ML Anthology

GCap: Graph-Based Automatic Image Captioning

Jia-Yu Pan, Hyung-Jeong Yang, Christos Faloutsos, Pinar Duygulu
CVPRW 2004 pp. 146
doi:10.1109/CVPR.2004.353 /cvprw/2004/pan2004cvprw-gcap/

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).

PDF CVPRW Semantic Scholar

Cite

Text

Pan et al. "GCap: Graph-Based Automatic Image Captioning." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2004. doi:10.1109/CVPR.2004.353

Markdown

[Pan et al. "GCap: Graph-Based Automatic Image Captioning." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2004.](https://mlanthology.org/cvprw/2004/pan2004cvprw-gcap/) doi:10.1109/CVPR.2004.353

BibTeX

@inproceedings{pan2004cvprw-gcap,
  title     = {{GCap: Graph-Based Automatic Image Captioning}},
  author    = {Pan, Jia-Yu and Yang, Hyung-Jeong and Faloutsos, Christos and Duygulu, Pinar},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2004},
  pages     = {146},
  doi       = {10.1109/CVPR.2004.353},
  url       = {https://mlanthology.org/cvprw/2004/pan2004cvprw-gcap/}
}