{"id":"W2758776636","doi":"10.1109/iscas.2017.8050660","title":"Pupil localization for gaze estimation using unsupervised graph-based model","year":2017,"lang":"en","type":"article","venue":"","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pupil; Ellipse; Computer vision; Computer science; Artificial intelligence; Gaze; Graph; Pattern recognition (psychology); Mathematics; Optics; Theoretical computer science; Geometry; Physics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000343607,0.000786765,0.0007234022,0.001578382,0.0004239484,0.0005215376,0.001198667,0.0008457631,0.001913896],"category_scores_gemma":[0.001641249,0.000453558,0.001124168,0.0009144181,0.0004088331,0.001012444,0.0006639438,0.0008092082,0.0007823369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007483177,"about_ca_system_score_gemma":0.0006196317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01760167,"about_ca_topic_score_gemma":0.01974308,"domain_scores_codex":[0.9997022,0.00007480998,0.00001119917,0.0001286698,0.00005335609,0.00002976456],"domain_scores_gemma":[0.9994486,0.0002468257,0.00007673004,0.0000631261,0.000142193,0.0000226164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00024168,0.0001320692,0.007196656,0.0002152964,0.000250223,0.0002123426,0.0002442831,0.7383347,0.01510058,0.007904685,0.004964677,0.2252029],"study_design_scores_gemma":[0.000003964672,0.0000125374,0.0008597918,0.000005003381,0.000009811787,0.00002656233,0.00000899317,0.9965975,0.0005135494,0.00162207,0.0003350026,0.000005376846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02914292,0.0005138909,0.9673718,0.0001852774,0.00003403156,0.00005063251,0.0002545653,0.001112503,0.001334413],"genre_scores_gemma":[0.7610466,0.0008321325,0.2308612,0.000185641,0.0001141254,0.0002005985,0.0009985634,0.0003186555,0.005442438],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01760167,"threshold_uncertainty_score":0.03499842,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0729298553334527,"score_gpt":0.3207433755960155,"score_spread":0.2478135202625628,"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."}}