Unsupervised Part-Based Weighting Aggregation Unsupervised Part-Based Weighting Aggregation | |
Xu, Jian1,2; Shi, Cunzhao1; Qi, Chengzuo1,2; Wang, Chunheng1; Xiao, Baihua1 | |
2018-02 | |
会议名称 | The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) |
会议日期 | 2018-2 |
会议地点 | 美国 |
出版地 | 美国 |
出版者 | AAAI |
摘要 | In this paper, we propose a simple but effective semantic part-based weighting aggregation (PWA) for image retrieval. The proposed PWA utilizes the discriminative filters of deep convolutional layers as part detectors. Moreover, we propose the effective unsupervised strategy to select some part detectors to generate the “probabilistic proposals”, which highlight certain discriminative parts of objects and suppress the |
收录类别 | EI |
资助项目 | National Natural Science Foundation of China[71621002] ; National Natural Science Foundation of China[61601462] ; National Natural Science Foundation of China[61531019] ; National Natural Science Foundation of China[61531019] ; National Natural Science Foundation of China[61601462] ; National Natural Science Foundation of China[71621002] |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/38518 |
专题 | 复杂系统管理与控制国家重点实验室 |
通讯作者 | Wang, Chunheng |
作者单位 | 1.State Key Laboratory of Management and Control for Complex Systems,Institute of Automation, Chinese Academy of Sciences(CASIA) 2.University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Xu, Jian,Shi, Cunzhao,Qi, Chengzuo,et al. Unsupervised Part-Based Weighting Aggregation Unsupervised Part-Based Weighting Aggregation[C]. 美国:AAAI,2018. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
PWA.pdf(1590KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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