Home › Researcher directory › Vincent Barra
Vincent Barra
Affiliation : Centre National de la Recherche Scientifique · Université Clermont Auvergne · Laboratoire d'Informatique, de Modélisation et d'Optimisation des Systèmes
- 20Publications (affiliation in France)
- 190Total publications
- 2201Citations
- 24h-index
Research profile
Vincent Barra has 20 indexed publications (2012–2026). Their work appears mainly in “HAL”, “Information Sciences” and “Neurocomputing”. Their most cited article, “Forecasting vegetation indices from spatio-temporal remotely sensed data using deep learning-based approaches: A systematic literature revie” (2022), has been cited 129 times. 4 of these publications date from the last three years of activity. Their work is co-authored with at least 7 researchers, including institutions in Tunisia, Morocco, Algeria.
Is this you? Get your research seen
Create your free DzCademia profile and add your articles: they will show up more easily on Google and in AI assistants like ChatGPT, so more people can read and cite your work.
Create my free profile Add my publicationsResearch areas
- Medical Image Segmentation Techniques
- Remote-Sensing Image Classification
- Advanced Image Fusion Techniques
- Advanced Neural Network Applications
- Solar and Space Plasma Dynamics
Publications (20)
- Fourier-optimal loss for distortion and time in non-stationary time series forecasting
- A Transformer-Based Explainable Deep Learning Model for Counterfactual Causal Intervention in Multivariate Spatio-Temporal Time Series Forecasting
- SYNAPSE: A multi-agent LLM framework with parameter-free cross-attention fusion for interpretable multimodal spatio-temporal forecasting
- Trustworthy AI for Spatio-Temporal Forecasting via Counterfactual Causality
- Multi-attention Generative Adversarial Network for multi-step vegetation indices forecasting using multivariate time series
- Real-World Case Study of a Deep Learning Enhanced Elderly Person Fall Video-Detection System
- Forecasting vegetation indices from spatio-temporal remotely sensed data using deep learning-based approaches: A systematic literature review
- Top-Down System for Multi-Person 3D Absolute Pose Estimation from Monocular Videos
- Fused 3-D spectral-spatial deep neural networks and spectral clustering for hyperspectral image classification
- A non-stationary NDVI time series modelling using triplet Markov chain
- Semi-supervised superpixel classification for medical images segmentation: application to detection of glaucoma disease
- Triplet Markov Chain for Modeling a Non-Stationary NDVI Time Series
- A new feature selection approach based on ensemble methods in semi-supervised classification
- Rare events detection in NDVI time-series using Jarque-Bera test
- An adaptive multiplicative decomposition of non stationary multi-temporal satellite images: Application to urban changes detection
- A study of changes prediction by HMM with non-stationarity image data: Case of urban area
- Towards an Intelligent Predictive Model for Analyzing Spatio-Temporal Satellite Image Based on Hidden Markov Chain
- Seasonal Vegetation Prediction from Satellite image using Hidden Markov Model
- Spatio-temporal modeling based on hidden Markov model for object tracking in satellite imagery
- Monitoring intra-urban changes with Hidden Markov Models using the spatial relationships
Publication venues
- HAL × 3
- Information Sciences × 1
- Neurocomputing × 1
- IEEE International Conference on Tools with Artificial Intelligence (ICTAI) × 1
- Engineering Applications of Artificial Intelligence × 1
- International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) × 1
Publications per year
- 20263
- 20251
- 20232
- 20222
- 20201
- 20191
- 20171
- 20161
- 20152
- 20142
Collaborations
Partner institutions : National School of Computer Science · Manouba University · Télécom Bretagne · Institut Supérieur d’Informatique, de Modélisation et de leurs Applications · Mohammed V University
Co-authors’ countries : Tunisia · Morocco · Algeria
Co-authors
Bibliographic data from OpenAlex (open database).
Why choose Dzcademia?
Profiles, articles and conference contributions: give your research a structured public presence. Integrated metadata help search engines and AI assistants identify your work and understand its references.
Comment with Google
Sign in with Google to comment directly on this page.