TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/COFW

COFW

Caltech Occluded Faces in the Wild

ImagesUnknownIntroduced 2013-01-01

The Caltech Occluded Faces in the Wild (COFW) dataset is designed to present faces in real-world conditions. Faces show large variations in shape and occlusions due to differences in pose, expression, use of accessories such as sunglasses and hats and interactions with objects (e.g. food, hands, microphones,
etc.). All images were hand annotated using the same 29 landmarks as in LFPW. Both the landmark positions as well as their occluded/unoccluded state were annotated. The faces are occluded to different degrees, with large variations in the type of occlusions encountered. COFW has an average occlusion of over 23.

Source: http://www.vision.caltech.edu/xpburgos/ICCV13/#dataset Image Source: http://www.vision.caltech.edu/xpburgos/ICCV13/#dataset

Benchmarks

1 Image, 2*2 Stitchi/MAE pitch (º)1 Image, 2*2 Stitchi/MAE yaw (º)3D/MAE pitch (º)3D/MAE yaw (º)3D/NME (inter-ocular)3D/Recall at 80% precision (Landmarks Visibility)3D/NME (inter-pupil)3D/NME3D Face Modelling/NME (inter-ocular)3D Face Modelling/Recall at 80% precision (Landmarks Visibility)3D Face Modelling/NME (inter-pupil)3D Face Modelling/NME3D Face Reconstruction/NME (inter-ocular)3D Face Reconstruction/Recall at 80% precision (Landmarks Visibility)3D Face Reconstruction/NME (inter-pupil)3D Face Reconstruction/NMEFace Reconstruction/NME (inter-ocular)Face Reconstruction/Recall at 80% precision (Landmarks Visibility)Face Reconstruction/NME (inter-pupil)Face Reconstruction/NMEFacial Landmark Detection/NME (inter-pupil)Facial Landmark Detection/NME (inter-ocular)Facial Landmark Detection/NMEFacial Recognition and Modelling/NME (inter-ocular)Facial Recognition and Modelling/Recall at 80% precision (Landmarks Visibility)Facial Recognition and Modelling/NME (inter-pupil)Facial Recognition and Modelling/NMEPose Estimation/MAE pitch (º)Pose Estimation/MAE yaw (º)

Related Benchmarks

COFW-68/3D/AUC@7 (box)COFW-68/3D/NME (box)COFW-68/3D/NME (inter-ocular)COFW-68/3D Face Modelling/AUC@7 (box)COFW-68/3D Face Modelling/NME (box)COFW-68/3D Face Modelling/NME (inter-ocular)COFW-68/3D Face Reconstruction/AUC@7 (box)COFW-68/3D Face Reconstruction/NME (box)COFW-68/3D Face Reconstruction/NME (inter-ocular)COFW-68/Face Reconstruction/AUC@7 (box)COFW-68/Face Reconstruction/NME (box)COFW-68/Face Reconstruction/NME (inter-ocular)COFW-68/Facial Recognition and Modelling/AUC@7 (box)COFW-68/Facial Recognition and Modelling/NME (box)COFW-68/Facial Recognition and Modelling/NME (inter-ocular)COFW-68 (300WLP)/3D/AUC@7COFW-68 (300WLP)/3D/NME (box)COFW-68 (300WLP)/3D Face Modelling/AUC@7COFW-68 (300WLP)/3D Face Modelling/NME (box)COFW-68 (300WLP)/3D Face Reconstruction/AUC@7COFW-68 (300WLP)/3D Face Reconstruction/NME (box)COFW-68 (300WLP)/Face Reconstruction/AUC@7COFW-68 (300WLP)/Face Reconstruction/NME (box)COFW-68 (300WLP)/Facial Recognition and Modelling/AUC@7COFW-68 (300WLP)/Facial Recognition and Modelling/NME (box)

Statistics

Papers
114
Benchmarks
29

Links

Homepage

Tasks

1 Image, 2*2 Stitchi3D3D Face Modelling3D Face ReconstructionFace AlignmentFace ReconstructionFacial Landmark DetectionFacial Recognition and ModellingHead Pose EstimationPose Estimation