ML Anthology

Framing Image Description as a Ranking Task: Data, Models and Evaluation Metrics (Extended Abstract)

Micah Hodosh, Peter Young, Julia Hockenmaier
IJCAI 2015 pp. 4188-4192
/ijcai/2015/hodosh2015ijcai-framing/

Abstract

In [Hodosh et al., 2013], we established a ranking based framework for sentence-based image description and retrieval. We introduce a new dataset of images paired with multiple descriptive captions that was specifically designed for these tasks. We also present strong KCCA-based baseline systems for description and search, and perform an in-depth study of evaluation metrics for these two tasks. Our results indicate that automatic evaluation metrics for our ranking-based tasks are more accurate and robust than those proposed for generation-based image description.

PDF IJCAI Semantic Scholar

Cite

Text

Hodosh et al. "Framing Image Description as a Ranking Task: Data, Models and Evaluation Metrics (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2015.

Markdown

[Hodosh et al. "Framing Image Description as a Ranking Task: Data, Models and Evaluation Metrics (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2015.](https://mlanthology.org/ijcai/2015/hodosh2015ijcai-framing/)

BibTeX

@inproceedings{hodosh2015ijcai-framing,
  title     = {{Framing Image Description as a Ranking Task: Data, Models and Evaluation Metrics (Extended Abstract)}},
  author    = {Hodosh, Micah and Young, Peter and Hockenmaier, Julia},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2015},
  pages     = {4188-4192},
  url       = {https://mlanthology.org/ijcai/2015/hodosh2015ijcai-framing/}
}