{"task":"Image Captioning","dataset":"MS-COCO","metric_names":["BLEU-1","BLEU-4","CIDEr","METEOR","SPICE","Test ROGUE-L"],"rows":[{"id":47263,"task":"Image Captioning","parent_task":null,"dataset":"MS-COCO","model_name":"NeuSyRE","metrics":{"BLEU-1":"79.1","BLEU-4":"37.6","CIDEr":"131.4","METEOR":"28.5","SPICE":"23.8","Test ROGUE-L":"57.7"},"paper_url":"https://www.semantic-web-journal.net/content/neusyre-neuro-symbolic-visual-understanding-and-reasoning-framework-based-scene-graph-0","paper_title":"NeuSyRE: Neuro-Symbolic Visual Understanding and Reasoning Framework based on Scene Graph Enrichment","paper_date":"2023-11-05","code_links":[{"title":"jaleedkhan/neusire","url":"https://github.com/jaleedkhan/neusire"}],"metrics_order":"[\"BLEU-1\", \"BLEU-4\", \"CIDEr\", \"METEOR\", \"SPICE\", \"Test ROGUE-L\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":758719,"task":"Image Captioning","parent_task":null,"dataset":"MS-COCO","model_name":"FLAT","metrics":{"BLEU-4":"40.5"},"paper_url":"https://paperswithcode.com/paper/flat-resampling-image-and-text-into-1d-flexible-length-aligned-transmodal-tokens-for-retrieval-and-generation","paper_title":"FLAT: Resampling Image and Text into 1D Flexible-Length Aligned Transmodal Tokens for Retrieval and Generation","paper_date":"2026-09-15","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":759367,"task":"Image Captioning","parent_task":null,"dataset":"MS-COCO","model_name":"RORPCap","metrics":{"CIDEr":"120.5"},"paper_url":"https://paperswithcode.com/paper/rorpcap-retrieval-based-objects-and-relations-prompt-for-image-captioning","paper_title":"RORPCap: Retrieval-based Objects and Relations Prompt for Image Captioning","paper_date":"2025-08-10","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]}]}