Automatic image description by using word-level features

Authors:
Shingo Horiuchi;Hirotaka Moriguchi;Shinichi Honiden;Xu Shengbo
Affiliations:
Service Innovation Center, NTT DATA, Japan;The University of Tokyo, Hongo, Bunkyo-ku, Tokyo, Japan;The University of Tokyo, Hongo, Bunkyo-ku, Tokyo, Japan;The University of Tokyo, Hongo, Bunkyo-ku, Tokyo, Japan
Venue:
Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service
Year:
2013

Citing 4
Cited 0

Every picture tells a story: generating sentences from images

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Understanding web images by object relation network

Proceedings of the 21st international conference on World Wide Web
Baby talk: Understanding and generating simple image descriptions

CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Collective generation of natural image descriptions

ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

Automatic image description is one of the challenging tasks of image recognitions. However, there are image descriptions that contain some too specific phrases that cannot be judged only from appearance of images. In this paper, we propose a novel approach to collect general phrases for generating image descriptions. On the assumption that there are high frequency phrases related to an query image in the image descriptions of similar images, we select nouns and their attribute phrases from the image descriptions of similar images based on their frequency. In order to evaluate the relevance of our image description, we conduct comparative experiments with existing approaches. Our experimental results show that our image descriptions are short, concise and visually relevant to query images.