|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Most of the saliency methods are evaluated on their ability to generate saliency maps, and not on their functionality in a complete vision pipeline, like for instance, image classification.
The proposed framework is gradient-based and model-agnostic.
We compare ITSELF to two state-of-the-art saliency estimators on five metrics and six datasets, four of which are composed of natural-images, and two of biomedical-images.
In this paper, we propose a new metric to address the long-standing problem of center bias in saliency evaluation.
Depth data containing a preponderance of discriminative power in location have been proven beneficial for accurate saliency prediction.
We introduce STAViS, a spatio-temporal audiovisual saliency network that combines spatio-temporal visual and auditory information in order to efficiently address the problem of saliency estimation in videos.
In recent years, predicting driver's focus of attention has been a very active area of research in the autonomous driving community.
For high-level visual recognition, self-supervised learning defines and makes use of proxy tasks such as colorization and visual tracking to learn a semantic representation useful for distinguishing objects.