OpenCodePapers

image-captioning-on-nocaps-xd-in-domain

Image Captioning
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeCIDErB1B2B3B4ROUGE-LMETEORSPICEModelNameReleaseDate
GIT: A Generative Image-to-text Transformer for Vision and Language✓ Link124.1888.8675.8659.9441.163.8233.8316.36GIT22022-05-27
GIT: A Generative Image-to-text Transformer for Vision and Language✓ Link122.488.5576.160.5341.6564.0233.4116.18GIT2022-05-27
[]()106.3685.3370.4452.9934.0260.6731.1815.51VLAF2
VIVO: Visual Vocabulary Pre-Training for Novel Object Captioning100.6282.9467.5649.6632.0759.4330.6214.7Microsoft Cognitive Services team2020-09-28
[]()90.7381.8464.0944.0325.6655.4128.3913.5test_cbs2
[]()82.8679.1462.1843.0425.6755.3726.8211.9icp2ssi1_coco_si_0.02_5_test
[]()80.6176.8957.337.7821.4953.4728.5314.99Human
[]()76.0277.6559.5839.8622.8353.9826.3511.8UpDown + ELMo + CBS
[]()74.2777.6860.3441.524.5754.4226.0411.47UpDown
[]()62.9676.4956.233.7315.1450.8423.6810.12Neural Baby Talk + CBS
[]()60.8975.9156.7835.5817.3951.4223.89.81Neural Baby Talk