利用局部语义描述子和协同匹配的场景建模
Modeling scene with local semantic descriptors and collaborative matching
根据协同识别理论中的支配原理，我们设计了一种捕获视觉语义原型嵌入的方法，将场景解释建模表示为视觉语义的交互过程，包括自激励 自抑制 它抑制对模式识别结果的稳定性进行讨论。本文模型能在局部标记中进行自动修正，比原有的场景分类SVM方法得到更好的结果。
correspondences from visual cues and semantic ones as prototypes in dynamic system. As the scene modeling for interpretation, collaborative visual-semantic interactions are factorized as self-simulation, self-restraint and other-restraint processes with decrease of energy to stable situation. Better performances demonstrate our framework can automatically correct false local labels with improvement of scene categorization via .
赵碧茹、谢昭、凌然、高隽
计算技术、计算机技术
协同系统局部语义特征全局直方图原型协同迭代支持向量机
synergic systemlocal semantic featureglobal histogram prototypecollaborative interactionsupport vector machine
赵碧茹,谢昭,凌然,高隽.利用局部语义描述子和协同匹配的场景建模[EB/OL].(2012-01-10)[2025-08-23].http://www.paper.edu.cn/releasepaper/content/201201-301.点此复制
评论