Learning to recognition from Bing Clickture data
文献类型：会议论文
| 作者 | Li, Chenghua1,2 ; Song, Qiang1,2; Wang, Yuhang1,2; Song, Hang1; Kang, Qi4; Cheng, Jian1,2,3; Lu, Hanqing1,2
|
| 出版日期 | 2016 |
| 会议日期 | 2016.7.11-7.15 |
| 会议地点 | Seattle, USA |
| 关键词 | Clickture Data Cnns Recognition |
| 英文摘要 | MSR Image Recognition Challenge (IRC) 2016 tries to deal with designing a dog breeds recognition system based on Clickture-Dog dataset. To address the task, we proposed an effective method with systematic strategies as follows. We presented a data cleaning method using faster-rcnn to learn a dog detector. Besides, we ensembeled a series of CNN models to enhance the robustness. A dense evaluation strategy was carried out to boost the test accuracy. Finally, we achieved the first prize of this challenge with 89.65% top-5 accuracy. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/20139]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_图像与视频分析团队 |
| 作者单位 | 1.Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China 2.University of Chinese Academy of Sciences 3.Research Center for Brain-inspired Intelligence, Institute of Automation, Chinese Academy of Sciences 4.Beijing Institute Of Technology |
| 推荐引用方式 GB/T 7714 | Li, Chenghua,Song, Qiang,Wang, Yuhang,et al. Learning to recognition from Bing Clickture data[C]. 见:. Seattle, USA. 2016.7.11-7.15. |
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。