{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/refinecap-concept-aware-refinement-for-image","title":"RefineCap: Concept-Aware Refinement for Image Captioning","arxiv_id":"2109.03529","date":"2021-09-08","proceeding":null,"authors":["Yekun Chai","Shuo Jin","Junliang Xing"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2109.03529v1","url_pdf":"https://arxiv.org/pdf/2109.03529v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"tag","task_name":"TAG"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-captioning-on-coco-captions","task":"Image Captioning","dataset":"COCO Captions","model":"RefineCap (w/ REINFORCE)","rank_in_archive_order":27,"of":41,"metrics":{"BLEU-1":"80.2","BLEU-2":"64.5","BLEU-3":"49.9","BLEU-4":"37.8","CIDER":"127.2","METEOR":"28.3","ROUGE-L":"58.0","SPICE":"22.5"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}