A Gated Fusion Network for Dynamic Saliency Prediction

TL;DR

This paper introduces GFSalNet, a deep learning model that dynamically predicts video saliency by adaptively fusing spatial and temporal features using a gated mechanism, outperforming existing static fusion methods.

Contribution

The paper presents the first deep saliency model with a gated fusion mechanism for dynamic adaptation to video content changes.

Findings

Outperforms or matches state-of-the-art methods on multiple datasets.

Exhibits strong generalization across different video datasets.

Effectively exploits temporal information through adaptive fusion.

Abstract

Predicting saliency in videos is a challenging problem due to complex modeling of interactions between spatial and temporal information, especially when ever-changing, dynamic nature of videos is considered. Recently, researchers have proposed large-scale datasets and models that take advantage of deep learning as a way to understand what's important for video saliency. These approaches, however, learn to combine spatial and temporal features in a static manner and do not adapt themselves much to the changes in the video content. In this paper, we introduce Gated Fusion Network for dynamic saliency (GFSalNet), the first deep saliency model capable of making predictions in a dynamic way via gated fusion mechanism. Moreover, our model also exploits spatial and channel-wise attention within a multi-scale architecture that further allows for highly accurate predictions. We evaluate the proposed approach on a number of datasets, and our experimental analysis demonstrates that it outperforms or is highly competitive with the state of the art. Importantly, we show that it has a good generalization ability, and moreover, exploits temporal information more effectively via its adaptive fusion scheme.