4.7 Article

Integrating object proposal with attention networks for video saliency detection

Journal

INFORMATION SCIENCES
Volume 576, Issue -, Pages 819-830

Publisher

ELSEVIER SCIENCE INC
DOI: 10.1016/j.ins.2021.08.069

Keywords

Video saliency detection; Saliency; Object proposal; Attention networks; Spatiotemporal features

Funding

  1. National Natural Science Foundation of China (NSFC) [61976123, 61601427]
  2. Taishan Young Scholars Program of Shandong Province
  3. Royal Society-K. C. Wong International Fellowship [NIF\R1\180909]
  4. Key Development Program for Basic Research of Shandong Province [ZR2020ZD44]

Ask authors/readers for more resources

In this paper, we propose an efficient video saliency-detection model that integrates object-proposal with attention networks to capture salient objects and human attention areas in dynamic video scenes. Experimental results show that our framework outperforms existing deep models in video saliency detection.
Video saliency detection is an active research issue in both information science and visual psychology. In this paper, we propose an efficient video saliency-detection model, based on integrating object-proposal with attention networks, for efficiently capturing salient objects and human attention areas in the dynamic scenes of videos. In our algorithm, visual object features are first exploited from individual video frame, using real-time neural net-works for object detection. Then, the spatial position information of each frame is used to screen out the large background in the video, so as to reduce the influence of background noises. Finally, the results, with backgrounds removed, are further refined by spreading the visual clues through an adaptive weighting scheme into the later layers of a convolutional neural network. Experimental results, conducted on widespread and commonly used data-bases for video saliency detection, verify that our proposed framework outperforms exist-ing deep models. (c) 2021 Elsevier Inc. All rights reserved.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available