Spatial-Aware Object-Level Saliency Prediction by Learning Graphlet Hierarchies
IEEE Transactions on Industrial Electronics(2015)
摘要
To fill the semantic gap between the predictive power of computational saliency models and human behavior, this paper proposes to predict where people look at using spatial-aware object-level cues. While object-level saliency has been recently suggested by psychophysics experiments and shown effective with a few computational models, the spatial relationship between the objects has not yet been explored in this context. We in this work for the first time explicitly model such spatial relationship, as well as leveraging semantic information of an image to enhance object-level saliency modeling. The core computational module is a graphlet-based (i.e., graphlets are moderate-sized connected subgraphs) deep architecture, which hierarchically learns a saliency map from raw image pixels to object-level graphlets (oGLs) and further to spatial-level graphlets (sGLs). Eye tracking data are also used to leverage human experience in saliency prediction. Experimental results demonstrate that the proposed oGLs and sGLs well capture object-level and spatial-level cues relating to saliency, and the resulting saliency model performs competitively compared with the state-of-the-art.
更多查看译文
关键词
ogl,eye tracking,object-level graphlets,graphlet,spatial,spatial-aware object-level saliency prediction,spatial-level graphlets,object-level,learning (artificial intelligence),object-level saliency modeling,gaze tracking,sgl,computational saliency models,graphlet hierarchies,saliency,semantic gap,spatial-aware object-level cues,eye tracking data,image enhancement,semantic information,computer architecture,visualization,computational modeling,probabilistic logic,semantics,vectors,layout
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络