OpenCodePapers

image-captioning-on-nocaps-val-out-domain

Image Captioning
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeCIDErSPICEPretrain (#images)ModelNameReleaseDate
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models✓ Link124.815.11.1BBLIP-2 ViT-G FlanT5 XL (zero-shot)2023-01-30
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models✓ Link124.414.81.1BBLIP-2 ViT-G OPT 6.7B (zero-shot)2023-01-30
BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models✓ Link123.415.11.1BBLIP-2 ViT-G OPT 2.7B (zero-shot)2023-01-30
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation✓ Link115.3 14.4129MBLIP_ViT-L2022-01-28
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision✓ Link115.2-1.8BSimVLM2021-08-24
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation✓ Link111.514.2129MBLIP_CapFilt-L2022-01-28
Scaling Up Vision-Language Pre-training for Image Captioning111.3 14.0200MLEMON_large2021-11-24
OmniVL:One Foundation Model for Image-Language and Video-Language Tasks106.314.214MOmniVL2022-09-15
Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts✓ Link94.511.9Enc-Dec2021-02-17
VinVL: Revisiting Visual Representations in Vision-Language Models✓ Link 88.3 12.15.7MVinVL2021-01-02
Check out how to contribute new results.