ML Research Wiki / Benchmarks / Image Captioning / Conceptual Captions

Conceptual Captions

Image Captioning Benchmark

Performance Over Time

📊 Showing 2 results | 📏 Metric: CIDEr

Click "Edit" next to any result to modify it, or add a new result at the bottom. All changes will be reviewed before going live.

Yellow rows = Pending edits Green rows = Pending new results

Model	Paper	CIDEr	Date	Actions
ClipCap (MLP + GPT2 tuning)	ClipCap: CLIP Prefix for Image Captioning	26.71	2021-11-18
ClipCap (Transformer)	ClipCap: CLIP Prefix for Image Captioning	25.12	2021-11-18

Rank	Model	Paper	CIDEr	Date	Code
1	ClipCap (MLP + GPT2 tuning)	ClipCap: CLIP Prefix for Image Captioning	26.71	2021-11-18	📦 rmokady/clip_prefix_caption 📦 Japanese-Image-Captioning/ClipCap-for-Japanese 📦 sithu31296/image-captioning 📦 MS-P3/code7
2	ClipCap (Transformer)	ClipCap: CLIP Prefix for Image Captioning	25.12	2021-11-18	📦 rmokady/clip_prefix_caption 📦 Japanese-Image-Captioning/ClipCap-for-Japanese 📦 sithu31296/image-captioning 📦 MS-P3/code7

2021

ClipCap (MLP + GPT2 tuning)

rmokady/clip_prefix_caption Japanese-Image-Captioning/ClipCap-for-Japanese

2021

ClipCap (Transformer)

rmokady/clip_prefix_caption Japanese-Image-Captioning/ClipCap-for-Japanese