Socializing the Semantic Gap

Author:

Li Xirong1,Uricchio Tiberio2,Ballan Lamberto3,Bertini Marco2,Snoek Cees G. M.4,Bimbo Alberto Del2

Affiliation:

1. Renmin University of China, Beijing, China

2. University of Florence, Firenze, Italy

3. University of Florence, Stanford University, Firenze, Italy

4. University of Amsterdam, Qualcomm Research Netherlands, Science Park, Netherlands

Abstract

Where previous reviews on content-based image retrieval emphasize what can be seen in an image to bridge the semantic gap, this survey considers what people tag about an image. A comprehensive treatise of three closely linked problems (i.e., image tag assignment, refinement, and tag-based image retrieval) is presented. While existing works vary in terms of their targeted tasks and methodology, they rely on the key functionality of tag relevance, that is, estimating the relevance of a specific tag with respect to the visual content of a given image and its social context. By analyzing what information a specific method exploits to construct its tag relevance function and how such information is exploited, this article introduces a two-dimensional taxonomy to structure the growing literature, understand the ingredients of the main works, clarify their connections and difference, and recognize their merits and limitations. For a head-to-head comparison with the state of the art, a new experimental protocol is presented, with training sets containing 10,000, 100,000, and 1 million images, and an evaluation on three test sets, contributed by various research groups. Eleven representative works are implemented and evaluated. Putting all this together, the survey aims to provide an overview of the past and foster progress for the near future.

Funder

Research Funds of Renmin University of China

NSFC

SRF for ROCS, SEM

SRFDP

STW STORY project, Telecom Italia PhD

Dutch national program COMMIT

AQUIS-CH

EC's FP7

Fundamental Research Funds for the Central Universities

Tuscany Region

Publisher

Association for Computing Machinery (ACM)

Subject

General Computer Science,Theoretical Computer Science

Cited by 122 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Digital Images – The Bread and Butter of Computer Vision;Synthetic Data;2024

2. An Image-Text Matching Method for Multi-Modal Robots;Journal of Organizational and End User Computing;2023-12-08

3. ChinaOpen: A Dataset for Open-world Multimodal Learning;Proceedings of the 31st ACM International Conference on Multimedia;2023-10-26

4. Diverse image search with explanations;Multimedia Tools and Applications;2023-08-10

5. Meta-learning Advisor Networks for Long-tail and Noisy Labels in Social Image Classification;ACM Transactions on Multimedia Computing, Communications, and Applications;2023-06-07

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3