{"url":"/task/gaze-estimation","name":"Gaze Estimation","slug":"gaze-estimation","description_markdown":"**Gaze Estimation** is a task to predict where a person is looking at given the person’s full face. The task contains two directions: 3-D gaze vector and 2-D gaze position estimation. 3-D gaze vector estimation is to predict the gaze vector, which is usually used in the automotive safety. 2-D gaze position estimation is to predict the horizontal and vertical coordinates on a 2-D screen, which allows utilizing gaze point to control a cursor for human-machine interaction.\n\n\n<span class=\"description-source\">Source: [A Generalized and Robust Method Towards Practical Gaze Estimation on Smart Phone ](https://arxiv.org/abs/1910.07331)</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":248,"papers_with_code":86,"benchmarks":11,"benchmark_tables_in_archive":11,"benchmark_tables_shown":11,"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":18,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/gaze-estimation-on-mpii-gaze","slug":"gaze-estimation-on-mpii-gaze","dataset":"MPII Gaze","dataset_url":"/dataset/mpiigaze","rows_in_archive":6,"metrics":["Angular Error"],"first_row_in_archive_order":{"model":"FAZE","paper_title":"Few-Shot Adaptive Gaze Estimation","paper_url":"/paper/few-shot-adaptive-gaze-estimation","paper_date":"2019-05-06","arxiv_id":"1905.01941","code_links":[{"title":"NVlabs/few_shot_gaze","url":"https://github.com/NVlabs/few_shot_gaze"}],"syntology":null}},{"leaderboard":"/sota/gaze-estimation-on-gaze360","slug":"gaze-estimation-on-gaze360","dataset":"Gaze360","dataset_url":"/dataset/gaze360","rows_in_archive":4,"metrics":["Angular Error"],"first_row_in_archive_order":{"model":"MCGaze","paper_title":"End-to-end Video Gaze Estimation via Capturing Head-face-eye Spatial-temporal Interaction Context","paper_url":"/paper/end-to-end-video-gaze-estimation-via","paper_date":"2023-10-27","arxiv_id":"2310.18131","code_links":[{"title":"zgchen33/mcgaze","url":"https://github.com/zgchen33/mcgaze"}],"syntology":null}},{"leaderboard":"/sota/gaze-estimation-on-eyediap-floating-target","slug":"gaze-estimation-on-eyediap-floating-target","dataset":"EYEDIAP (floating target)","dataset_url":"/dataset/eyediap","rows_in_archive":2,"metrics":["Angular Error"],"first_row_in_archive_order":{"model":"RecurrentGaze (Temporal)","paper_title":"Recurrent CNN for 3D Gaze Estimation using Appearance and Shape Cues","paper_url":"/paper/recurrent-cnn-for-3d-gaze-estimation-using","paper_date":"2018-05-08","arxiv_id":"1805.03064","code_links":[{"title":"crisie/RecurrentGaze","url":"https://github.com/crisie/RecurrentGaze"},{"title":"crisie/CRNN-Gaze","url":"https://github.com/crisie/CRNN-Gaze"},{"title":"code-implementation1/Code9","url":"https://github.com/code-implementation1/Code9/tree/main/CRNN"}],"syntology":{"n":10,"n_ran":0,"n_unverified":10,"n_pointer_only":0}}},{"leaderboard":"/sota/gaze-estimation-on-eyediap-screen-target","slug":"gaze-estimation-on-eyediap-screen-target","dataset":"EYEDIAP (screen target)","dataset_url":"/dataset/eyediap","rows_in_archive":2,"metrics":["Angular Error"],"first_row_in_archive_order":{"model":"RecurrentGaze (Static)","paper_title":"Recurrent CNN for 3D Gaze Estimation using Appearance and Shape Cues","paper_url":"/paper/recurrent-cnn-for-3d-gaze-estimation-using","paper_date":"2018-05-08","arxiv_id":"1805.03064","code_links":[{"title":"crisie/RecurrentGaze","url":"https://github.com/crisie/RecurrentGaze"},{"title":"crisie/CRNN-Gaze","url":"https://github.com/crisie/CRNN-Gaze"},{"title":"code-implementation1/Code9","url":"https://github.com/code-implementation1/Code9/tree/main/CRNN"}],"syntology":{"n":10,"n_ran":0,"n_unverified":10,"n_pointer_only":0}}},{"leaderboard":"/sota/gaze-estimation-on-gazecapture","slug":"gaze-estimation-on-gazecapture","dataset":"GazeCapture","dataset_url":"/dataset/gazecapture","rows_in_archive":2,"metrics":["Euclidean Mean Error (EME)","FPS"],"first_row_in_archive_order":{"model":"Ensemble Calibration","paper_title":"One Eye is All You Need: Lightweight Ensembles for Gaze Estimation with Single