Towards Retrieval-Augmented Architectures for Image Captioning

S Sarto, M Cornia, L Baraldi, A Nicolosi… - ACM Transactions on …, 2024 - dl.acm.org
The objective of image captioning models is to bridge the gap between the visual and
linguistic modalities by generating natural language descriptions that accurately reflect the …

Unwinding AI's Moral Maze: Hypertext's Ethical Potential

C Atzenbeck - Proceedings of the 35th ACM Conference on Hypertext …, 2024 - dl.acm.org
This paper considers hypertext in its various forms as a paradigm that has the potential to
reduce a number of ethical concerns that come with (generative) AI. Based on a user …

Uncovering labeler bias in machine learning annotation tasks

L Haliburton, J Leusmann, R Welsch, S Ghebremedhin… - AI and Ethics, 2024 - Springer
As artificial intelligence becomes increasingly pervasive, it is essential that we understand
the implications of bias in machine learning. Many developers rely on crowd workers to …

DaedalusData: Exploration, Knowledge Externalization and Labeling of Particles in Medical Manufacturing–A Design Study

A Wyss, G Morgenshtern… - … on Visualization and …, 2024 - ieeexplore.ieee.org
In medical diagnostics of both early disease detection and routine patient care, particle-
based contamination of in-vitro diagnostics consumables poses a significant threat to …

Identifying Hand-based Input Preference Based on Wearable EEG

K Zhang, Z Cao, X Zheng, M Billinghurst - Proceedings of the …, 2024 - dl.acm.org
Understanding user input preference can improve the user experience, however
automatically determining preference can be difficult. In this paper, we designed an EEG …

[PDF][PDF] MASTERARBEIT/MASTER'S THESIS

Z Al Sarrih - 2024 - phaidra.univie.ac.at
The rapid advancements in computer vision technologies by industrial companies like
Amazon, Google, IBM, and Microsoft have led to the development of robust image …