ranked #7 on
Image Classification
on Kuzushiji-MNIST
Offline Signature Verification by Combining Graph Edit Distance and Triplet Networks
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.
DLL: A Blazing Fast Deep Neural Network Library
Deep Learning Library (DLL) is a new library for machine learning with deep neural networks that focuses on speed.
