3eb65004054f5d21fca4087f5658c727-AuthorFeedback.pdf

Thanks for the insightful and helpful reviews, which will significantly improve our paper. R1, R2, R3 indicate to whom the concern belongs. Ground truth is in red, predictions are in blue, and predicted eye gaze point of the gaze-based model is in green. SVMo bridges global and local context both spatially ( e.g., whole frame vs anchor Other contributions include exhaustive experiments which may be useful for future studies. In (c), the predicted gaze falls on the intersection of 3 objects, slightly closer to the center of the rabbit.