{"task":"Pose Estimation","dataset":"CrowdPose","metric_names":["AP","AP50","AP75","APM","Test","AP Hard","AP Easy","AP Medium"],"rows":[{"id":41530,"task":"Pose Estimation","parent_task":null,"dataset":"CrowdPose","model_name":"BUCTD-W48 (w/cond. input from PETR, and generative sampling)","metrics":{"AP":"78.5","AP Easy":"83.9","AP Hard":"72.3","AP Medium":"79.0"},"paper_url":"https://arxiv.org/abs/2306.07879v2","paper_title":"Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity","paper_date":"2023-06-13","code_links":[{"title":"amathislab/BUCTD","url":"https://github.com/amathislab/BUCTD"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":41531,"task":"Pose Estimation","parent_task":null,"dataset":"CrowdPose","model_name":"ViTPose-G","metrics":{"AP":"78.3","AP Hard":"67.9","AP50":"85.3","AP75":"81.4","APM":"86.6"},"paper_url":"https://arxiv.org/abs/2204.12484v3","paper_title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","paper_date":"2022-04-26","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"vitae-transformer/vitpose","url":"https://github.com/vitae-transformer/vitpose"},{"title":"vitae-transformer/qformer","url":"https://github.com/vitae-transformer/qformer"},{"title":"JunkyByte/easy_ViTPose","url":"https://github.com/JunkyByte/easy_ViTPose"},{"title":"jaehyunnn/ViTPose_pytorch","url":"https://github.com/jaehyunnn/ViTPose_pytorch"},{"title":"gpastal24/ViTPose-Pytorch","url":"https://github.com/gpastal24/ViTPose-Pytorch"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":41532,"task":"Pose Estimation","parent_task":null,"dataset":"CrowdPose","model_name":"BUCTD-W48 (w/cond. input from PETR)","metrics":{"AP":"76.7"},"paper_url":"https://arxiv.org/abs/2306.07879v2","paper_title":"Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity","paper_date":"2023-06-13","code_links":[{"title":"amathislab/BUCTD","url":"https://github.com/amathislab/BUCTD"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":41533,"task":"Pose Estimation","parent_task":null,"dataset":"CrowdPose","model_name":"SwinV2-L 1K-MIM","metrics":{"AP":"75.5"},"paper_url":"https://arxiv.org/abs/2205.13543v2","paper_title":"Revealing the Dark Secrets of Masked Image Modeling","paper_date":"2022-05-26","code_links":[{"title":"SwinTransformer/MIM-Depth-Estimation","url":"https://github.com/SwinTransformer/MIM-Depth-Estimation"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":41534,"task":"Pose Estimation","parent_task":null,"dataset":"CrowdPose","model_name":"SwinV2-B 1K-MIM","metrics":{"AP":"74.9"},"paper_url":"https://arxiv.org/abs/2205.13543v2","paper_title":"Revealing the Dark Secrets of Masked Image Modeling","paper_date":"2022-05-26","code_links":[{"title":"SwinTransformer/MIM-Depth-Estimation","url":"https://github.com/SwinTransformer/MIM-Depth-Estimation"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":41535,"task":"Pose Estimation","parent_task":null,"dataset":"CrowdPose","model_name":"BUCTD-W48","metrics":{"AP":"72.9"},"paper_url":"https://arxiv.org/abs/2306.07879v2","paper_title":"Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity","paper_date":"2023-06-13","code_links":[{"title":"amathislab/BUCTD","url":"https://github.com/amathislab/BUCTD"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":41536,"task":"Pose Estimation","parent_task":null,"dataset":"CrowdPose","model_name":"OpenPifPaf","metrics":{"AP":"70.5","AP Easy":"78.4","AP Hard":"63.8","AP Medium":"72.1","AP50":"89.1","AP75":"76.1"},"paper_url":"https://arxiv.org/abs/2103.02440v2","paper_title":"OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association","paper_date":"2021-03-03","code_links":[{"title":"openpifpaf/openpifpaf","url":"https://github.com/openpifpaf/openpifpaf"},{"title":"openpifpaf/openpifpafwebdemo","url":"https://github.com/openpifpaf/openpifpafwebdemo"},{"title":"vita-epfl/openpifpaf","url":"https://github.com/vita-epfl/openpifpaf"},{"title":"vita-epfl/openpifpaf_posetrack","url":"https://github.com/vita-epfl/openpifpaf_posetrack"},{"title":"openpifpaf/openpifpaf_posetrack","url":"https://github.com/openpifpaf/openpifpaf_posetrack"},{"title":"yasutomo57jp/openpifpaf_ros","url":"https://github.com/yasutomo57jp/openpifpaf_ros"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":41537,"task":"Pose