Scope and topics

Computer vision has always been an extremely popular topic in the field of Artificial Intelligence. It is of fundamental importance in many high-impact application areas, such as in security with Visual Object Tracking, in the medical field through the possibility of making predictions of diseases and attempting to locate through object detection and segmentation possible diseased areas in images. It is perfectly applicable to any kind of visual input even from different domains such as using data from ECG or EEG that can easily be transformed from one-dimensional signals into two/tri-dimensional signals and represent them with high semantic meaning as images. Moreover, with the latest generative techniques, artificial data can be made with extraordinary fidelity. 

The techniques produced in this area are able to work on both static images and sequences of images, which can have both temporal and volumetric expansion. Because of all these applications, some of them extremely sensitive and high-impact for humans, it has become necessary in recent years to begin to understand why a neural model working on images chooses one response over another. This is possible through explainable Artificial Intelligence techniques. As time goes on, however, it becomes increasingly important not only to explain why an artificial neural network makes choices, but also and especially to provide architectures that can explicitly or implicitly provide a set of explanations/rules, why it was possible to interpret a certain output with given input and verify the mechanisms that are activated within it, even making them predictable. Finally, it is becoming more and more appropriate to put side by side with this type of analysis, how well a model is able to ''defend'' and ''adapt'' itself from elements in the external world. that attempt to confuse the model and try to steer it down the wrong path. 

Thus, the purpose of this special session is to revise computer vision models by changing the perspective of looking at these methodologies, making them no longer only data- and performance-driven, which is the point on which mostly new algorithms are created, but to be able to make them become human-centric, that is, through processes of explainability, interpretability, and resilience to go about unwinding the skein of uncertainty that hovers over deep learning and, especially, in the field of computer vision by allowing artificial intelligence to be reliable from a human perspective. 

The topics of interest for this special session include (but are not limited to):

• Explainability and interpretability of deep neural networks

• Resilient models in computer vision

• Robustness and adaptation to adversarial inputs 

• Visualization techniques for explainability and interpretability

• Meta-explanation, generative description of outputs

• Specific explainability and effects of visual attributes in images

• Datasets reliability 

• Multisource imaging interpretation

Submission Guideline

Please follow the submission guideline from the IEEE WCCI 2024 submission website. To submit a paper use the EDAS Conference platform and specify, in the topics section, that your paper is for the "A Human-Centric Perspective of Explainability, Interpretability and Resilience in Computer Vision".

Special session papers are treated the same as regular conference papers. All papers accepted and presented at WCCI2024 will be included in the conference proceedings published by IEEE Xplore.

Important Dates

• Paper Submission: January 15th, 2024. Deadline extended to January 29th, 2024!

• Paper Acceptance Notification: March 15th, 2024

• Final Paper Submission & Early Registration Deadline: May 1st, 2024

• IEEE WCCI 2024: June 30th - July 5th, 2024
  
  

Organizers

Emanuel Di Nardo
University of Naples Parthenope

Emanuel Di Nardo received a Ph.D. from University of Milan in 2022 with a focus on computer vision and with a deep study in modeling neural networks for Visual Object Tracking. He is a lecturer in Department of Science and Technologies at University of Naples Parthenope and he cooperates in teaching and research activities with the Computational Intelligence & Smart Systems Lab. Further, he works as researcher consultant on Artificial Intelligence in private companies. His main interests are neural networks modeling for applications in Computer Vision. His interests, also, spread on multiple fields, from generative methodologies to building deep neuro-fuzzy architecture to application in interdisciplinary fields like Marine Engineering, Biology and Medical Applications, with a deep focus on explainable AI. He is member of AIxIA and CVPL associations.

Ihsan Ullah
Insight SFI Research Center for Data Analytics, University of Galway, Galway, Ireland

Dr. Ihsan Ullah did his Ph.D. in the University of Milan, specializing in designing lightweight deep neural network architectures with the pyramidal approach. He has more than nine years of research and development experience in applying Deep Learning to a variety of images, video, text, and time-series recognition problems while working with renowned labs in the US (Computational Vision and Geometry Lab at Stanford University), Europe (at CVPR Lab at the University of Naples Parthenope, Italy), and the Middle East (Visual Computing Lab in King Saud University, Saudi Arabia). Before joining the School of Computer Science in University of Galway, he was a Senior Research Data Scientist in CeADAR Ireland's Centre for Applied AI in University College Dublin where he was the head of the Special Projects group and was actively involved in applying for various national and international fundings e.g., Horizon Europe, SFI, EI. Prior to that, he worked in Data Mining and Machine Learning Group of School of Computer Science in NUI Galway as a Senior Postdoc, Adjunct Lecturer, and Project Manager of the H2020 project 'ROCSAFE'. He also worked as a Postdoc at INSIGHT Research Centre in NUI Galway and Research Engineer in Prosa Srl Italy. Currently, he is a Funded Investigator in Insight SFI Research Center for Data Analytics, University of Galway. Also, he is Principal Investigator on SFI Funded project. His main areas of research interest are in designing lightweight deep learning models, computer vision and Pattern Recognition, Explainable AI, and federated learning.

Angelo Ciaramella
University of Naples Parthenope

Angelo Ciaramella received, in 1998, the Laurea degree (cum laude) in Computer Science from the University of Salerno and in 2002 he received a Ph.D. from the same University. From 2021 he is Full Professor at the Department of Science and Technology of the University of Naples “Parthenope” where he serves as President of the Course of Study in Computer Science (informatica.uniparthenope.it), Director of the Apple Foundation Program Parthenope (iosdeveloperacademy.uniparthenope.it), Head of the Computational Intelligence & Smart Systems Lab (cisslab.uniparthenope.it), Director of the local nodes of the CINI Big Data, Digital Health and InfoLife national laboratories. The main research interests of Angelo Ciaramella are Computational Intelligence, Machine Learning and Data Mining. In particular, he has been interested in statistical, Machine Learning and Deep Learning approaches for Blind Source Separation, Sparse Coding, Compressive Sensing and Dictionary Learning, for signal processing (i.e., audio, streaming, astrophysical and geological) and feature extraction. He has been working on fuzzy and neuro-fuzzy systems for structured and unstructured data. He is interested in developing Fuzzy Decision Support Systems in risk assessment. He also studied and developed new methodologies for pre-processing, clustering, visualization, and assessment of biological, air quality and social network data (e.g., twitter). He is also interested in signal processing by Deep Learning methodologies in Brain Computer Interfaces. He is associate editor of international journals (i.e., Information Sciences) and are editor of Soft Computing Journal, he has been co-editor of books and guest editor of Special Issues. He is in the steering committee of WILF conference, has been co-general Chair (ITADATA2023, PDP2023, WILF2021, IDCS2019), technical chair (CIBB2018), organizer and chair of Special Sessions (e.g., EAIS, CIBB, WIRN, Fuzz-IEEE, NAFIPS), and he is in the Program Committee (e.g., CIBB, EAIS, Fuzz-IEEE, WIRN, GCIS, ICIC, AI2IA) of international conferences.  He is a Senior Member of IEEE and member of IEEE Computational Intelligence Society, IEEE Signal Processing, SIREN, GIRPR and AIxIA.