Visual object localization in image collections | |
Qu, Yanyun ; Liu, Han ; Qu YY(曲延云) | |
2011 | |
关键词 | Image segmentation Learning algorithms Unsupervised learning |
英文摘要 | Conference Name:6th International Conference on Image and Graphics, ICIG 2011. Conference Address: Hefei, Anhui, China. Time:August 12, 2011 - August 15, 2011.; National Natural Science Foundation of China; Chinese Academy of Science; Microsoft Research Asia; Xian Institute of Optics and Precision Mechanics of CAS; Anhui Crearo Technology Co., Ltd; The research of object localization is active in the field of visual object category. In this paper, we focus on object localization in a given special category dataset. We propose to exploit the context aware category discovery for object localization without any labeled examples. Firstly, the image is segmented based on a multiple segmentation algorithm. Secondly, these generated regions are clustered by spectral clustering method to find the category pattern based on the context of the dataset and the saliency. Thirdly, the object is localized based on the weakly supervised learning algorithm. To justify the effectiveness of the proposed method, the detection precision is employed to evaluate the performance of our approach. The experimental results demonstrate that our approach is promising in object localization with unsupervised learning method. ? 2011 IEEE. |
语种 | 英语 |
出处 | http://dx.doi.org/10.1109/ICIG.2011.123 |
出版者 | IEEE Computer Society |
内容类型 | 其他 |
源URL | [http://dspace.xmu.edu.cn/handle/2288/87092] ![]() |
专题 | 信息技术-会议论文 |
推荐引用方式 GB/T 7714 | Qu, Yanyun,Liu, Han,Qu YY. Visual object localization in image collections. 2011-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论