{"task":"Image Captioning","dataset":"COCO Captions test","metric_names":["BLEU-4","CIDEr","METEOR","SPICE"],"rows":[{"id":47103,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions test","model_name":"From Captions to Visual Concepts and Back","metrics":{"BLEU-4":"56.7","CIDEr":"92.5","METEOR":"33.1"},"paper_url":"http://arxiv.org/abs/1411.4952v3","paper_title":"From Captions to Visual Concepts and Back","paper_date":"2014-11-18","code_links":[{"title":"s-gupta/visual-concepts","url":"https://github.com/s-gupta/visual-concepts"}],"metrics_order":"[\"BLEU-4\", \"CIDEr\", \"METEOR\", \"SPICE\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47104,"task":"Image Captioning","parent_task":null,"dataset":"COCO Captions test","model_name":"Unified VLP","metrics":{"BLEU-4":"36.5","CIDEr":"116.9","METEOR":"28.4","SPICE":"21.2"},"paper_url":"https://arxiv.org/abs/1909.11059v3","paper_title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","paper_date":"2019-09-24","code_links":[{"title":"rmokady/clip_prefix_caption","url":"https://github.com/rmokady/clip_prefix_caption"},{"title":"LuoweiZhou/VLP","url":"https://github.com/LuoweiZhou/VLP"},{"title":"WebQnA/WebQA_Baseline","url":"https://github.com/WebQnA/WebQA_Baseline"}],"metrics_order":"[\"BLEU-4\", \"CIDEr\", \"METEOR\", \"SPICE\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]}]}