Visual-semantic Collaborative Interactions in Synergic System for Scene Modeling

摘要：

With the reference of slaving principles from synergetic in physics, the embedding correspondences from visual cues and semantic ones are captured as prototypes in dynamic system. In scene modeling for interpretation, collaborative visual-semantic interactions are factorized as self-stimulation, self-restraint and other-restraint processes with decrease of energy to stable situation. The experiments demonstrate our framework can automatically correct false local labels and improve the accuracy of scene categorization.

关键词： synergic system local semantic feature global histogram prototype collaborative interaction support vector machine

作者: Biru Zhao Zhao Xie Kewei Wu Jun Gao

作者单位: School of Computer and Information Hefei University of Technology Hefei, PR China

会议类型: 国际会议

会议名称: 2011 4th International Congress on Image and Signal Processing(第四届图像与信号处理国际学术会议 CISP 2011)

会议地点: 上海

会议语种:英文

页码: 1488-1492

在线出版日期: 2011-10-15（万方平台首次上网日期，不代表论文的发表时间）