Robust Object Recognition via Visual Pathway Feedback
文献类型：会议论文
| 作者 | Chong Wang ; Junge Zhang; Peipei Yang; Kaiqi Huang
|
| 出版日期 | 2014 |
| 会议日期 | 2014 |
| 会议地点 | Stockholm,Sweden |
| 关键词 | Object Recognition Bag Of Words Visual Pathway Feedback |
| 英文摘要 | Object recognition, which consists of classification and detection, has two important attributes for robustness: (1) Closeness: detection windows should be close to object locations, and (2) Adaptiveness: object matching should be adaptive to object variations in classification. It is difficult to satisfy both attributes by considering classification and detection separately, thus recent studies combine them based on confidence contextualization and foreground modeling. However, these combinations neglect feature saliency and object structure, which are important for recognition. In fact, object recognition originates in the mechanism of “what” and “where” pathways in human visual systems, and more importantly, these pathways have feedback to each other, which provides a probable way to improve closeness and adaptiveness. Inspired by the feedback, we propose a robust object recognition framework by designing a computational model of the feedback mechanism. In the “what” feedback, the feature saliency from classification is exploited to rectify detection windows for better closeness; while in the “where” feedback, object parts from detection are used to model object matching of object structure for better adaptiveness. Experiments show that the “what” and “where” feedback can be effective to improve closeness and adaptiveness for robust object recognition, and encouraging results are obtained on the challenging PASCAL VOC 2007 dataset |
| 会议录 | ICPR
 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/12430]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 |
| 通讯作者 | Kaiqi Huang |
| 作者单位 | CASIA |
| 推荐引用方式 GB/T 7714 | Chong Wang,Junge Zhang,Peipei Yang,et al. Robust Object Recognition via Visual Pathway Feedback[C]. 见:. Stockholm,Sweden. 2014. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。