Skip to search boxSkip to navigationSkip to main content

Stepwise AI interpretive approach for multimodal data fusion

Research Output: Chapter in Book/Report/Conference proceeding Conference contribution Peer-review

Open access

Abstract

In recent years, Artificial Intelligence technology has excelled in various tasks and is taking the world by storm. However, the various transformations in neural networks make it difficult to make sense of the reasons why decisions are made. For this reason, trustworthy AI techniques have started gaining popularity. AI interpretability serves as an anchor point in the field of data fusion for multimodal AI, providing in-depth insights. The paper proposed a Stepwise AI Interpretative (SAII) approach using different pairing methods of 'one-To-one' and 'many-To-many' in an attempt to illustrate/demonstrate the interpretability of the process of pairing images and text. A counterfactual instantiation method was used to compare the whole-local relationship between a set of images and their associated descriptive text. The approach was evaluated via 'task performance'.

Publication Information

Output type

Research Output: Chapter in Book/Report/Conference proceeding Conference contribution Peer-review

Original language

English

Publication milestones

  • Published - 25/11/2025

Publication status

Published - 25/11/2025

Publisher

Institute of Electrical and Electronics Engineers Inc., United States

Publication series

  • Publication series name: 6th International Conference on Intelligent Computing in Data Sciences, ICDS 2024

ISBN (Print)

9798350351200

ISBN (Electronic)

9798350351200

External Publication IDs

  • handle.net: 10547/626849
  • Scopus: 85211959021

Host publication title

6th International Conference on Intelligent Computing in Data Sciences, ICDS 2024

Host publication editors

  • Youness Oubenaalla
  • El Habib Nfaoui
  • Jaouad Boumhidi
  • Chakir Loqman
  • Cesare Alippi

Access to documents

Publication metrics