{"url":"/task/facial-landmark-detection","name":"Facial Landmark Detection","slug":"facial-landmark-detection","description_markdown":"**Facial Landmark Detection** is a computer vision task that involves detecting and localizing specific points or landmarks on a face, such as the eyes, nose, mouth, and chin. The goal is to accurately identify these landmarks in images or videos of faces in real-time and use them for various applications, such as face recognition, facial expression analysis, and head pose estimation.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Style Aggregated Network for Facial Landmark Detection](https://arxiv.org/pdf/1803.04108v4.pdf) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":139,"papers_with_code":52,"benchmarks":10,"benchmark_tables_in_archive":10,"benchmark_tables_shown":10,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":16,"subtasks":3,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/facial-landmark-detection-on-300w","slug":"facial-landmark-detection-on-300w","dataset":"300W","dataset_url":"/dataset/300w","rows_in_archive":15,"metrics":["NME","Mean Error Rate"],"first_row_in_archive_order":{"model":"D-ViT","paper_title":"Cascaded Dual Vision Transformer for Accurate Facial Landmark Detection","paper_url":"/paper/cascaded-dual-vision-transformer-for-accurate","paper_date":"2024-11-08","arxiv_id":"2411.07167","code_links":[{"title":"Human3DAIGC/AccurateFacialLandmarkDetection","url":"https://github.com/Human3DAIGC/AccurateFacialLandmarkDetection"}],"syntology":null}},{"leaderboard":"/sota/facial-landmark-detection-on-aflw-full","slug":"facial-landmark-detection-on-aflw-full","dataset":"AFLW-Full","dataset_url":"/dataset/aflw","rows_in_archive":5,"metrics":["Mean NME ","Mean NME","NME"],"first_row_in_archive_order":{"model":"FiFA","paper_title":"Fiducial Focus Augmentation for Facial Landmark Detection","paper_url":"/paper/fiducial-focus-augmentation-for-facial","paper_date":"2024-02-23","arxiv_id":"2402.15044","code_links":[],"syntology":null}},{"leaderboard":"/sota/facial-landmark-detection-on-aflw-front","slug":"facial-landmark-detection-on-aflw-front","dataset":"AFLW-Front","dataset_url":"/dataset/aflw","rows_in_archive":3,"metrics":["Mean NME","Mean NME ","NME"],"first_row_in_archive_order":{"model":"FiFA","paper_title":"Fiducial Focus Augmentation for Facial Landmark Detection","paper_url":"/paper/fiducial-focus-augmentation-for-facial","paper_date":"2024-02-23","arxiv_id":"2402.15044","code_links":[],"syntology":null}},{"leaderboard":"/sota/facial-landmark-detection-on-catflw","slug":"facial-landmark-detection-on-catflw","dataset":"CatFLW","dataset_url":"/dataset/catflw","rows_in_archive":3,"metrics":["NME"],"first_row_in_archive_order":{"model":"ELD (EfficientNetV2S)","paper_title":"Automated Detection of Cat Facial Landmarks","paper_url":"/paper/automated-detection-of-cat-facial-landmarks","paper_date":"2023-10-15","arxiv_id":"2310.09793","code_links":[],"syntology":null}},{"leaderboard":"/sota/facial-landmark-detection-on-wflw-1","slug":"facial-landmark-detection-on-wflw-1","dataset":"WFLW","dataset_url":"/dataset/wflw","rows_in_archive":3,"metrics":["NME","NME (inter-ocular)","AUC@10 (inter-ocular)","FR@10 (inter-ocular)"],"first_row_in_archive_order":{"model":"D-ViT","paper_title":"Cascaded Dual Vision Transformer for Accurate Facial Landmark Detection","paper_url":"/paper/cascaded-dual-vision-transformer-for-accurate","paper_date":"2024-11-08","arxiv_id":"2411.07167","code_links":[{"title":"Human3DAIGC/AccurateFacialLandmarkDetection","url":"https://github.com/Human3DAIGC/AccurateFacialLandmarkDetection"}],"syntology":null}},{"leaderboard":"/sota/facial-landmark-detection-on-300-vw-c","slug":"facial-landmark-detection-on-300-vw-c","dataset":"300-VW (C)","dataset_url":"/dataset/300-vw","rows_in_archive":2,"metrics":["AUC0.08 