Title | ||
---|---|---|
An integrated approach to visual attention modelling using spatial-temporal saliency and objectness |
Abstract | ||
---|---|---|
Visual attention modelling is an important research topic with a wide range of applications in visual tracking, perceptual quality assessment, re-targeting, video summarization, etc. In this paper, we propose a visual attention model that captures both bottom-up spatial-temporal saliency and top-down objectness. Leveraging on co-occurrence histograms, the proposed model captures a number of low-level cues including contrast, gradient, as well as, magnitude and gradient of optical flow. Additionally, the proposed model incorporates mid-level objectness cue which helps to boost the modelling performance greatly. The proposed model obtained superior AUC-ROCs when evaluated over the ASCMN dataset and the UCF Sports Action dataset. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/ICIP.2017.8296319 | 2017 IEEE International Conference on Image Processing (ICIP) |
Keywords | Field | DocType |
video summarization,perceptual quality assessment,UCF sports action dataset,ASCMN dataset,AUC-ROC,optical flow,integrated approach,visual attention model,visual tracking,spatial-temporal saliency,mid-level objectness cue | Computer vision,Automatic summarization,Histogram,Pattern recognition,Visualization,Salience (neuroscience),Computer science,Visual attention,Eye tracking,Artificial intelligence,Perception,Optical flow | Conference |
ISSN | ISBN | Citations |
1522-4880 | 978-1-5090-2176-5 | 1 |
PageRank | References | Authors |
0.37 | 11 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jean-Baptiste Weibel | 1 | 1 | 1.04 |
Hui Li Tan | 2 | 76 | 7.42 |
Shijian Lu | 3 | 1346 | 93.57 |