A Gated Fusion Network for Dynamic Saliency Prediction
This work improves video saliency prediction for applications like video compression and analysis by introducing a dynamic fusion approach, though it is incremental as it builds on existing deep learning models.
The paper tackles the problem of predicting saliency in videos by addressing the static combination of spatial and temporal features in existing models, introducing GFSalNet with a gated fusion mechanism and attention modules to achieve highly accurate predictions that outperform or are competitive with state-of-the-art methods.
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.