Emotion-Aware Human Attention Prediction

Macario O. Cordel; Shaojing Fan; Zhiqi Shen; Mohan S. Kankanhalli
November, 2021


Despite the recent success in face recognition and object classification, in the field of human gaze prediction, computer models are still struggling to accurately mimic human attention. One main reason is that visual attention is a complex human behavior influenced by multiple factors, ranging from low-level features (e.g., color, contrast) to high-level human perception (e.g., objects interactions, object sentiment), making it difficult to model computationally. In this work, we investigate the relation between object sentiment and human attention. We first introduce an improved evaluation metric (AttI) for measuring human attention that focuses on human fixation consensus. A series of empirical data analyses with AttI indicate that emotionevoking objects receive attention favor, especially when they co-occur with emotionally-neutral objects, and this favor varies with different image complexity. Based on the empirical analyses, we design a deep neural network for human attention prediction which allows the attention bias on emotion-evoking objects to be encoded in its feature space. Experiments on two benchmark datasets demonstrate its superior performance, especially on metrics that evaluate relative importance of salient regions. This research provides the clearest picture to date on how object sentiments influence human attention, and it makes one of the first attempts to model this phenomenon computationally.

Keywords: Emotion Awareness, Predictive Model



author={Cordel, M.O. and Fan, S. and Zhiqi, S. and Kankanhalli, M.},
title={{Emotion-Aware Human Attention Prediction}},
booktitle={{Proceeding of the IEEE/CVF 2019 International Conference on Computer Vision and Pattern Recognition, CVPR 2019}},