Estimation","parent_task":null,"dataset":"CrowdPose","model_name":"MIPNet (HRNet-W48)","metrics":{"AP":"70.0","AP Hard":"59.4","APM":"71.1"},"paper_url":"https://arxiv.org/abs/2101.11223v3","paper_title":"Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation","paper_date":"2021-01-27","code_links":[{"title":"rawalkhirodkar/MIPNet","url":"https://github.com/rawalkhirodkar/MIPNet"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":41538,"task":"Pose Estimation","parent_task":null,"dataset":"CrowdPose","model_name":"KAPAO-L","metrics":{"AP":"68.9","AP50":"89.4","AP75":"75.6","APM":"69.9","Test":"76.6"},"paper_url":"https://arxiv.org/abs/2111.08557v4","paper_title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","paper_date":"2021-11-16","code_links":[{"title":"wmcnally/kapao","url":"https://github.com/wmcnally/kapao"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":41539,"task":"Pose Estimation","parent_task":null,"dataset":"CrowdPose","model_name":"KAPAO-M","metrics":{"AP":"67.1","AP50":"88.8","AP75":"73.4","APM":"68.1","Test":"75.2"},"paper_url":"https://arxiv.org/abs/2111.08557v4","paper_title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","paper_date":"2021-11-16","code_links":[{"title":"wmcnally/kapao","url":"https://github.com/wmcnally/kapao"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":41540,"task":"Pose Estimation","parent_task":null,"dataset":"CrowdPose","model_name":"Hourglass-104","metrics":{"AP":"65.2","AP50":"85.9","AP75":"69.5","APM":"66.2"},"paper_url":"https://arxiv.org/abs/2107.03098v2","paper_title":"Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation","paper_date":"2021-07-07","code_links":[{"title":"hellojialee/OffsetGuided","url":"https://github.com/hellojialee/OffsetGuided"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":41541,"task":"Pose Estimation","parent_task":null,"dataset":"CrowdPose","model_name":"KAPAO-S","metrics":{"AP":"63.8","AP50":"87.7","AP75":"69.4","APM":"64.8","Test":"72.1"},"paper_url":"https://arxiv.org/abs/2111.08557v4","paper_title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","paper_date":"2021-11-16","code_links":[{"title":"wmcnally/kapao","url":"https://github.com/wmcnally/kapao"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":79377,"task":"Pose Estimation","parent_task":"3D","dataset":"CrowdPose","model_name":"BUCTD-W48 (w/cond. input from PETR, and generative sampling)","metrics":{"AP":"78.5","AP Easy":"83.9","AP Hard":"72.3","AP Medium":"79.0"},"paper_url":"https://arxiv.org/abs/2306.07879v2","paper_title":"Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity","paper_date":"2023-06-13","code_links":[{"title":"amathislab/BUCTD","url":"https://github.com/amathislab/BUCTD"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":79378,"task":"Pose Estimation","parent_task":"3D","dataset":"CrowdPose","model_name":"ViTPose-G","metrics":{"AP":"78.3","AP Hard":"67.9","AP50":"85.3","AP75":"81.4","APM":"86.6"},"paper_url":"https://arxiv.org/abs/2204.12484v3","paper_title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","paper_date":"2022-04-26","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"vitae-transformer/vitpose","url":"https://github.com/vitae-transformer/vitpose"},{"title":"vitae-transformer/qformer","url":"https://github.com/vitae-transformer/qformer"},{"title":"JunkyByte/easy_ViTPose","url":"https://github.com/JunkyByte/easy_ViTPose"},{"title":"jaehyunnn/ViTPose_pytorch","url":"https://github.com/jaehyunnn/ViTPose_pytorch"},{"title":"gpastal24/ViTPose-Pytorch","url":"https://github.com/gpastal24/ViTPose-Pytorch"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":79379,"task":"Pose