{"task":"Dense Captioning","dataset":"Visual Genome","metric_names":["mAP"],"rows":[{"id":131867,"task":"Dense Captioning","parent_task":null,"dataset":"Visual Genome","model_name":"ControlCap","metrics":{"mAP":"18.2"},"paper_url":"https://arxiv.org/abs/2401.17910v3","paper_title":"ControlCap: Controllable Region-level Captioning","paper_date":"2024-01-31","code_links":[{"title":"callsys/controlcap","url":"https://github.com/callsys/controlcap"}],"metrics_order":"[\"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":131868,"task":"Dense Captioning","parent_task":null,"dataset":"Visual Genome","model_name":"GRiT (ViT-B)","metrics":{"mAP":"15.5"},"paper_url":"https://arxiv.org/abs/2212.00280v1","paper_title":"GRiT: A Generative Region-to-text Transformer for Object Understanding","paper_date":"2022-12-01","code_links":[{"title":"JialianW/GRiT","url":"https://github.com/JialianW/GRiT"}],"metrics_order":"[\"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":131869,"task":"Dense Captioning","parent_task":null,"dataset":"Visual Genome","model_name":"CAG-Net","metrics":{"mAP":"10.5"},"paper_url":"http://arxiv.org/abs/1904.01410v1","paper_title":"Context and Attribute Grounded Dense Captioning","paper_date":"2019-04-02","code_links":[],"metrics_order":"[\"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":131870,"task":"Dense Captioning","parent_task":null,"dataset":"Visual Genome","model_name":"FCLN","metrics":{"mAP":"5.4"},"paper_url":"http://arxiv.org/abs/1511.07571v1","paper_title":"DenseCap: Fully Convolutional Localization Networks for Dense Captioning","paper_date":"2015-11-24","code_links":[{"title":"jcjohnson/densecap","url":"https://github.com/jcjohnson/densecap"}],"metrics_order":"[\"mAP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}