Eeg signals enhance attention prediction during realistic visual searches
EEGaze: Multimodal Attention Prediction in Visual Search via EEG-Based Saliency Refinement
Human-Computer InteractionArtificial IntelligenceMultimedia
Summary
Finding things in cluttered scenes, like keys on a messy desk, depends not just on what we see but also on how our brain is working at the time. The authors created a big collection of eye-tracking and brainwave data while people searched for items in real-world scenes. They also built a new method that improves computer predictions of where people look by including brain signal data. Their method reliably worked better than others at guessing attention in these natural search tasks.
What this means in practice
- •For human-computer interaction designers: Improve user interface elements by predicting user attention more accurately with EEG-informed models in real-world tasks.
- •For assistive technology developers: Enhance devices that aid people with visual impairments by integrating brainwave data to better anticipate focus areas in complex scenes.
Authors
Mansi Sharma, Dinar Orazgaliyev, Antonio Krüger, Philipp Müller
Abstract
Visual search is ubiquitous in daily life, from locating keys in a messy apartment to finding a tool in a cluttered workshop or an application icon on a desktop screen. While visual attention is to a large extent driven by image content, research in psychology indicates that user cognitive states have a significant influence on attention allocation. A promising way to access information about cognitive states is via Electroencephalography (EEG) recordings. Despite this potential, previous works in computational attention modeling have largely disregarded EEG, and related studies in psychology operate with abstract, simplistic stimuli, or even artificially guided search procedures. We bridge this gap with two contributions. First, we present EEGaze 140, the largest publicly available multimodal dataset of free visual search with realistic stimuli. The dataset contains synchronized EEG and eye tracking recordings from 36 participants across 140 naturalistic scenes, covering two scenarios: searching for desktop icons and finding tools in cluttered workshop scenes. Second, we introduce EEGazeNet, the first method for human attention prediction in visual search that integrates EEG signals. Our approach consists of a EEG guided refinement stage that adapts the output of a state of the art saliency prediction method to the user current cognitive state. In comprehensive evaluations on EEGaze 140, we show that EEGazeNet consistently outperforms all baselines and ablation conditions.