DeepTSF
A machine learning operations (MLOps) framework for time series forecasting
A machine learning operations (MLOps) framework for time series forecasting read more of DeepTSF
Deep learning algorithm for segmenting blueberry rows within orchards using UAV multispectral images. This work has been carried out in the scope of the H2020 FlexiGroBots project, which has been funded by the European Commission in the scope of its H... read more of Blueberry Row Detection
The Aristotle University of Thessaloniki created the Mastodon posts dataset within the context of the project TEMA (Trusted Extremely Precise Mapping and Prediction for Emergency Management; Grant Agreement No. 101093003; Call: HORIZON-CL4-2022-DATA-01; T... read more of Mastodon posts dataset
Eating and Drinking Activity Recognition Database (MOBISERV-AIIA Database) was created in order to fulfill the need for a good benchmarking database for the evaluation of specialized meal intake (such as eating and drinking) activity recognition algorithm... read more of MOBISERV-AIIA Database
The AUTH UAV Gesture Dataset (created by AUTH in the context of the “AERIAL-CORE” collaborative project, funded from the European Union’s Horizon 2020 research and innovation programme) contains videos depicting human subjects performing 6 classes of gest... read more of AUTH UAV Gesture Dataset
THRUST-AID is an AI-powered automatic powerline defect detection tool, trained on extensive ultra-high resolution aerial imagery data selected from the entire Lithuania’s transmission network. The developed AI analytics software is able to identify high-r... read more of THRUST-AID: AI Diagnostics for aerial electricity grid inspections
THRUST-AID YOLOv8-based Clearing Object Detection model will help investigate the surroundings of the powerline based on RGB aerial data and indicate potential threats read more of THRUST-AID: Clearing Object Detection Model
THRUST-4RESST is a multifunctional forest condition assessment tool that is based on AI-aided analytics of time-resolved satellite data read more of THRUST-4RESST
AI-RON MAN Wildfire Hazard Risk Assessment scheduled pipeline to continuously update Thermal Anomalies predictions read more of AI-RON MAN Wildfire Hazard Risk Assessment - Pipeline
AI-RON MAN Wildfire Hazard Risk Assessment web application read more of AI-RON MAN Wildfire Hazard Risk Assessment - Webapp
Backend service of AI-RON MAN Wildfire Hazard Risk Assessment platform read more of AI-RON MAN Wildfire Hazard Risk Assessment - Backend service
Nowadays, digital images and video are everywhere. Image Processing revolutionizes very many domains, notably: -Digital Media (video/image/movie) Content Production and Broadcasting, Social Media Analytics, -Medical/Biological/Dental Imaging and Diagn... read more of Super Resolution Lecture
Keyphrase prediction is a significant task in natural language processing that aims to generate concise phrases summarizing a document. Researchers have conducted extensive studies using statistical and deep learning methods, as well as incorporating exte... read more of From Statistical Methods to Deep Learning, Automatic Keyphrase Prediction: A Survey
Geometric deep learning is an emerging field at the intersection of deep learning and graph theory, aimed at analyzing and processing structured data such as graphs, meshes, point clouds, and manifolds. Traditional deep learning models have primarily focu... read more of Geometric deep learning
Nowadays, Artificial Intelligence, notably Advanced Machine Learning (ML) drives scientific and economic growth worldwide. They are essentially massive ‘learning by experience/examples’ systems. However, as our tasks and the world change, such systems sho... read more of Advanced Deep Learning Module
Nowadays, Artificial Intelligence drives scientific and economic growth worldwide. This is largely due to advances in Machine Learning (ML), notably in Deep Neural Networks (DNNs), which are essentially massive ‘learning by experience/examples’ systems. T... read more of Neural Networks and Deep Learning Module
Nowadays, digital images and video are everywhere. Image Processing revolutionizes very many domains, notably: -Digital Media (video/image/movie) Content Production and Broadcasting, Social Media Analytics, -Medical/Biological/Dental Imaging and Diagn... read more of Super Resolution Lecture
Nowadays, digital images and video are everywhere. Image Processing revolutionizes very many domains, notably: -Digital Media (video/image/movie) Content Production and Broadcasting, Social Media Analytics, -Medical/Biological/Dental Imaging and Diagn... read more of Computational Aesthetics Lecture
An important task in image analysis is image segmentation. Once this key task done, there are huge of applications which can be done. Of course, the more accurate the segmentation, the better the quality of the applications. Deep learning algorithms can improve image segmentation. Their improvement offers new perspectives for the development and implementation of imaging biomarkers in clinical routine.
Deep learning has recently showed a great potential in imaging, notably to improve image quality. CT manufacturers have used this new AI technique to develop new reconstruction algorithms based on deep learning. The first results obtained with these new algorithms confirm the improvement of image quality compared to that with iterative reconstruction algorithms. The first results are very promising with the implementation of low-dose protocols and a great interest for ultra- low dose protocols.