Encoders","paper_url":"/paper/one-eye-is-all-you-need-lightweight-ensembles","paper_date":"2022-11-22","arxiv_id":"2211.11936","code_links":[{"title":"rishipython/one-eye-is-all-you-need-lightweight-ensembles-for-gaze-estimation-with-single-encoders","url":"https://github.com/rishipython/one-eye-is-all-you-need-lightweight-ensembles-for-gaze-estimation-with-single-encoders"}],"syntology":null}},{"leaderboard":"/sota/gaze-estimation-on-eth-xgaze","slug":"gaze-estimation-on-eth-xgaze","dataset":"ETH-XGaze","dataset_url":"/dataset/eth-xgaze","rows_in_archive":1,"metrics":["Angular Error"],"first_row_in_archive_order":{"model":"ETHXGaze","paper_title":"ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation","paper_url":"/paper/eth-xgaze-a-large-scale-dataset-for-gaze","paper_date":"2020-07-31","arxiv_id":"2007.15837","code_links":[{"title":"xucong-zhang/ETH-XGaze","url":"https://github.com/xucong-zhang/ETH-XGaze"}],"syntology":null}},{"leaderboard":"/sota/gaze-estimation-on-eyediap","slug":"gaze-estimation-on-eyediap","dataset":"EYEDIAP","dataset_url":"/dataset/eyediap","rows_in_archive":1,"metrics":["Mean Angle Error"],"first_row_in_archive_order":{"model":"AGE-Net","paper_title":"Agent-Guided Gaze Estimation Network by Two-Eye Asymmetry Exploration","paper_url":"/paper/agent-guided-gaze-estimation-network-by-two","paper_date":"2024-10-30","arxiv_id":null,"code_links":[{"title":"iszff/AGE-Net","url":"https://github.com/iszff/AGE-Net"}],"syntology":null}},{"leaderboard":"/sota/gaze-estimation-on-mpiigaze-1","slug":"gaze-estimation-on-mpiigaze-1","dataset":"MPIIGaze","dataset_url":"/dataset/mpiigaze","rows_in_archive":1,"metrics":["Mean Angle Error"],"first_row_in_archive_order":{"model":"AGE-Net","paper_title":"Agent-Guided Gaze Estimation Network by Two-Eye Asymmetry Exploration","paper_url":"/paper/agent-guided-gaze-estimation-network-by-two","paper_date":"2024-10-30","arxiv_id":null,"code_links":[{"title":"iszff/AGE-Net","url":"https://github.com/iszff/AGE-Net"}],"syntology":null}},{"leaderboard":"/sota/gaze-estimation-on-mpsgaze","slug":"gaze-estimation-on-mpsgaze","dataset":"MPSGaze","dataset_url":"/dataset/mpsgaze","rows_in_archive":1,"metrics":["Angular Error"],"first_row_in_archive_order":{"model":"ResNet18","paper_title":"ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation","paper_url":"/paper/eth-xgaze-a-large-scale-dataset-for-gaze","paper_date":"2020-07-31","arxiv_id":"2007.15837","code_links":[{"title":"xucong-zhang/ETH-XGaze","url":"https://github.com/xucong-zhang/ETH-XGaze"}],"syntology":null}},{"leaderboard":"/sota/gaze-estimation-on-rt-gene","slug":"gaze-estimation-on-rt-gene","dataset":"RT-GENE","dataset_url":"/dataset/rt-gene","rows_in_archive":1,"metrics":["Angular Error"],"first_row_in_archive_order":{"model":"RT-GENE 4 model ensemble","paper_title":"RT-GENE: Real-Time Eye Gaze Estimation in Natural Environments","paper_url":"/paper/rt-gene-real-time-eye-gaze-estimation-in","paper_date":"2018-09-01","arxiv_id":null,"code_links":[{"title":"Tobias-Fischer/rt_gene","url":"https://github.com/Tobias-Fischer/rt_gene"}],"syntology":null}},{"leaderboard":"/sota/gaze-estimation-on-ut-multi-view","slug":"gaze-estimation-on-ut-multi-view","dataset":"UT Multi-view","dataset_url":null,"rows_in_archive":1,"metrics":["Angular Error"],"first_row_in_archive_order":{"model":"RT-GENE 4 model ensemble","paper_title":"RT-GENE: Real-Time Eye Gaze Estimation in Natural Environments","paper_url":"/paper/rt-gene-real-time-eye-gaze-estimation-in","paper_date":"2018-09-01","arxiv_id":null,"code_links":[{"title":"Tobias-Fischer/rt_gene","url":"https://github.com/Tobias-Fischer/rt_gene"}],"syntology":null}}],"datasets":[{"url":"/dataset/ava","name":"AVA","full_name":"Atomic Visual Actions","num_papers_in_archive":113},{"url":"/dataset/mpiigaze","name":"MPIIGaze","full_name":"","num_papers_in_archive":78},{"url":"/dataset/gaze360","name":"Gaze360","full_name":"Physically Unconstrained Gaze Estimation in the Wild","num_papers_in_archive":62},{"url":"/dataset/eyediap","name":"EYEDIAP","full_name":"","num_papers_in_archive":57},{"url":"/dataset/eth-xgaze","name":"ETH-XGaze","full_name":"","num_papers_in_archive":56},{"url":"/dataset/gazecapture","name":"GazeCapture","full_name":"Eye Tracking for