Special sessions

Medical Applications of Pattern Recognition and AI

• Proposed by: Gareth Howells (University of Kent, UK)
• Topics of interest: The special session aims to explore the current challenges and state-of-the-art of medical applications developed using pattern recognition and AI techniques with a focus on exploring the practical issues associated with their deployment and limitations inherent with problems in effectively explainable AI. The session will also explore the practical deployment of such systems for healthcare and associated medical applications as well as new developments in the underlying technology. A special focus will be on adaptable applications that specifically address the needs of the disabled community because disabilities are wide ranging (one person’s need totally differing from another's) making bespoke technology potentially costly and difficult to produce on a large scale and hence generating a need for easily adaptable systems using AI techniques. A further major area will be on techniques that reduce the rehabilitation time for major medical conditions such as physical disability by providing AI based assistance systems that improve users’ use of technologies such as improving powered wheelchair driving skills.

Analysis and learning of multi-variate, multi-temporal, multi-resolution and multi-source remote sensing data

• Please also visit dedicated website
• Proposed by: Laetitia Chapel, Minh-Tan Pham, Sébastien Lefèvre (Université de Bretagne Sud, France), Erchan Aptoula (Gebze Technical University, Turkey)
• Topics of interest: Artificial intelligence applied to multi* remote sensing data, Recognition of patterns, objects and targets from multi* remote sensing data, 2D/3D remote sensing data analysis and processing, Multi* remote sensing image classification, retrieval and semantic segmentation, Machine learning, deep learning approaches to deal with multi* remote sensing data, Analysis of multi-resolution remote sensing images, Fusion of multi-source remote sensing data, Multi-temporal remote sensing data analysis and classification, Transfer Learning and domain adaptation for multi* remote sensing data, Feature extraction and feature selection for multi* remote sensing data, Multi-task learning from multi* remote sensing data

Graphs for Pattern Recognition: Representations, Theory and Applications

• Proposed by: Walter G. Kropatsch (Vienna University of Technology, Austria), Donatello Conte (University of Tours, France), Vincenzo Carletti (University of Salerno, Italy)
• Topics of interest: Dynamic, spatial and temporal graphs, Graph representations and methods in computer vision, Geometry and Topology in Graphs, Graph Neural Networks, Benchmarks for Graphs in Pattern Recognition, Graph Learning and Classification, Graph Matching, Social Networks Analysis, Graph Representation Learning

Time series analysis

• Please also visit dedicated website
• Proposed by: Charlotte Pelletier (Université de Bretagne Sud, France), Jonathan Weber, Maxime Devanne, Germain Forestier (Université de Haute-Alsace, France)
• Topics of interest: time series classification, forecasting, clustering, segmentation, regression, representation, and generation, missing values, irregular temporal sampling, time series outliers, early classification, heterogeneous time series, cold start and the lack (or few amount) of labeled data to train models

Vis&ML for XAI: Bridging the gap between ML and visualization communities for eXplainable Artificial Intelligence 

• Please also visit dedicated website
• Proposed by: Romain Giot, Romain Bourqui (University of Bordeaux, France), Wojciech Samek (Fraunhofer Heinrich Hertz Institute, Germany)
• Topics of interest: Trust, Uncertainty, Fairness, Accountability and Transparency; Explainable/Interpretable Machine Learning; Information visualization for models or their predictions; Interactive applications for XAI; XAI Evaluation and Benchmarks; Human-AI interface and interaction design; Sample-centric and Dataset-centric explanations; Attention mechanisms for XAI; XAI-based pruning