{"id":"W3164168002","doi":"10.1145/3450341.3458880","title":"Sub-centimeter 3D gaze vector accuracy on real-world tasks: an investigation of eye and motion capture calibration routines","year":2021,"lang":"en","type":"article","venue":"ACM Symposium on Eye Tracking Research and Applications","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Glenrose Rehabilitation Hospital; Alberta Health Services; Women and Children’s Health Research Institute; University of Alberta","funders":"","keywords":"Computer vision; Computer science; Gaze; Artificial intelligence; Eye tracking; Fixation (population genetics); Calibration; Motion capture; Monocular; Task (project management); Reference frame; Eye movement; Frame (networking); Motion (physics); Mathematics; Engineering","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":[0.0005754326,0.0001716807,0.0001977137,0.0003738605,0.0004005073,0.0002792099,0.0005106188,0.0001311855,0.00000433671],"category_scores_gemma":[0.0002242571,0.0001627942,0.00003243675,0.001063865,0.0002849169,0.000509968,0.0002048625,0.0004295355,0.000007616137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005289382,"about_ca_system_score_gemma":0.00009032091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001203183,"about_ca_topic_score_gemma":0.0001029358,"domain_scores_codex":[0.9979588,0.000248488,0.0003047719,0.0007237995,0.0004235807,0.0003405408],"domain_scores_gemma":[0.9976622,0.0005908298,0.0001385494,0.00101571,0.0004309313,0.0001618183],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004125118,0.0006431991,0.06130982,0.0001530152,0.00004281862,0.0000114824,0.00122184,0.0001334503,0.6769715,0.2000616,0.0003218974,0.05908814],"study_design_scores_gemma":[0.0008510682,0.0005820088,0.4668299,0.0002723874,0.0000279389,0.00000978573,0.0002149979,0.01162096,0.486451,0.03176086,0.0009040236,0.0004750634],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.964519,0.000099941,0.02265188,0.0115173,0.00005121784,0.0005397403,0.00002601396,0.0002330514,0.0003618863],"genre_scores_gemma":[0.9950263,0.000206154,0.004120037,0.0001084029,0.00009113876,0.0001599985,0.00009530061,0.00001745852,0.0001751971],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4055201,"threshold_uncertainty_score":0.6638556,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04852354243660974,"score_gpt":0.348596981867638,"score_spread":0.3000734394310283,"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."}}