Everyone","num_papers_in_archive":56},{"url":"/dataset/openeds","name":"OpenEDS","full_name":"","num_papers_in_archive":31},{"url":"/dataset/rt-gene","name":"RT-GENE","full_name":"","num_papers_in_archive":29},{"url":"/dataset/openeds2020","name":"OpenEDS2020","full_name":"","num_papers_in_archive":7},{"url":"/dataset/uco-laeo","name":"UCO-LAEO","full_name":"","num_papers_in_archive":6},{"url":"/dataset/ava-laeo","name":"AVA-LAEO","full_name":"","num_papers_in_archive":5},{"url":"/dataset/gd","name":"GD","full_name":"Gaze-Detection","num_papers_in_archive":3},{"url":"/dataset/gafa","name":"GAFA","full_name":"Gaze from afar dataset","num_papers_in_archive":2},{"url":"/dataset/parks-gaze","name":"PARKS-Gaze","full_name":"","num_papers_in_archive":2},{"url":"/dataset/ego-ch-gaze","name":"EGO-CH-Gaze","full_name":"Learning to Detect Attended Objects in Cultural Sites with Gaze Signals and Weak Object Supervision","num_papers_in_archive":1},{"url":"/dataset/eyeinfo","name":"EyeInfo","full_name":"","num_papers_in_archive":1},{"url":"/dataset/lisa-gaze-dataset","name":"LISA Gaze Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mpsgaze","name":"MPSGaze","full_name":"Multi-Person Swap Gaze Dataset","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":86,"tagged_in_all":248,"items":[{"url":"/paper/fine-grained-head-pose-estimation-without","title":"Fine-Grained Head Pose Estimation Without Keypoints","date":"2017-10-02","arxiv_id":"1710.00925","repositories_listed":14,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/an-improved-one-millisecond-mobile-backbone","title":"MobileOne: An Improved One millisecond Mobile Backbone","date":"2022-06-08","arxiv_id":"2206.04040","repositories_listed":10,"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":2}},{"url":"/paper/learning-from-simulated-and-unsupervised","title":"Learning from Simulated and Unsupervised Images through Adversarial Training","date":"2016-12-22","arxiv_id":"1612.07828","repositories_listed":9,"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/appearance-based-gaze-estimation-with-deep","title":"Appearance-based Gaze Estimation With Deep Learning: A Review and Benchmark","date":"2021-04-26","arxiv_id":"2104.12668","repositories_listed":7,"syntology":null},{"url":"/paper/mpiigaze-real-world-dataset-and-deep","title":"MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation","date":"2017-11-24","arxiv_id":"1711.09017","repositories_listed":6,"syntology":null},{"url":"/paper/appearance-based-gaze-estimation-in-the-wild","title":"Appearance-Based Gaze Estimation in the Wild","date":"2015-04-11","arxiv_id":"1504.02863","repositories_listed":6,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/its-written-all-over-your-face-full-face","title":"It's Written All Over Your Face: Full-Face Appearance-Based Gaze Estimation","date":"2016-11-27","arxiv_id":"1611.08860","repositories_listed":4,"syntology":null},{"url":"/paper/weakly-supervised-gaze-estimation-from","title":"3DGazeNet: Generalizing Gaze Estimation with Weak-Supervision from Synthetic Views","date":"2022-12-06","arxiv_id":"2212.02997","repositories_listed":3,"syntology":null},{"url":"/paper/recurrent-cnn-for-3d-gaze-estimation-using","title":"Recurrent CNN for 3D Gaze Estimation using Appearance and Shape Cues","date":"2018-05-08","arxiv_id":"1805.03064","repositories_listed":3,"syntology":{"n":10,"n_ran":0,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/tinytracker-ultra-fast-and-ultra-low-power","title":"TinyTracker: Ultra-Fast and Ultra-Low-Power Edge Vision In-Sensor for Gaze Estimation","date":"2023-07-15","arxiv_id":"2307.07813","repositories_listed":2,"syntology":null},{"url":"/paper/l2cs-net-fine-grained-gaze-estimation-in","title":"L2CS-Net: Fine-Grained Gaze Estimation in Unconstrained Environments","date":"2022-03-07","arxiv_id":"2203.03339","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_unverified":5,"n_pointer_only":2}},{"url":"/paper/weakly-supervised-physically-unconstrained","title":"Weakly-Supervised Physically Unconstrained Gaze Estimation","date":"2021-05-20","arxiv_id":"2105.09803","repositories_listed":2,"syntology":null},{"url":"/paper/self-learning-transformations-for-improving","title":"Self-Learning