Salient Object Detection in Video using Deep Non-Local Neural Networks

TL;DR

This paper introduces a novel deep non-local neural network architecture for video salient object detection, leveraging global dependencies to improve detection accuracy over existing methods.

Contribution

The paper proposes a new deep non-local neural network architecture specifically designed for video saliency detection, combining appearance and motion features.

Findings

Outperforms state-of-the-art methods on DAVIS and FBMS datasets.

Effectively captures global dependencies for improved saliency detection.

Separately studies static and dynamic saliency detection effects.

Abstract

Detection of salient objects in image and video is of great importance in many computer vision applications. In spite of the fact that the state of the art in saliency detection for still images has been changed substantially over the last few years, there have been few improvements in video saliency detection. This paper investigates the use of recently introduced non-local neural networks in video salient object detection. Non-local neural networks are applied to capture global dependencies and hence determine the salient objects. The effect of non-local operations is studied separately on static and dynamic saliency detection in order to exploit both appearance and motion features. A novel deep non-local neural network architecture is introduced for video salient object detection and tested on two well-known datasets DAVIS and FBMS. The experimental results show that the proposed algorithm outperforms state-of-the-art video saliency detection methods.