arrow
返回

A Context-Driven Extractive Framework for Generating Realistic Image Descriptions

delete2017-02-01
delete17
delete
OA
AI
A
Amara Tariq *
H
Hassan Foroosh
DOI:10.1109/TIP.2016.2628585delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Automatic image annotation methods are extremely beneficial for image search, retrieval, and organization systems. The lack of strict correlation between semantic concepts and visual features, referred to as the semantic gap, is a huge challenge for annotation systems. In this paper, we propose an image annotation model that incorporates contextual cues collected from sources both intrinsic and extrinsic to images, to bridge the semantic gap. The main focus of this paper is a large real-world data set of news images that we collected. Unlike standard image annotation benchmark data sets, our data set does not require human annotators to generate artificial ground truth descriptions after data collection, since our images already include contextually meaningful and real-world captions written by journalists. We thoroughly study the nature of image descriptions in this real-world data set. News image captions describe both visual contents and the contexts of images. Auxiliary information sources are also available with such images in the form of news article and metadata (e.g., keywords and categories). The proposed framework extracts contextual-cues from available sources of different data modalities and transforms them into a common representation space, i.e., the probability space. Predicted annotations are later transformed into sentence-like captions through an extractive framework applied over news articles. Our context-driven framework outperforms the state of the art on the collected data set of approximately 20 000 items, as well as on a previously available smaller news images data set.
Keyword:
Textual image description
context discovery
image semantics
heterogeneous information fusion
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Transactions on Image Processing 封面图
IEEE Transactions on Image Processing
IF:
13.7
论文数:
1.0W
被引数:
8.4W

机构

State University System of Florida 封面图
State University System of Florida
学者数:
12.8W
论文数: 10.9W
被引数: 130
U
University of Central Florida
学者数:
8.7K
论文数: 6.8K
被引数: 1.4W
引用论文

引用论文

err分享
err收藏
err分享
err收藏
Fast Semantic Diffusion for Large-Scale Context-Based Image and Video Annotation
err2012-06-01
err37
errOAAI
errJiang, Yu-Gang; Dai, Qi; Wang, Jun; Ngo, Chong-Wah; Xue, Xiangyang; Chang, Shih-Fu
err分享
err收藏
err分享
err收藏
err分享
err收藏
Growth Factors in the Intestinal Tract
err2018-01-01
err0
PREAI
errMichael A. Schumacher; Soula Danopoulos; Denise Al Alam; Mark R. Frey
err分享
err收藏
Learning Visual Contexts for Image Annotation From Flickr Groups
err2011-04-01
err43
errOAAI
errUlges, Adrian; Worring, Marcel; Breuel, Thomas
err分享
err收藏
学者 查看更多内容