CASIA OpenIR  > 智能感知与计算研究中心
Window Mining by Clustering Mid-Level Representation for Weakly Supervised Object Localization
Chong Wang; Weiqiang Ren; Kaiqi Huang
2014
会议名称International Conference on Image Processing
会议录名称Proc. International Conference on Image Processing 2014
页码4067-4071
会议日期2014-10-01
会议地点Paris, France
摘要Discovering positive detection windows in training images is a challenging problem in weakly supervised object detection. In this paper, we propose a window mining strategy by the simple and efficient k-means clustering. Firstly, a recent segmentation based object proposal is used for its highly semantic candidate windows; secondly, the bag-of-words model is adopted as mid-level object representation for each window. By clustering these windows with k-means, semantic clusters can be generated. Then, to discover the positive windows from these clusters, we further propose a cluster selection method based on each cluster's discrimination, which is evaluated by classification performance given the category label. With the semantic clusters, this selection process is effective and efficient. Evaluation on the challenging PASCAL VOC 2007 dataset shows that the proposed method outperforms all previous weakly supervised approaches.
关键词Data Mining   image Representation   image Segmentation
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/12682
专题智能感知与计算研究中心
通讯作者Kaiqi Huang
作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Chong Wang,Weiqiang Ren,Kaiqi Huang. Window Mining by Clustering Mid-Level Representation for Weakly Supervised Object Localization[C],2014:4067-4071.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Chong Wang]的文章
[Weiqiang Ren]的文章
[Kaiqi Huang]的文章
百度学术
百度学术中相似的文章
[Chong Wang]的文章
[Weiqiang Ren]的文章
[Kaiqi Huang]的文章
必应学术
必应学术中相似的文章
[Chong Wang]的文章
[Weiqiang Ren]的文章
[Kaiqi Huang]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。