{"id":"W2067291342","doi":"10.1109/bsc.2008.4563283","title":"Using infrared illumination to improve eye & face tracking in low quality video images","year":2008,"lang":"en","type":"article","venue":"","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer vision; Artificial intelligence; Computer science; BitTorrent tracker; Pupil; Eye tracking; Face (sociological concept); Tracking (education); Image quality; Thresholding; Facial recognition system; Rotation (mathematics); Pattern recognition (psychology); Image (mathematics); Optics","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":[0.0003643601,0.0003821705,0.0003765156,0.0005820861,0.0002254608,0.000576974,0.0005937947,0.0004851098,0.001570243],"category_scores_gemma":[0.001363809,0.0002337098,0.0003068138,0.0004448472,0.0001928592,0.0007589629,0.0003372515,0.0004001477,0.0009440927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002382321,"about_ca_system_score_gemma":0.0002325307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001651138,"about_ca_topic_score_gemma":0.002366682,"domain_scores_codex":[0.9997588,0.0000300784,0.00001240615,0.0000702016,0.0001053941,0.00002323598],"domain_scores_gemma":[0.9995522,0.0001366598,0.00006688606,0.00005153758,0.0001738337,0.00001890922],"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":[0.0002553999,0.0001250813,0.003059078,0.0001341585,0.00004883363,0.0001403946,0.0001416202,0.01224505,0.3090096,0.001092323,0.001981706,0.6717668],"study_design_scores_gemma":[0.00005484466,0.0004337529,0.01111902,0.00004162339,0.00009419479,0.000821896,0.00004493489,0.5718165,0.4060465,0.0007634736,0.008700993,0.0000623623],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07354792,0.0005531415,0.9210468,0.0001044513,0.0000844772,0.00004906625,0.00005865297,0.001902871,0.002652542],"genre_scores_gemma":[0.2728278,0.000642043,0.7226837,0.0001004696,0.00007787729,0.00006306052,0.0001588962,0.0001418699,0.003304158],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001651138,"threshold_uncertainty_score":0.005253017,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05928213000485835,"score_gpt":0.3411185868187079,"score_spread":0.2818364568138496,"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."}}