GCap: Graph-based automatic image captioning

Jia Yu Pan; Hyung Jeong Yang; Christos Faloutsos; Pinar Duygulu

doi:10.1109/CVPR.2004.353

GCap: Graph-based automatic image captioning

Jia Yu Pan
, Hyung Jeong Yang
, Christos Faloutsos
, Pinar Duygulu

Research output: Contribution to journal › Conference article › peer-review

65 Citations (Scopus)

Abstract

Given an image, how do we automatically assign keywords to it? In this paper, we propose a novel, graph-based approach (GCap) which outperforms previously reported methods for automatic image captioning. Moreover, it is fast and scales well, with its training and testing time linear to the data set size. We report auto-captioning experiments on the "standard" Corel image database of 680 MBytes, where GCap outperforms recent, successful auto-captioning methods by up to 10 percentage points in captioning accuracy (50% relative improvement).

Original language	English
Article number	1384943
Journal	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume	2004-January
Issue number	January
DOIs	https://doi.org/10.1109/CVPR.2004.353
Publication status	Published - 2004
Externally published	Yes
Event	2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2004 - Washington, United States Duration: 27 Jun 2004 → 2 Jul 2004

Access to Document

10.1109/CVPR.2004.353

Cite this

@article{9cba514141e4482a8302119a2c8c499b,

title = "GCap: Graph-based automatic image captioning",

abstract = "Given an image, how do we automatically assign keywords to it? In this paper, we propose a novel, graph-based approach (GCap) which outperforms previously reported methods for automatic image captioning. Moreover, it is fast and scales well, with its training and testing time linear to the data set size. We report auto-captioning experiments on the {"}standard{"} Corel image database of 680 MBytes, where GCap outperforms recent, successful auto-captioning methods by up to 10 percentage points in captioning accuracy (50\% relative improvement).",

author = "Pan, \{Jia Yu\} and Yang, \{Hyung Jeong\} and Christos Faloutsos and Pinar Duygulu",

note = "Publisher Copyright: {\textcopyright} 2004 IEEE.; 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2004 ; Conference date: 27-06-2004 Through 02-07-2004",

year = "2004",

doi = "10.1109/CVPR.2004.353",

language = "English",

volume = "2004-January",

journal = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

issn = "2160-7508",

publisher = "IEEE Computer Society",

number = "January",

}

TY - JOUR

T1 - GCap

T2 - 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2004

AU - Pan, Jia Yu

AU - Yang, Hyung Jeong

AU - Faloutsos, Christos

AU - Duygulu, Pinar

PY - 2004

Y1 - 2004

N2 - Given an image, how do we automatically assign keywords to it? In this paper, we propose a novel, graph-based approach (GCap) which outperforms previously reported methods for automatic image captioning. Moreover, it is fast and scales well, with its training and testing time linear to the data set size. We report auto-captioning experiments on the "standard" Corel image database of 680 MBytes, where GCap outperforms recent, successful auto-captioning methods by up to 10 percentage points in captioning accuracy (50% relative improvement).

AB - Given an image, how do we automatically assign keywords to it? In this paper, we propose a novel, graph-based approach (GCap) which outperforms previously reported methods for automatic image captioning. Moreover, it is fast and scales well, with its training and testing time linear to the data set size. We report auto-captioning experiments on the "standard" Corel image database of 680 MBytes, where GCap outperforms recent, successful auto-captioning methods by up to 10 percentage points in captioning accuracy (50% relative improvement).

UR - https://www.scopus.com/pages/publications/84932600063

U2 - 10.1109/CVPR.2004.353

DO - 10.1109/CVPR.2004.353

M3 - Conference article

AN - SCOPUS:84932600063

SN - 2160-7508

VL - 2004-January

JO - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

JF - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

IS - January

M1 - 1384943

Y2 - 27 June 2004 through 2 July 2004

ER -

GCap: Graph-based automatic image captioning

Abstract

Access to Document

Other files and links

Fingerprint

Cite this