Cornia et al

Reported on 3 benchmarks across 1 task · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing3 results

Image CaptioningonFlickr30k Captions test
BLEU-4· uses extra data· 2017-06-26
21.3
best: 30.1 (Unified VLP)
SOTA
Paying More Attention to Saliency: Image Captioning with Saliency and Context Attention arXiv:1706.08474
Image CaptioningonFlickr30k Captions test
CIDEr· uses extra data· 2017-06-26
46.4
best: 67.4 (Unified VLP)
SOTA
Paying More Attention to Saliency: Image Captioning with Saliency and Context Attention arXiv:1706.08474
Image CaptioningonFlickr30k Captions test
METEOR· uses extra data· 2017-06-26
20
best: 23 (Unified VLP)
SOTA
Paying More Attention to Saliency: Image Captioning with Saliency and Context Attention arXiv:1706.08474