Probabilistic modeling of scenes using object frames

作     者：SU Hao YU AdamsWei 

作者机构：School of Mathematics Beihang University Department of Computer Science Stanford University Language Technologies Institute Carnegie Mellon University 

出 版 物：《Science China(Information Sciences)》 (中国科学:信息科学(英文版))

年 卷 期：2015年第58卷第3期

页      面：119-131页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

主　　题：Bayes network scene understanding object frame probabilistic model 

摘      要：In this paper,we propose a probabilistic scene model using object frames,each of which is a group of co-occurring objects with fixed spatial *** contrast to standard co-occurrence models,which mostly explore the pairwise co-existence of objects,the proposed model captures the spatial relationship among groups of *** information is closely tied to the semantics of the underlying scenes,which allows us to perform object detection and scene recognition in a unified *** proposed probabilistic model has two major *** first models the dependencies between object frames and objects by adopting the Latent Dirichlet Allocation model for text *** second component characterizes the dependencies between object frames and scenes by establishing a mapping between global image features and object frame *** results show that the induced object frames are both semantically meaningful and spatially *** addition,our model significantly improves the performance of object recognition and scene retrieval.