南京师大学报（自然科学版）2017，Vol.40Issue(1)：65-72,8.DOI:10.3969/j.issn.1001-4616.2017.01.010
基于姿态的判别属性学习及在细粒度识别中的应用
Pose-Based Discriminative-Attributes Learning for Fine-Grained Recognition
摘要
Abstract
Commonly existed various posture of object makes great challenges for object recognition in computer vision literature.Attribute representation shows robust describable ability with dear semantic meaning invariant to changes of environment factors including posture.However,the inherent description advantages of attributes also result big challenges for itself to learn well worked attribute predictor.Consequently,the key issues in attribute learning are to alleviate the difficulty of predicting attributes and enhance the discriminant ability at the mean time,which especially important for finegrained recognition task.By explicitly modeling the posture states and learning discriminative attribute with respect to different postures,describable and discriminative attribute can be built for final category recognition.The proposed posebased discriminative attribute is verified on publicly available fine-grained dataset CUB with advanced performance.关键词
属性学习/判别属性/分散式表示/细粒度识别Key words
attribute learning/discriminative attribute/distributed representation/fine-grained recognition分类
信息技术与安全科学引用本文复制引用
宋凤义,张守东,杨明..基于姿态的判别属性学习及在细粒度识别中的应用[J].南京师大学报（自然科学版）,2017,40(1):65-72,8.基金项目
江苏省自然科学基金项目(BK20161020)、江苏省高校自然科学研究项目(15KJB520023). （BK20161020）
