Abstract | ||
---|---|---|
Video salient object detection has been attracting more and more research interests recently. However, the definition of salient objects in videos has been controversial all the time, which has become a critical bottleneck in video salient object detection. Specifically, the sequential information contained in videos results in a fact that objects have a relative saliency ranking between each other rather than specific saliency. This implies that simply distinguishing objects into salient or not-salient as usual could not represent the information about saliency comprehensively. To address this issue, 1) in this paper we propose a completely new definition for the salient objects in videos---ranking salient objects, which considers relative saliency ranking assisted with eye fixation points. 2) Based on this definition, a ranking video salient object dataset(RVSOD) is built. 3) Leveraging our RVSOD, a novel neural network called Synthesized Video Saliency Network (SVSNet) is constructed to detect both traditional salient objects and human eye movements in videos. Finally, a ranking saliency module (RSM) takes the results of SVSNet as input to generate the ranking saliency maps. We hope our approach will serve as a baseline and lead to a conceptually new research in the field of video saliency.
|
Year | DOI | Venue |
---|---|---|
2019 | 10.1145/3343031.3350882 | Proceedings of the 27th ACM International Conference on Multimedia |
Keywords | Field | DocType |
datasets, neural networks, ranking saliency, salient object detection | Computer vision,Salient object detection,Ranking,Computer science,Artificial intelligence | Conference |
ISBN | Citations | PageRank |
978-1-4503-6889-6 | 2 | 0.38 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zheng Wang | 1 | 43 | 4.79 |
Xinyu Yan | 2 | 3 | 1.08 |
Ya-Hong Han | 3 | 476 | 44.97 |
Meijun Sun | 4 | 74 | 11.77 |