2026-10-14T22:39:18Z https://www.scidb.cn/oai

10.57760/sciencedb.j00240.00219 2026-06-01T16:17:00Z

2026-06-01 Code and trained weights for S²UG-Mamba doi:10.57760/sciencedb.j00240.00219 en This repository provides the official code and baseline trained weights for the paper Uncertainty-Gated Mamba and Frequency Compensation Network for Saliency Prediction, which can be used to reproduce the proposed method. Aiming to address the challenges in visual saliency prediction, including high computational cost for long-range modeling, over-propagated responses to complex backgrounds, and dispersed fixation hotspots caused by decoder upsampling, we propose a novel saliency prediction network named Spatio-Spectral Uncertainty-Gated Mamba Network (S²UG-Mamba). This model integrates uncertainty-gated Mamba enhancement and dynamic frequency domain modulation. saliency prediction; state space model; Mamba; uncertainty-aware; frequency domain enhancemen Ji Jiaxin PUBLIC https://creativecommons.org/licenses/by-nc-nd/4.0/ dataset Science Data Bank