Estimation","parent_task":"3D","dataset":"CrowdPose","model_name":"BUCTD-W48 (w/cond. input from PETR)","metrics":{"AP":"76.7"},"paper_url":"https://arxiv.org/abs/2306.07879v2","paper_title":"Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity","paper_date":"2023-06-13","code_links":[{"title":"amathislab/BUCTD","url":"https://github.com/amathislab/BUCTD"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":79380,"task":"Pose Estimation","parent_task":"3D","dataset":"CrowdPose","model_name":"SwinV2-L 1K-MIM","metrics":{"AP":"75.5"},"paper_url":"https://arxiv.org/abs/2205.13543v2","paper_title":"Revealing the Dark Secrets of Masked Image Modeling","paper_date":"2022-05-26","code_links":[{"title":"SwinTransformer/MIM-Depth-Estimation","url":"https://github.com/SwinTransformer/MIM-Depth-Estimation"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":79381,"task":"Pose Estimation","parent_task":"3D","dataset":"CrowdPose","model_name":"SwinV2-B 1K-MIM","metrics":{"AP":"74.9"},"paper_url":"https://arxiv.org/abs/2205.13543v2","paper_title":"Revealing the Dark Secrets of Masked Image Modeling","paper_date":"2022-05-26","code_links":[{"title":"SwinTransformer/MIM-Depth-Estimation","url":"https://github.com/SwinTransformer/MIM-Depth-Estimation"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":79382,"task":"Pose Estimation","parent_task":"3D","dataset":"CrowdPose","model_name":"BUCTD-W48","metrics":{"AP":"72.9"},"paper_url":"https://arxiv.org/abs/2306.07879v2","paper_title":"Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity","paper_date":"2023-06-13","code_links":[{"title":"amathislab/BUCTD","url":"https://github.com/amathislab/BUCTD"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":79383,"task":"Pose Estimation","parent_task":"3D","dataset":"CrowdPose","model_name":"OpenPifPaf","metrics":{"AP":"70.5","AP Easy":"78.4","AP Hard":"63.8","AP Medium":"72.1","AP50":"89.1","AP75":"76.1"},"paper_url":"https://arxiv.org/abs/2103.02440v2","paper_title":"OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association","paper_date":"2021-03-03","code_links":[{"title":"openpifpaf/openpifpaf","url":"https://github.com/openpifpaf/openpifpaf"},{"title":"openpifpaf/openpifpafwebdemo","url":"https://github.com/openpifpaf/openpifpafwebdemo"},{"title":"vita-epfl/openpifpaf","url":"https://github.com/vita-epfl/openpifpaf"},{"title":"vita-epfl/openpifpaf_posetrack","url":"https://github.com/vita-epfl/openpifpaf_posetrack"},{"title":"openpifpaf/openpifpaf_posetrack","url":"https://github.com/openpifpaf/openpifpaf_posetrack"},{"title":"yasutomo57jp/openpifpaf_ros","url":"https://github.com/yasutomo57jp/openpifpaf_ros"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":79384,"task":"Pose Estimation","parent_task":"3D","dataset":"CrowdPose","model_name":"MIPNet (HRNet-W48)","metrics":{"AP":"70.0","AP Hard":"59.4","APM":"71.1"},"paper_url":"https://arxiv.org/abs/2101.11223v3","paper_title":"Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation","paper_date":"2021-01-27","code_links":[{"title":"rawalkhirodkar/MIPNet","url":"https://github.com/rawalkhirodkar/MIPNet"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":79385,"task":"Pose Estimation","parent_task":"3D","dataset":"CrowdPose","model_name":"KAPAO-L","metrics":{"AP":"68.9","AP50":"89.4","AP75":"75.6","APM":"69.9","Test":"76.6"},"paper_url":"https://arxiv.org/abs/2111.08557v4","paper_title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","paper_date":"2021-11-16","code_links":[{"title":"wmcnally/kapao","url":"https://github.com/wmcnally/kapao"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":79386,"task":"Pose