Multisensor-Pipeline: A Lightweight, Flexible, and Extensible Framework for Building Multimodal-Multisensor Interfaces

Barz, Michael; Bhatti, Omair Shahzad; Lüers, Bengt; Prange, Alexander; Sonntag, Daniel

doi:10.1145/3461615.3485432

Cited by 4 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Windowing is also quite important because using sliding windows would require a trade-off between having sufficient samples for the ML algorithm to function properly and not introducing large time delays, which could affect the overall user experience; while using ever expanding windows would be inefficient. This poses a question regarding whether or not to discard older samples, which can be facilitated using available tools and frameworks, e.g., Barz et al ( 2021a ).…”

Section: Discussionmentioning

confidence: 99%

A review of machine learning in scanpath analysis for passive gaze-based interaction

Mohamed Selim,

Barz,

Bhatti

et al. 2024

Front. Artif. Intell.

View full text Add to dashboard Cite

The scanpath is an important concept in eye tracking. It refers to a person's eye movements over a period of time, commonly represented as a series of alternating fixations and saccades. Machine learning has been increasingly used for the automatic interpretation of scanpaths over the past few years, particularly in research on passive gaze-based interaction, i.e., interfaces that implicitly observe and interpret human eye movements, with the goal of improving the interaction. This literature review investigates research on machine learning applications in scanpath analysis for passive gaze-based interaction between 2012 and 2022, starting from 2,425 publications and focussing on 77 publications. We provide insights on research domains and common learning tasks in passive gaze-based interaction and present common machine learning practices from data collection and preparation to model selection and evaluation. We discuss commonly followed practices and identify gaps and challenges, especially concerning emerging machine learning topics, to guide future research in the field.

show abstract

Section: Discussionmentioning

confidence: 99%