private"],"first_row_in_archive_order":{"model":"CPM+SBR+PAM","paper_title":"Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors","paper_url":"/paper/supervision-by-registration-an-unsupervised","paper_date":"2018-07-03","arxiv_id":"1807.00966","code_links":[{"title":"facebookresearch/supervision-by-registration","url":"https://github.com/facebookresearch/supervision-by-registration"}],"syntology":null}},{"leaderboard":"/sota/facial-landmark-detection-on-300w-full","slug":"facial-landmark-detection-on-300w-full","dataset":"300W (Full)","dataset_url":"/dataset/300w","rows_in_archive":2,"metrics":["Mean NME "],"first_row_in_archive_order":{"model":"TS3","paper_title":"Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection","paper_url":"/paper/teacher-supervises-students-how-to-learn-from","paper_date":"2019-08-06","arxiv_id":"1908.02116","code_links":[{"title":"D-X-Y/SAN","url":"https://github.com/D-X-Y/SAN"},{"title":"D-X-Y/landmark-detection","url":"https://github.com/D-X-Y/landmark-detection"}],"syntology":{"n":9,"n_ran":1,"n_unverified":8,"n_pointer_only":0}}},{"leaderboard":"/sota/facial-landmark-detection-on-coco-wholebody","slug":"facial-landmark-detection-on-coco-wholebody","dataset":"COCO-WholeBody","dataset_url":"/dataset/coco-wholebody","rows_in_archive":2,"metrics":["keypoint AP"],"first_row_in_archive_order":{"model":"HPRNet (Hourglass-104)","paper_title":"HPRNet: Hierarchical Point Regression for Whole-Body Human Pose Estimation","paper_url":"/paper/hprnet-hierarchical-point-regression-for","paper_date":"2021-06-08","arxiv_id":"2106.04269","code_links":[{"title":"nerminsamet/HPRNet","url":"https://github.com/nerminsamet/HPRNet"}],"syntology":null}},{"leaderboard":"/sota/facial-landmark-detection-on-cofw","slug":"facial-landmark-detection-on-cofw","dataset":"COFW","dataset_url":"/dataset/cofw","rows_in_archive":2,"metrics":["NME (inter-pupil)","NME (inter-ocular)","NME"],"first_row_in_archive_order":{"model":"D-ViT","paper_title":"Cascaded Dual Vision Transformer for Accurate Facial Landmark Detection","paper_url":"/paper/cascaded-dual-vision-transformer-for-accurate","paper_date":"2024-11-08","arxiv_id":"2411.07167","code_links":[{"title":"Human3DAIGC/AccurateFacialLandmarkDetection","url":"https://github.com/Human3DAIGC/AccurateFacialLandmarkDetection"}],"syntology":null}},{"leaderboard":"/sota/facial-landmark-detection-on-aflw2000-3d","slug":"facial-landmark-detection-on-aflw2000-3d","dataset":"AFLW2000-3D","dataset_url":"/dataset/aflw2000-3d","rows_in_archive":1,"metrics":["GTE"],"first_row_in_archive_order":{"model":"JVCR","paper_title":"Joint Voxel and Coordinate Regression for Accurate 3D Facial Landmark Localization","paper_url":"/paper/joint-voxel-and-coordinate-regression-for","paper_date":"2018-01-28","arxiv_id":"1801.09242","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/300w","name":"300W","full_name":"300 Faces-In-The-Wild","num_papers_in_archive":206},{"url":"/dataset/helen","name":"Helen","full_name":"","num_papers_in_archive":201},{"url":"/dataset/aflw","name":"AFLW","full_name":"Annotated Facial Landmarks in the Wild","num_papers_in_archive":154},{"url":"/dataset/afw","name":"AFW","full_name":"Annotated Faces in the Wild","num_papers_in_archive":154},{"url":"/dataset/lfpw","name":"LFPW","full_name":"Labeled Face Parts in the Wild","num_papers_in_archive":128},{"url":"/dataset/aflw2000-3d","name":"AFLW2000-3D","full_name":"","num_papers_in_archive":117},{"url":"/dataset/cofw","name":"COFW","full_name":"Caltech Occluded Faces in the Wild","num_papers_in_archive":114},{"url":"/dataset/wflw","name":"WFLW","full_name":"Wider Facial Landmarks in the Wild","num_papers_in_archive":108},{"url":"/dataset/coco-wholebody","name":"COCO-WholeBody","full_name":"","num_papers_in_archive":33},{"url":"/dataset/300-vw","name":"300-VW","full_name":"300 Videos in the Wild","num_papers_in_archive":6},{"url":"/dataset/catflw","name":"CatFLW","full_name":"","num_papers_in_archive":4},{"url":"/dataset/casia-face-africa","name":"CASIA-Face-Africa","full_name":"","num_papers_in_archive":3},{"url":"/dataset/thermal-face-database","name":"Thermal Face