Michael Barz and Omair Bhatti from DFKI’s research department Interactive Machine Learning (IML) participated in the international conference on Intelligent User Interfaces (IUI 2023) in Sydney, Australia. They and their colleagues from DFKI's research department IML received prestigious awards for their papers on mobile eye tracking and explainable machine learning.
ACM IUI 2023 is the 28th annual meeting of the intelligent interfaces community. Michael Barz and Omair Bhatti presented two demonstration papers and one poster paper on mobile eye tracking and explainable machine learning. The two demonstration papers received the Best Demonstration Award and the Best Demo Honorable Mention Award, respectively, during the conference dinner at Hilton Sydney. They were selected from 15 demo papers.
Explainable Machine Learning
The demo paper “A User Interface for Explaining Machine Learning Model Explanations” by Md Abdul Kadir et al. is about the interactive visualization tool EMILE-UI that allows users to evaluate explanations of an image-based classification task, specifically those provided by saliency maps. The demo received the Best Demonstration Award.
Mobile Eye Tracking
The demo paper “Interactive Fixation-to-AOI Mapping for Mobile Eye Tracking Data based on Few-Shot Image Classification” by Michael Barz et al. received the Best Demo Honorable Mention Award. The researchers present a web-based annotation tool, eyeNotate, that leverages few-shot image classification and interactive machine learning to accelerate the annotation process for mobile eye tracking data.
References
Md Abdul Kadir, Abdulrahman Mohamed Selim, Michael Barz, Daniel Sonntag: A User Interface for Explaining Machine Learning Model Explanations. In: Companion Proceedings of the 28th International Conference on Intelligent User Interfaces, pp. 59–63, Association for Computing Machinery, Sydney, NSW, Australia, 2023, ISBN: 9798400701078.
Michael Barz, Omair Shahzad Bhatti, Hasan Md Tusfiqur Alam, Ho Minh Duy Nguyen, Daniel Sonntag: Interactive Fixation-to-AOI Mapping for Mobile Eye Tracking Data Based on Few-Shot Image Classification. In: Companion Proceedings of the 28th International Conference on Intelligent User Interfaces, pp. 175-178, Association for Computing Machinery, 2023.
