Fast Video Saliency Detection based on Feature Competition

In this paper, we propose a light video saliency prediction model, named SalFCM, which achieves fixation detection rate of 110fps. It is known that the human attention is captured by objects that have always been present or newly appeared. To model this dynamic change, we propose an Inter-frame Feat...

Full description

Saved in:
Bibliographic Details
Published in2020 IEEE International Conference on Visual Communications and Image Processing (VCIP) pp. 74 - 77
Main Authors Yan, Hang, Xu, Yiling, Sun, Jun, Yang, Le, Zhang, Yunfei, Huang, Wei
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2020
Subjects
ablation studies
Adaptation models
attention
Correlation
detection rate
dynamic
Feature extraction
features
Fuses
Predictive models
Task analysis
trade-off
Video saliency
Visualization
Online AccessGet full text

Cover

More Information
Summary:In this paper, we propose a light video saliency prediction model, named SalFCM, which achieves fixation detection rate of 110fps. It is known that the human attention is captured by objects that have always been present or newly appeared. To model this dynamic change, we propose an Inter-frame Feature Competition Module (IFCM) to make an adaptive choice between correlated and differential features of consecutive frames. Besides, it is noted that saliency is better explained by low-level rather than high-level features in some visual scenes. Hence, we design a Hierarchical Feature Competition Module (HFCM) to balance the influence of low-level and high-level features. Our model achieves a good trade-off between precision and processing speed. The developed SalFCM is evaluated on three video saliency datasets: DHF1K, Hollywood-2 and UCF-sports. We conduct ablation studies to verify the effectiveness of the proposed model.
ISSN:2642-9357
DOI:10.1109/VCIP49819.2020.9301802