Transformations for Improving Gaze and Head Redirection","date":"2020-10-23","arxiv_id":"2010.12307","repositories_listed":2,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/geddnet-a-network-for-gaze-estimation-with","title":"Towards High Performance Low Complexity Calibration in Appearance Based Gaze Estimation","date":"2020-01-25","arxiv_id":"2001.09284","repositories_listed":2,"syntology":null},{"url":"/paper/gaze360-physically-unconstrained-gaze","title":"Gaze360: Physically Unconstrained Gaze Estimation in the Wild","date":"2019-10-22","arxiv_id":"1910.10088","repositories_listed":2,"syntology":null},{"url":"/paper/ritnet-real-time-semantic-segmentation-of-the","title":"RITnet: Real-time Semantic Segmentation of the Eye for Gaze Tracking","date":"2019-10-01","arxiv_id":"1910.00694","repositories_listed":2,"syntology":null},{"url":"/paper/learning-to-find-eye-region-landmarks-for","title":"Learning to Find Eye Region Landmarks for Remote Gaze Estimation in Unconstrained Settings","date":"2018-05-12","arxiv_id":"1805.04771","repositories_listed":2,"syntology":null},{"url":"/paper/faster-gaze-prediction-with-dense-networks","title":"Faster gaze prediction with dense networks and Fisher pruning","date":"2018-01-17","arxiv_id":"1801.05787","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/eye-tracking-for-everyone","title":"Eye Tracking for Everyone","date":"2016-06-18","arxiv_id":"1606.05814","repositories_listed":2,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/inference-time-gaze-refinement-for-micro","title":"Inference-Time Gaze Refinement for Micro-Expression Recognition: Enhancing Event-Based Eye Tracking with Motion-Aware Post-Processing","date":"2025-06-14","arxiv_id":"2506.12524","repositories_listed":1,"syntology":null},{"url":"/paper/trade-offs-in-privacy-preserving-eye-tracking","title":"Trade-offs in Privacy-Preserving Eye Tracking through Iris Obfuscation: A Benchmarking Study","date":"2025-04-14","arxiv_id":"2504.10267","repositories_listed":1,"syntology":null},{"url":"/paper/adapting-robot-s-explanation-for-failures","title":"Adapting Robot's Explanation for Failures Based on Observed Human Behavior in Human-Robot Collaboration","date":"2025-04-13","arxiv_id":"2504.09717","repositories_listed":1,"syntology":null},{"url":"/paper/iris-style-transfer-enhancing-iris","title":"Iris Style Transfer: Enhancing Iris Recognition with Style Features and Privacy Preservation through Neural Style Transfer","date":"2025-03-06","arxiv_id":"2503.04707","repositories_listed":1,"syntology":null},{"url":"/paper/securegaze-defending-gaze-estimation-against","title":"SecureGaze: Defending Gaze Estimation Against Backdoor Attacks","date":"2025-02-27","arxiv_id":"2502.20306","repositories_listed":1,"syntology":null},{"url":"/paper/agent-guided-gaze-estimation-network-by-two","title":"Agent-Guided Gaze Estimation Network by Two-Eye Asymmetry Exploration","date":"2024-10-30","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/upper-body-pose-based-gaze-estimation-for","title":"Upper-Body Pose-based Gaze Estimation for Privacy-Preserving 3D Gaze Target Detection","date":"2024-09-26","arxiv_id":"2409.17886","repositories_listed":1,"syntology":null},{"url":"/paper/merging-multiple-datasets-for-improved","title":"Merging Multiple Datasets for Improved Appearance-Based Gaze Estimation","date":"2024-09-02","arxiv_id":"2409.00912","repositories_listed":1,"syntology":null},{"url":"/paper/gem-context-aware-gaze-estimation-with-visual","title":"GEM: Context-Aware Gaze EstiMation with Visual Search Behavior Matching for Chest Radiograph","date":"2024-08-10","arxiv_id":"2408.05502","repositories_listed":1,"syntology":null},{"url":"/paper/2408-00950","title":"PrivateGaze: Preserving User Privacy in Black-box Mobile Gaze Tracking Services","date":"2024-08-01","arxiv_id":"2408.00950","repositories_listed":1,"syntology":null},{"url":"/paper/learning-gaze-aware-compositional-gan","title":"Learning Gaze-aware Compositional GAN","date":"2024-05-31","arxiv_id":"2405.20643","repositories_listed":1,"syntology":null}],"syntology_records":9,"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"}}