Hybrid Learning Framework for Large-Scale Web Image Annotation and Localization
Yong Li; Jing Liu; Yuhang Wang; Bingyuan Liu; Jun Fu; Yunze Gao; Hui Wu; Hang Song; Peng Ying; Hanqing Lu
2015
会议名称Conference and Labs of the Evaluation forum
会议录名称CEUR Workshop Proceedings 1391
会议日期September 8-11, 2015
会议地点Toulouse, France
摘要In this paper, we describe the details of our participation in the ImageCLEF 2015 Scalable Image Annotation task. The task is to annotate and localize different concepts depicted in images. We propose a hybrid learning framework to solve the scalable annotation task, in which the supervised methods given limited annotated images and the searchbased solutions on the whole dataset are explored jointly. We adopt a two-stage solution to first annotate images with possible concepts and then localize the concepts in the images. For the first stage, we adopt the classification model to get the class-predictions of each image. To overcome the overfitting problem of the trained classifier with limited labelled data, we use a search-based approach to annotate an image by mining the textual information of its similar neighbors, which are similar on both visual appearance and semantics. We combine the results of classification and the search-based solution to obtain the annotations of each image. For the second stage, we train a concept localization model based on the architecture of Fast R-CNN, and output the top-k predicted regions for each concept obtained in the first stage. Meanwhile, localization by search is adopted, which works well for the concepts without obvious objects. The final result is achieved by combing the two kinds of localization results. The submitted runs of our team achieved the second place among the different teams. This shows the outperformance of the proposed hybrid two-stage learning framework for the scalable annotation task.
关键词Hybrid Learning Svm Fast R-cnn Annotation Concept Localization
收录类别其他
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/11768
专题模式识别国家重点实验室_图像与视频分析
通讯作者Jing Liu
推荐引用方式
GB/T 7714
Yong Li,Jing Liu,Yuhang Wang,et al. Hybrid Learning Framework for Large-Scale Web Image Annotation and Localization[C],2015.
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
clef_iva_nlpr.pdf(1331KB)会议论文 开放获取CC BY-NC-SA浏览 下载
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
[Yong Li]的文章
[Jing Liu]的文章
[Yuhang Wang]的文章
百度学术
百度学术中相似的文章
[Yong Li]的文章
[Jing Liu]的文章
[Yuhang Wang]的文章
必应学术
必应学术中相似的文章
[Yong Li]的文章
[Jing Liu]的文章
[Yuhang Wang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: clef_iva_nlpr.pdf
格式: Adobe PDF
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。