TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Natural Language Processing/Image Captioning/COCO Captions

Image Captioning on COCO Captions

Metric: BLEU-1 (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕BLEU-1▼Extra DataPaperDate↕Code
1GRIT (No VL pretraining - base)84.2NoGRIT: Faster and Better Image captioning Transfo...2022-07-20Code
2ExpansionNet v2 (No VL pretraining)83.5NoExploiting Multiple Sequence Lengths in Fast End...2022-08-13Code
3Xmodal-Ctx83.4NoBeyond a Pre-Trained Object Detector: Cross-Moda...2022-05-09Code
4Xmodal-Ctx81.5NoBeyond a Pre-Trained Object Detector: Cross-Moda...2022-05-09Code
5X-Transformer80.9NoX-Linear Attention Networks for Image Captioning2020-03-31Code
6Meshed-Memory Transformer80.8NoMeshed-Memory Transformer for Image Captioning2019-12-17Code
7Transformer_NSC80.7NoA Better Variant of Self-Critical Sequence Train...2020-03-22Code
8RefineCap (w/ REINFORCE)80.2NoRefineCap: Concept-Aware Refinement for Image Ca...2021-09-08-
9RDN80.2NoReflective Decoding Network for Image Captioning2019-08-30-