Estimation","parent_task":"3D","dataset":"CrowdPose","model_name":"KAPAO-M","metrics":{"AP":"67.1","AP50":"88.8","AP75":"73.4","APM":"68.1","Test":"75.2"},"paper_url":"https://arxiv.org/abs/2111.08557v4","paper_title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","paper_date":"2021-11-16","code_links":[{"title":"wmcnally/kapao","url":"https://github.com/wmcnally/kapao"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":79387,"task":"Pose Estimation","parent_task":"3D","dataset":"CrowdPose","model_name":"Hourglass-104","metrics":{"AP":"65.2","AP50":"85.9","AP75":"69.5","APM":"66.2"},"paper_url":"https://arxiv.org/abs/2107.03098v2","paper_title":"Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation","paper_date":"2021-07-07","code_links":[{"title":"hellojialee/OffsetGuided","url":"https://github.com/hellojialee/OffsetGuided"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":79388,"task":"Pose Estimation","parent_task":"3D","dataset":"CrowdPose","model_name":"KAPAO-S","metrics":{"AP":"63.8","AP50":"87.7","AP75":"69.4","APM":"64.8","Test":"72.1"},"paper_url":"https://arxiv.org/abs/2111.08557v4","paper_title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","paper_date":"2021-11-16","code_links":[{"title":"wmcnally/kapao","url":"https://github.com/wmcnally/kapao"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146836,"task":"Pose Estimation","parent_task":"1 Image, 2*2 Stitchi","dataset":"CrowdPose","model_name":"BUCTD-W48 (w/cond. input from PETR, and generative sampling)","metrics":{"AP":"78.5","AP Easy":"83.9","AP Hard":"72.3","AP Medium":"79.0"},"paper_url":"https://arxiv.org/abs/2306.07879v2","paper_title":"Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity","paper_date":"2023-06-13","code_links":[{"title":"amathislab/BUCTD","url":"https://github.com/amathislab/BUCTD"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146837,"task":"Pose Estimation","parent_task":"1 Image, 2*2 Stitchi","dataset":"CrowdPose","model_name":"ViTPose-G","metrics":{"AP":"78.3","AP Hard":"67.9","AP50":"85.3","AP75":"81.4","APM":"86.6"},"paper_url":"https://arxiv.org/abs/2204.12484v3","paper_title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","paper_date":"2022-04-26","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"vitae-transformer/vitpose","url":"https://github.com/vitae-transformer/vitpose"},{"title":"vitae-transformer/qformer","url":"https://github.com/vitae-transformer/qformer"},{"title":"JunkyByte/easy_ViTPose","url":"https://github.com/JunkyByte/easy_ViTPose"},{"title":"jaehyunnn/ViTPose_pytorch","url":"https://github.com/jaehyunnn/ViTPose_pytorch"},{"title":"gpastal24/ViTPose-Pytorch","url":"https://github.com/gpastal24/ViTPose-Pytorch"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146838,"task":"Pose Estimation","parent_task":"1 Image, 2*2 Stitchi","dataset":"CrowdPose","model_name":"BUCTD-W48 (w/cond. input from PETR)","metrics":{"AP":"76.7"},"paper_url":"https://arxiv.org/abs/2306.07879v2","paper_title":"Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity","paper_date":"2023-06-13","code_links":[{"title":"amathislab/BUCTD","url":"https://github.com/amathislab/BUCTD"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146839,"task":"Pose Estimation","parent_task":"1 Image, 2*2 Stitchi","dataset":"CrowdPose","model_name":"SwinV2-L 1K-MIM","metrics":{"AP":"75.5"},"paper_url":"https://arxiv.org/abs/2205.13543v2","paper_title":"Revealing the Dark Secrets of Masked Image Modeling","paper_date":"2022-05-26","code_links":[{"title":"SwinTransformer/MIM-Depth-Estimation","url":"https://github.com/SwinTransformer/MIM-Depth-Estimation"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146840,"task":"Pose Estimation","parent_task":"1 Image, 2*2 Stitchi","dataset":"CrowdPose","model_name":"SwinV2-B 1K-MIM","metrics":{"AP":"74.9"},"paper_url":"https://arxiv.org/abs/2205.13543v2","paper_title":"Revealing the Dark Secrets of Masked Image Modeling","paper_date":"2022-05-26","code_links":[{"title":"SwinTransformer/MIM-Depth-Estimation","url":"https://github.com/SwinTransformer/MIM-Depth-Estimation"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146841,"task":"Pose