SIGN: A Statistically-Informed Gaze Network for Gaze Time Prediction
This work addresses gaze prediction for applications in advertising and visual search, representing an incremental improvement with a novel hybrid approach.
The researchers tackled the problem of predicting aggregate gaze times on images by developing SIGN, a statistically-informed gaze network that combines CNNs and Visual Transformers. They demonstrated that SIGN significantly improves gaze duration prediction over state-of-the-art benchmarks on two datasets (AdGaze3500 and COCO-Search18) and can generate plausible gaze patterns corresponding to empirical fixation patterns.
We propose a first version of SIGN, a Statistically-Informed Gaze Network, to predict aggregate gaze times on images. We develop a foundational statistical model for which we derive a deep learning implementation involving CNNs and Visual Transformers, which enables the prediction of overall gaze times. The model enables us to derive from the aggregate gaze times the underlying gaze pattern as a probability map over all regions in the image, where each region's probability represents the likelihood of being gazed at across all possible scan-paths. We test SIGN's performance on AdGaze3500, a dataset of images of ads with aggregate gaze times, and on COCO-Search18, a dataset with individual-level fixation patterns collected during search. We demonstrate that SIGN (1) improves gaze duration prediction significantly over state-of-the-art deep learning benchmarks on both datasets, and (2) can deliver plausible gaze patterns that correspond to empirical fixation patterns in COCO-Search18. These results suggest that the first version of SIGN holds promise for gaze-time predictions and deserves further development.