CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
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
Conference NameConference and Labs of the Evaluation forum
Source PublicationCEUR Workshop Proceedings 1391
Conference DateSeptember 8-11, 2015
Conference PlaceToulouse, France
AbstractIn 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.
KeywordHybrid Learning Svm Fast R-cnn Annotation Concept Localization
Indexed By其他
Document Type会议论文
Corresponding AuthorJing Liu
Recommended Citation
GB/T 7714
Yong Li,Jing Liu,Yuhang Wang,et al. Hybrid Learning Framework for Large-Scale Web Image Annotation and Localization[C],2015.
Files in This Item: Download All
File Name/Size DocType Version Access License
clef_iva_nlpr.pdf(1331KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yong Li]'s Articles
[Jing Liu]'s Articles
[Yuhang Wang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yong Li]'s Articles
[Jing Liu]'s Articles
[Yuhang Wang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yong Li]'s Articles
[Jing Liu]'s Articles
[Yuhang Wang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: clef_iva_nlpr.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.