Abstract | ||
---|---|---|
Contemporary video search and categorization are non-trivial tasks due to the massively increasing amount and content variety of videos. We put forward the study of visual saliency models in video. Such a model is employed to identify salient objects from the image background. Starting from the observation that motion information in video often attracts more human attention compared to static images, we devise a region contrast based saliency detection model using spatial-temporal cues (RCST). We introduce and study four saliency principles to realize the RCST. This generalizes the previous static image for saliency computational model to video. We conduct experiments on a publicly available video segmentation database where our method significantly outperforms seven state-of-the-art methods with respect to PR curve, ROC curve and visual comparison. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/VCIP.2013.6706438 | VCIP |
Keywords | Field | DocType |
visual comparison,salient object identification,video signal processing,video categorization,video motion information,rcst,spatial-temporal cue,saliency principles,video visual saliency model,color feature,region contrast based saliency detection model,image background,saliency computational model,video segmentation database,feature extraction,contemporary video search,image sequences,object detection,human attention,object recognition,motion feature,pr curve,saliency,salient object detection,static image,video retrieval,roc curve,image colour analysis,image motion analysis | Object detection,Computer vision,Visual comparison,Feature detection (computer vision),Pattern recognition,Salience (neuroscience),Computer science,Image processing,Feature extraction,Video tracking,Artificial intelligence,Cognitive neuroscience of visual object recognition | Conference |
Volume | Issue | ISBN |
null | null | 978-1-4799-0288-0 |
Citations | PageRank | References |
1 | 0.36 | 12 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chuang Gan | 1 | 253 | 31.92 |
Zengchang Qin | 2 | 439 | 45.46 |
Jia Xu | 3 | 224 | 11.46 |
Tao Wan | 4 | 181 | 21.18 |