Detail publikace

What you want to do next: A novel approach for intent prediction in gaze-based interaction

Originální název

What you want to do next: A novel approach for intent prediction in gaze-based interaction

Anglický název

What you want to do next: A novel approach for intent prediction in gaze-based interaction

Jazyk

en

Originální abstrakt

(Recieved best paper honorable mention award.) Interaction intent prediction and the Midas touch have been a longstanding challenge for eye-tracking researchers and users of gaze-based interaction. Inspired by machine learning approaches in biometric person authentication, we developed and tested an offline framework for task-independent prediction of interaction intents. We describe the principles of the method, the features extracted, normalization methods, and evaluation metrics. We systematically evaluated the proposed approach on an example dataset of gaze-augmented problem-solving sessions, and we present results of the three normalization methods, different feature sets and fusion of multiple feature types. Our results show that accuracy of up to 76 % can be achieved with Area Under Curve around 80 %. We discuss the possibility of applying the results for an online system capable of interaction intent prediction.

Anglický abstrakt

(Recieved best paper honorable mention award.) Interaction intent prediction and the Midas touch have been a longstanding challenge for eye-tracking researchers and users of gaze-based interaction. Inspired by machine learning approaches in biometric person authentication, we developed and tested an offline framework for task-independent prediction of interaction intents. We describe the principles of the method, the features extracted, normalization methods, and evaluation metrics. We systematically evaluated the proposed approach on an example dataset of gaze-augmented problem-solving sessions, and we present results of the three normalization methods, different feature sets and fusion of multiple feature types. Our results show that accuracy of up to 76 % can be achieved with Area Under Curve around 80 %. We discuss the possibility of applying the results for an online system capable of interaction intent prediction.

BibTex


@inproceedings{BUT91283,
  author="Roman {Bednařík} and Hana {Vrzáková} and Michal {Hradiš}",
  title="What you want to do next: A novel approach for intent prediction in gaze-based interaction",
  annote="(Recieved best paper honorable mention award.)

Interaction intent prediction and the Midas touch have been a longstanding
challenge for eye-tracking researchers and users of gaze-based interaction.
Inspired by machine learning approaches in biometric person authentication, we
developed and tested an offline framework for task-independent prediction of
interaction intents. We describe the principles of the method, the features
extracted, normalization methods, and evaluation metrics. We systematically
evaluated the proposed approach on an example dataset of gaze-augmented
problem-solving sessions, and we present results of the three normalization
methods, different feature sets and fusion of multiple feature types. Our results
show that accuracy of up to 76 % can be achieved with Area Under Curve around 80
%. We discuss the possibility of applying the results for an online system
capable of interaction intent prediction.",
  address="Association for Computing Machinery",
  booktitle="ETRA '12 Proceedings of the Symposium on Eye Tracking Research and Applications",
  chapter="91283",
  doi="10.1145/2168556.2168569",
  edition="NEUVEDEN",
  howpublished="print",
  institution="Association for Computing Machinery",
  year="2012",
  month="march",
  pages="83--90",
  publisher="Association for Computing Machinery",
  type="conference paper"
}