Estimation","parent_task":"1 Image, 2*2 Stitchi","dataset":"CrowdPose","model_name":"BUCTD-W48","metrics":{"AP":"72.9"},"paper_url":"https://arxiv.org/abs/2306.07879v2","paper_title":"Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity","paper_date":"2023-06-13","code_links":[{"title":"amathislab/BUCTD","url":"https://github.com/amathislab/BUCTD"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146842,"task":"Pose Estimation","parent_task":"1 Image, 2*2 Stitchi","dataset":"CrowdPose","model_name":"OpenPifPaf","metrics":{"AP":"70.5","AP Easy":"78.4","AP Hard":"63.8","AP Medium":"72.1","AP50":"89.1","AP75":"76.1"},"paper_url":"https://arxiv.org/abs/2103.02440v2","paper_title":"OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association","paper_date":"2021-03-03","code_links":[{"title":"openpifpaf/openpifpaf","url":"https://github.com/openpifpaf/openpifpaf"},{"title":"openpifpaf/openpifpafwebdemo","url":"https://github.com/openpifpaf/openpifpafwebdemo"},{"title":"vita-epfl/openpifpaf","url":"https://github.com/vita-epfl/openpifpaf"},{"title":"vita-epfl/openpifpaf_posetrack","url":"https://github.com/vita-epfl/openpifpaf_posetrack"},{"title":"openpifpaf/openpifpaf_posetrack","url":"https://github.com/openpifpaf/openpifpaf_posetrack"},{"title":"yasutomo57jp/openpifpaf_ros","url":"https://github.com/yasutomo57jp/openpifpaf_ros"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146843,"task":"Pose Estimation","parent_task":"1 Image, 2*2 Stitchi","dataset":"CrowdPose","model_name":"MIPNet (HRNet-W48)","metrics":{"AP":"70.0","AP Hard":"59.4","APM":"71.1"},"paper_url":"https://arxiv.org/abs/2101.11223v3","paper_title":"Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation","paper_date":"2021-01-27","code_links":[{"title":"rawalkhirodkar/MIPNet","url":"https://github.com/rawalkhirodkar/MIPNet"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146844,"task":"Pose Estimation","parent_task":"1 Image, 2*2 Stitchi","dataset":"CrowdPose","model_name":"KAPAO-L","metrics":{"AP":"68.9","AP50":"89.4","AP75":"75.6","APM":"69.9","Test":"76.6"},"paper_url":"https://arxiv.org/abs/2111.08557v4","paper_title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","paper_date":"2021-11-16","code_links":[{"title":"wmcnally/kapao","url":"https://github.com/wmcnally/kapao"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146845,"task":"Pose Estimation","parent_task":"1 Image, 2*2 Stitchi","dataset":"CrowdPose","model_name":"KAPAO-M","metrics":{"AP":"67.1","AP50":"88.8","AP75":"73.4","APM":"68.1","Test":"75.2"},"paper_url":"https://arxiv.org/abs/2111.08557v4","paper_title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","paper_date":"2021-11-16","code_links":[{"title":"wmcnally/kapao","url":"https://github.com/wmcnally/kapao"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146846,"task":"Pose Estimation","parent_task":"1 Image, 2*2 Stitchi","dataset":"CrowdPose","model_name":"Hourglass-104","metrics":{"AP":"65.2","AP50":"85.9","AP75":"69.5","APM":"66.2"},"paper_url":"https://arxiv.org/abs/2107.03098v2","paper_title":"Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation","paper_date":"2021-07-07","code_links":[{"title":"hellojialee/OffsetGuided","url":"https://github.com/hellojialee/OffsetGuided"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":146847,"task":"Pose Estimation","parent_task":"1 Image, 2*2 Stitchi","dataset":"CrowdPose","model_name":"KAPAO-S","metrics":{"AP":"63.8","AP50":"87.7","AP75":"69.4","APM":"64.8","Test":"72.1"},"paper_url":"https://arxiv.org/abs/2111.08557v4","paper_title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","paper_date":"2021-11-16","code_links":[{"title":"wmcnally/kapao","url":"https://github.com/wmcnally/kapao"}],"metrics_order":"[\"AP\", \"AP50\", \"AP75\", \"APM\", \"Test\", \"AP Hard\", \"AP Easy\", \"AP Medium\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}