{"task":"Object Detection","dataset":"ELEVATER","metric_names":["AP"],"rows":[{"id":62561,"task":"Object Detection","parent_task":null,"dataset":"ELEVATER","model_name":"GLIP-T","metrics":{"AP":"62.6"},"paper_url":"https://arxiv.org/abs/2204.08790v6","paper_title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","paper_date":"2022-04-19","code_links":[{"title":"microsoft/GLIP","url":"https://github.com/microsoft/GLIP"},{"title":"computer-vision-in-the-wild/cvinw_readings","url":"https://github.com/computer-vision-in-the-wild/cvinw_readings"},{"title":"microsoft/esvit","url":"https://github.com/microsoft/esvit"},{"title":"microsoft/unicl","url":"https://github.com/microsoft/unicl"},{"title":"eric-ai-lab/pevit","url":"https://github.com/eric-ai-lab/pevit"},{"title":"Computer-Vision-in-the-Wild/Elevater_Toolkit_IC","url":"https://github.com/Computer-Vision-in-the-Wild/Elevater_Toolkit_IC"},{"title":"sincerass/mvlpt","url":"https://github.com/sincerass/mvlpt"},{"title":"microsoft/klite","url":"https://github.com/microsoft/klite"},{"title":"rsCPSyEu/ovd_cod","url":"https://github.com/rsCPSyEu/ovd_cod"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":76540,"task":"Object Detection","parent_task":"3D","dataset":"ELEVATER","model_name":"GLIP-T","metrics":{"AP":"62.6"},"paper_url":"https://arxiv.org/abs/2204.08790v6","paper_title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","paper_date":"2022-04-19","code_links":[{"title":"microsoft/GLIP","url":"https://github.com/microsoft/GLIP"},{"title":"computer-vision-in-the-wild/cvinw_readings","url":"https://github.com/computer-vision-in-the-wild/cvinw_readings"},{"title":"microsoft/esvit","url":"https://github.com/microsoft/esvit"},{"title":"microsoft/unicl","url":"https://github.com/microsoft/unicl"},{"title":"eric-ai-lab/pevit","url":"https://github.com/eric-ai-lab/pevit"},{"title":"Computer-Vision-in-the-Wild/Elevater_Toolkit_IC","url":"https://github.com/Computer-Vision-in-the-Wild/Elevater_Toolkit_IC"},{"title":"sincerass/mvlpt","url":"https://github.com/sincerass/mvlpt"},{"title":"microsoft/klite","url":"https://github.com/microsoft/klite"},{"title":"rsCPSyEu/ovd_cod","url":"https://github.com/rsCPSyEu/ovd_cod"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":117067,"task":"Object Detection","parent_task":"2D Classification","dataset":"ELEVATER","model_name":"GLIP-T","metrics":{"AP":"62.6"},"paper_url":"https://arxiv.org/abs/2204.08790v6","paper_title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","paper_date":"2022-04-19","code_links":[{"title":"microsoft/GLIP","url":"https://github.com/microsoft/GLIP"},{"title":"computer-vision-in-the-wild/cvinw_readings","url":"https://github.com/computer-vision-in-the-wild/cvinw_readings"},{"title":"microsoft/esvit","url":"https://github.com/microsoft/esvit"},{"title":"microsoft/unicl","url":"https://github.com/microsoft/unicl"},{"title":"eric-ai-lab/pevit","url":"https://github.com/eric-ai-lab/pevit"},{"title":"Computer-Vision-in-the-Wild/Elevater_Toolkit_IC","url":"https://github.com/Computer-Vision-in-the-Wild/Elevater_Toolkit_IC"},{"title":"sincerass/mvlpt","url":"https://github.com/sincerass/mvlpt"},{"title":"microsoft/klite","url":"https://github.com/microsoft/klite"},{"title":"rsCPSyEu/ovd_cod","url":"https://github.com/rsCPSyEu/ovd_cod"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":124143,"task":"Object Detection","parent_task":"2D Object Detection","dataset":"ELEVATER","model_name":"GLIP-T","metrics":{"AP":"62.6"},"paper_url":"https://arxiv.org/abs/2204.08790v6","paper_title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","paper_date":"2022-04-19","code_links":[{"title":"microsoft/GLIP","url":"https://github.com/microsoft/GLIP"},{"title":"computer-vision-in-the-wild/cvinw_readings","url":"https://github.com/computer-vision-in-the-wild/cvinw_readings"},{"title":"microsoft/esvit","url":"https://github.com/microsoft/esvit"},{"title":"microsoft/unicl","url":"https://github.com/microsoft/unicl"},{"title":"eric-ai-lab/pevit","url":"https://github.com/eric-ai-lab/pevit"},{"title":"Computer-Vision-in-the-Wild/Elevater_Toolkit_IC","url":"https://github.com/Computer-Vision-in-the-Wild/Elevater_Toolkit_IC"},{"title":"sincerass/mvlpt","url":"https://github.com/sincerass/mvlpt"},{"title":"microsoft/klite","url":"https://github.com/microsoft/klite"},{"title":"rsCPSyEu/ovd_cod","url":"https://github.com/rsCPSyEu/ovd_cod"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":149862,"task":"Object Detection","parent_task":"16k","dataset":"ELEVATER","model_name":"GLIP-T","metrics":{"AP":"62.6"},"paper_url":"https://arxiv.org/abs/2204.08790v6","paper_title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","paper_date":"2022-04-19","code_links":[{"title":"microsoft/GLIP","url":"https://github.com/microsoft/GLIP"},{"title":"computer-vision-in-the-wild/cvinw_readings","url":"https://github.com/computer-vision-in-the-wild/cvinw_readings"},{"title":"microsoft/esvit","url":"https://github.com/microsoft/esvit"},{"title":"microsoft/unicl","url":"https://github.com/microsoft/unicl"},{"title":"eric-ai-lab/pevit","url":"https://github.com/eric-ai-lab/pevit"},{"title":"Computer-Vision-in-the-Wild/Elevater_Toolkit_IC","url":"https://github.com/Computer-Vision-in-the-Wild/Elevater_Toolkit_IC"},{"title":"sincerass/mvlpt","url":"https://github.com/sincerass/mvlpt"},{"title":"microsoft/klite","url":"https://github.com/microsoft/klite"},{"title":"rsCPSyEu/ovd_cod","url":"https://github.com/rsCPSyEu/ovd_cod"}],"metrics_order":"[\"AP\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}