{"id":"W3160049074","doi":"10.1109/icpr48806.2021.9412066","title":"Detection and Correspondence Matching of Corneal Reflections for Eye Tracking Using Deep Learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer vision; Artificial intelligence; Computer science; Eye tracking; Gaze; BitTorrent tracker; Eye tracking on the ISS; Rotation (mathematics); Optics; Physics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002100759,0.00007144636,0.0001209343,0.0001085176,0.0002625905,0.00006791272,0.0001240051,0.00006353317,0.000003786388],"category_scores_gemma":[0.0001626949,0.00007432049,0.00003732033,0.0003447031,0.0000423889,0.0002131168,0.00008818882,0.0001530109,7.131387e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002766703,"about_ca_system_score_gemma":0.00003246789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003657551,"about_ca_topic_score_gemma":0.000114679,"domain_scores_codex":[0.9992936,0.00005043769,0.0001557115,0.0002651125,0.00007870126,0.00015647],"domain_scores_gemma":[0.9994122,0.0001783158,0.00008976593,0.0001411294,0.0001529295,0.0000256378],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001075935,0.00003168376,0.002522819,0.00003224004,0.00001634791,0.00001039184,0.0007079493,0.002518791,0.8150808,0.01508222,9.400161e-7,0.1639851],"study_design_scores_gemma":[0.0004238477,0.0001933021,0.02078375,0.00007673175,0.00002480947,0.0002923149,0.00115329,0.5541757,0.4127414,0.009577751,0.0003180031,0.0002390428],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3898552,0.00005040807,0.6096635,0.0000499116,0.0001149015,0.00003170051,1.595808e-7,0.0001126546,0.0001215075],"genre_scores_gemma":[0.8486895,0.000005315003,0.1511458,0.00001892168,0.00001471282,0.000003572725,2.896219e-7,0.000005118248,0.0001167367],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.551657,"threshold_uncertainty_score":0.3030702,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04105118042782398,"score_gpt":0.3293669713504438,"score_spread":0.2883157909226198,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}