Papers › RefineCap: Concept-Aware Refinement for Image Captioning

RefineCap: Concept-Aware Refinement for Image Captioning

8 Sep 2021arXiv:2109.03529archive 2025-07-28

Yekun Chai, Shuo Jin, Junliang Xing

Automatically translating images to texts involves image scene understanding and language modeling. In this paper, we propose a novel model, termed RefineCap, that refines the output vocabulary of the language decoder using decoder-guided visual semantics, and implicitly learns the mapping between visual tag words and images. The proposed Visual-Concept Refinement method can allow the generator to attend to semantic details in the image, thereby generating more semantically descriptive captions. Our model achieves superior performance on the MS-COCO dataset in comparison with previous visual-concept based models.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderDescriptiveImage CaptioningLanguage ModelingLanguage ModellingScene UnderstandingTAG

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Captioning COCO Captions RefineCap (w/ REINFORCE) BLEU-1 80.2 #27 of 41 Archive leaderboard report
Image Captioning COCO Captions RefineCap (w/ REINFORCE) BLEU-2 64.5 #27 of 41 Archive leaderboard report
Image Captioning COCO Captions RefineCap (w/ REINFORCE) BLEU-3 49.9 #27 of 41 Archive leaderboard report
Image Captioning COCO Captions RefineCap (w/ REINFORCE) BLEU-4 37.8 #27 of 41 Archive leaderboard report
Image Captioning COCO Captions RefineCap (w/ REINFORCE) CIDER 127.2 #27 of 41 Archive leaderboard report
Image Captioning COCO Captions RefineCap (w/ REINFORCE) METEOR 28.3 #27 of 41 Archive leaderboard report
Image Captioning COCO Captions RefineCap (w/ REINFORCE) ROUGE-L 58.0 #27 of 41 Archive leaderboard report
Image Captioning COCO Captions RefineCap (w/ REINFORCE) SPICE 22.5 #27 of 41 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections