{"id":"W4390562181","doi":"10.22541/au.170432961.11380493/v1","title":"Low-cost Geometry-based Eye Gaze Detection using Facial Landmarks Generated through Deep Learning","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Gaze; Computer science; Artificial intelligence; Leverage (statistics); Landmark; Computer vision; Face (sociological concept); Inference; Eye tracking; Set (abstract data type); Deep learning; Machine learning; Human–computer interaction","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001761218,0.0005266894,0.0004048987,0.0005843226,0.0001500914,0.0003178486,0.000598812,0.0003321682,0.002715453],"category_scores_gemma":[0.0008428231,0.0002480808,0.000373814,0.000345231,0.0002057624,0.0003894189,0.0006137023,0.0005290661,0.001121415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003940781,"about_ca_system_score_gemma":0.0005371565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005745565,"about_ca_topic_score_gemma":0.008690996,"domain_scores_codex":[0.9998654,0.00001806272,0.000004128035,0.00004309884,0.00005131593,0.00001786717],"domain_scores_gemma":[0.999799,0.00004525102,0.00002706944,0.00004524917,0.00006934292,0.00001410956],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002680826,0.00008953637,0.006596397,0.0001192344,0.0001097392,0.0001615844,0.0001098923,0.1829265,0.09647437,0.003519464,0.00787534,0.7017498],"study_design_scores_gemma":[0.000006070279,0.00003627892,0.002110268,0.00001048485,0.000009280909,0.00007628972,0.00001201632,0.981199,0.01352759,0.001695386,0.00130797,0.000009233711],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06079458,0.0003866674,0.933255,0.0001683594,0.00005314377,0.00004503097,0.0003765453,0.002948649,0.001971983],"genre_scores_gemma":[0.7268472,0.000400321,0.2662071,0.00009345574,0.00005544758,0.00008694252,0.0009392551,0.0002105505,0.005159758],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005745565,"threshold_uncertainty_score":0.01142424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02743058286720234,"score_gpt":0.286220855223201,"score_spread":0.2587902723559987,"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."}}