DocumentCode :
639387
Title :
Harvesting Mid-level Visual Concepts from Large-Scale Internet Images
Author :
Quannan Li ; Jiajun Wu ; Zhuowen Tu
Author_Institution :
Dept. of Comput. Sci., UCLA, Los Angeles, CA, USA
fYear :
2013
fDate :
23-28 June 2013
Firstpage :
851
Lastpage :
858
Abstract :
Obtaining effective mid-level representations has become an increasingly important task in computer vision. In this paper, we propose a fully automatic algorithm which harvests visual concepts from a large number of Internet images (more than a quarter of a million) using text-based queries. Existing approaches to visual concept learning from Internet images either rely on strong supervision with detailed manual annotations or learn image-level classifiers only. Here, we take the advantage of having massive well organized Google and Bing image data, visual concepts (around 14, 000) are automatically exploited from images using word-based queries. Using the learned visual concepts, we show state-of-the-art performances on a variety of benchmark datasets, which demonstrate the effectiveness of the learned mid-level representations: being able to generalize well to general natural images. Our method shows significant improvement over the competing systems in image classification, including those with strong supervision.
Keywords :
image classification; image retrieval; learning (artificial intelligence); Bing image data; Google image data; automatic algorithm; image classification; large-scale Internet images; midlevel visual concepts harvesting; text-based queries; visual concept learning; word-based queries; Birds; Computer vision; Internet; Support vector machines; Visualization; Windows;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on
Conference_Location :
Portland, OR
ISSN :
1063-6919
Type :
conf
DOI :
10.1109/CVPR.2013.115
Filename :
6618959
Link To Document :
بازگشت