Hybrid Learning Framework for Large-Scale Web Image Annotation and Localization

	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	紫东太初大模型研究中心_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