Database","full_name":"","num_papers_in_archive":1},{"url":"/dataset/sf-tl54","name":"SF-TL54: A Thermal Facial Landmark Dataset with Visual Pairs","full_name":"SF-TL54: A Thermal Facial Landmark Dataset with Visual Pairs","num_papers_in_archive":0},{"url":"/dataset/tfw-annotated-thermal-faces-in-the-wild","name":"TFW: Annotated Thermal Faces in the Wild Dataset","full_name":"TFW: Annotated Thermal Faces in the Wild Dataset","num_papers_in_archive":0},{"url":"/dataset/toronto-neuroface-dataset","name":"Toronto NeuroFace Dataset","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/3d-facial-landmark-localization","name":"3D Facial Landmark Localization"},{"url":"/task/speech-to-facial-landmark","name":"Speech to Facial Landmark"},{"url":"/task/unsupervised-facial-landmark-detection","name":"Unsupervised Facial Landmark Detection"}],"parent_tasks":[{"url":"/task/facial-recognition-and-modelling","name":"Facial Recognition and Modelling"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":52,"tagged_in_all":139,"items":[{"url":"/paper/high-resolution-representations-for-labeling","title":"High-Resolution Representations for Labeling Pixels and Regions","date":"2019-04-09","arxiv_id":"1904.04514","repositories_listed":39,"syntology":{"n":18,"n_ran":3,"n_unverified":15,"n_pointer_only":5}},{"url":"/paper/pfld-a-practical-facial-landmark-detector","title":"PFLD: A Practical Facial Landmark Detector","date":"2019-02-28","arxiv_id":"1902.10859","repositories_listed":18,"syntology":null},{"url":"/paper/faceposenet-making-a-case-for-landmark-free","title":"FacePoseNet: Making a Case for Landmark-Free Face Alignment","date":"2017-08-24","arxiv_id":"1708.07517","repositories_listed":5,"syntology":null},{"url":"/paper/fast-localization-of-facial-landmark-points","title":"Fast Localization of Facial Landmark Points","date":"2014-03-26","arxiv_id":"1403.6888","repositories_listed":3,"syntology":null},{"url":"/paper/facexformer-a-unified-transformer-for-facial","title":"FaceXFormer: A Unified Transformer for Facial Analysis","date":"2024-03-19","arxiv_id":"2403.12960","repositories_listed":2,"syntology":null},{"url":"/paper/img2pose-face-alignment-and-detection-via","title":"img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation","date":"2020-12-14","arxiv_id":"2012.07791","repositories_listed":2,"syntology":null},{"url":"/paper/whole-body-human-pose-estimation-in-the-wild","title":"Whole-Body Human Pose Estimation in the Wild","date":"2020-07-23","arxiv_id":"2007.11858","repositories_listed":2,"syntology":null},{"url":"/paper/pixel-in-pixel-net-towards-efficient-facial","title":"Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild","date":"2020-03-08","arxiv_id":"2003.03771","repositories_listed":2,"syntology":{"n":17,"n_ran":2,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/learning-to-impute-a-general-framework-for-1","title":"Learning to Impute: A General Framework for Semi-supervised Learning","date":"2019-12-22","arxiv_id":"1912.10364","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/teacher-supervises-students-how-to-learn-from","title":"Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection","date":"2019-08-06","arxiv_id":"1908.02116","repositories_listed":2,"syntology":{"n":9,"n_ran":1,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/super-realtime-facial-landmark-detection-and","title":"Super-realtime facial landmark detection and shape fitting by deep regression of shape model parameters","date":"2019-02-09","arxiv_id":"1902.03459","repositories_listed":2,"syntology":null},{"url":"/paper/look-at-boundary-a-boundary-aware-face","title":"Look at Boundary: A Boundary-Aware Face Alignment Algorithm","date":"2018-05-26","arxiv_id":"1805.10483","repositories_listed":2,"syntology":null},{"url":"/paper/mol-joint-estimation-of-micro-expression","title":"MOL: Joint Estimation of Micro-Expression, Optical Flow, and Landmark via Transformer-Graph-Style Convolution","date":"2025-06-17","arxiv_id":"2506.14511","repositories_listed":1,"syntology":null},{"url":"/paper/precise-facial-landmark-detection-by-dynamic","title":"Precise