DML Sharif University of Technology
EEG-based Personalized and Interpretable Visual Attention Prediction
Human visual attention is a mapping that determines to what regions of an image human’s eyes focus more while perceiving it. Personalized visual attention is visual attention computed for a specific individual. The importance of visual attention lies in its wide range of applications in computer vision and cognitive science, such as neural encoding, image captioning, self-driving cars, video anomaly detection, image classification, and visual design. One of important aspects of visual attention is personalization, the ability to assign every individual their own, specialized attention map. In this project we aim to utilize EEG signals measured from people’s brain to predict their personalized attention map. EEG brain signals are used to predict the emotion of the person as well as an abstraction of his personal traits that affects his attention. We use Information Gain, Cross Correlation, Area under ROC Curve, KL divergence, Similarity, Normalized Scan-path Saliency, and Earth Mover’s Distance for attention prediction and Cross Entropy for emotion prediction as our evaluation metrics
We use SALICON and EMOd datasets for attention prediction, SEED, and DEAP datasets for emotion recognition, and SEED-IV and EYE-EEG dataset for our final framework as main benchmarks
Start Date
Sept. 22, 2020
Armin Behnamnia
Mohammad Ostadmohammadi
Hamid R. Rabiee