Nonparametric Method for Data-driven Image Captioning
Article Structure
Abstract
We present a nonparametric density estimation technique for image caption generation.
Introduction
Automatic image captioning is a much studied topic in both the Natural Language Processing (NLP) and Computer Vision (CV) areas of research.
Image Captioning by Transfer
The IM2TEXT model by Ordonez et al.
Dataset
In this paper, we use the SBU-Flickr dataset2.
Our Approach
4.1 Overview
Topics
BLEU
Appears in 8 sentences as: BLEU (8)
In Nonparametric Method for Data-driven Image Captioning
- BLEU Scores 13 N J:Page 4, “Our Approach”
- Figure l: BLEU scores vs k for SumBasic extraction.Page 4, “Our Approach”
- Although BLEU (Papineni et al., 2002) scores are widely used for image caption evaluation, we find them to be poor indicators of the quality of our model.Page 4, “Our Approach”
- As shown in Figure 1, our system’s BLEU scores increase rapidly until about k = 25.Page 4, “Our Approach”
- Past this point we observe the density estimation seems to get washed out by oversmoothing, but the BLEU scores continue to improve until k = 500 but only because the generated captions become increasingly shorter.Page 4, “Our Approach”
- Furthermore, although we observe that our SumBasic extracted captions obtain consistently higher BLEU scores, our personal observations find KL Divergence captions to be better at balancing recall and precision.Page 4, “Our Approach”
- Nevertheless, BLEU scores are the accepted metric for recent work, and our KL Divergence captions with k = 25 still outperform all other previously published systems and baselines.Page 4, “Our Approach”
- We omit full results here due to space, but make our BLEU setup with captions for all systems and baselines available for documentary purposes.Page 4, “Our Approach”
See all papers in Proc. ACL 2014 that mention BLEU.
See all papers in Proc. ACL that mention BLEU.
Back to top.
BLEU scores
Appears in 6 sentences as: BLEU Scores (1) BLEU scores (5)
In Nonparametric Method for Data-driven Image Captioning
- BLEU Scores 13 N J:Page 4, “Our Approach”
- Figure l: BLEU scores vs k for SumBasic extraction.Page 4, “Our Approach”
- As shown in Figure 1, our system’s BLEU scores increase rapidly until about k = 25.Page 4, “Our Approach”
- Past this point we observe the density estimation seems to get washed out by oversmoothing, but the BLEU scores continue to improve until k = 500 but only because the generated captions become increasingly shorter.Page 4, “Our Approach”
- Furthermore, although we observe that our SumBasic extracted captions obtain consistently higher BLEU scores , our personal observations find KL Divergence captions to be better at balancing recall and precision.Page 4, “Our Approach”
- Nevertheless, BLEU scores are the accepted metric for recent work, and our KL Divergence captions with k = 25 still outperform all other previously published systems and baselines.Page 4, “Our Approach”
See all papers in Proc. ACL 2014 that mention BLEU scores.
See all papers in Proc. ACL that mention BLEU scores.
Back to top.