Facial Landmark Detection by Dynamic Semantic Aggregation Transformer","date":"2024-12-01","arxiv_id":"2412.00740","repositories_listed":1,"syntology":null},{"url":"/paper/cascaded-dual-vision-transformer-for-accurate","title":"Cascaded Dual Vision Transformer for Accurate Facial Landmark Detection","date":"2024-11-08","arxiv_id":"2411.07167","repositories_listed":1,"syntology":null},{"url":"/paper/popos-improving-efficient-and-robust-facial","title":"POPoS: Improving Efficient and Robust Facial Landmark Detection with Parallel Optimal Position Search","date":"2024-10-12","arxiv_id":"2410.09583","repositories_listed":1,"syntology":null},{"url":"/paper/towards-multi-domain-face-landmark-detection","title":"Towards Multi-domain Face Landmark Detection with Synthetic Data from Diffusion model","date":"2024-01-24","arxiv_id":"2401.13191","repositories_listed":1,"syntology":null},{"url":"/paper/star-loss-reducing-semantic-ambiguity-in-1","title":"STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection","date":"2023-06-05","arxiv_id":"2306.02763","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/keyposs-plug-and-play-facial-landmark","title":"KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range Multilateration","date":"2023-05-25","arxiv_id":"2305.16437","repositories_listed":1,"syntology":null},{"url":"/paper/artfacepoints-high-resolution-facial-landmark","title":"ArtFacePoints: High-resolution Facial Landmark Detection in Paintings and Prints","date":"2022-10-17","arxiv_id":"2210.09204","repositories_listed":1,"syntology":null},{"url":"/paper/shape-preserving-facial-landmarks-with-graph","title":"Shape Preserving Facial Landmarks with Graph Attention Networks","date":"2022-10-13","arxiv_id":"2210.07233","repositories_listed":1,"syntology":null},{"url":"/paper/acr-loss-adaptive-coordinate-based-regression","title":"ACR Loss: Adaptive Coordinate-based Regression Loss for Face Alignment","date":"2022-03-29","arxiv_id":"2203.15835","repositories_listed":1,"syntology":null},{"url":"/paper/facial-landmark-points-detection-using","title":"Facial Landmark Points Detection Using Knowledge Distillation-Based Neural Networks","date":"2021-11-13","arxiv_id":"2111.07047","repositories_listed":1,"syntology":null},{"url":"/paper/towards-fine-grained-image-classification","title":"Towards Fine-grained Image Classification with Generative Adversarial Networks and Facial Landmark Detection","date":"2021-08-28","arxiv_id":"2109.00891","repositories_listed":1,"syntology":null},{"url":"/paper/hprnet-hierarchical-point-regression-for","title":"HPRNet: Hierarchical Point Regression for Whole-Body Human Pose Estimation","date":"2021-06-08","arxiv_id":"2106.04269","repositories_listed":1,"syntology":null},{"url":"/paper/improving-robustness-of-facial-landmark","title":"Improving Robustness of Facial Landmark Detection by Defending Against Adversarial Attacks","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/teacher-student-asynchronous-learning-with","title":"Teacher-Student Asynchronous Learning with Multi-Source Consistency for Facial Landmark Detection","date":"2020-12-12","arxiv_id":"2012.06711","repositories_listed":1,"syntology":null},{"url":"/paper/robust-facial-landmark-detection-by-multi","title":"Robust Facial Landmark Detection by Multi-order Multi-constraint Deep Networks","date":"2020-12-09","arxiv_id":"2012.04927","repositories_listed":1,"syntology":null},{"url":"/paper/deep-structured-prediction-for-facial-1","title":"Deep Structured Prediction for Facial Landmark Detection","date":"2020-10-18","arxiv_id":"2010.09035","repositories_listed":1,"syntology":null},{"url":"/paper/anchorface-an-anchor-based-facial-landmark","title":"AnchorFace: An Anchor-based Facial Landmark Detector Across Large Poses","date":"2020-07-07","arxiv_id":"2007.03221","repositories_listed":1,"syntology":null}],"syntology_records":5,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}