{"id":"W2026937303","doi":"10.1109/rose.2012.6402633","title":"Gaze estimation using Kinect/PTZ camera","year":2012,"lang":"en","type":"article","venue":"","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer vision; Gaze; Artificial intelligence; Computer science; Orientation (vector space); Position (finance); Head (geology); Calibration; Multinomial logistic regression; Mathematics; Statistics","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":[0.0002757816,0.0008210591,0.0007506333,0.001266232,0.000294455,0.0004355789,0.0005624305,0.0005708,0.004195535],"category_scores_gemma":[0.0007870462,0.0003995746,0.0004450256,0.0007683189,0.0001167524,0.0008670783,0.0008004954,0.0005651081,0.00179507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002803783,"about_ca_system_score_gemma":0.0005427325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004319671,"about_ca_topic_score_gemma":0.007258158,"domain_scores_codex":[0.9995685,0.00005019295,0.00002475139,0.000136676,0.0001945418,0.00002519988],"domain_scores_gemma":[0.9997695,0.00003500305,0.00003999274,0.0000241726,0.000113737,0.0000175792],"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":[0.0006479382,0.000117282,0.00958306,0.0009856732,0.0001564009,0.000346224,0.0003751586,0.00863076,0.3502433,0.002034927,0.008140396,0.6187389],"study_design_scores_gemma":[0.0001394399,0.0004286263,0.1030018,0.0003392201,0.0001660046,0.00315961,0.0003910903,0.5212107,0.3360479,0.003295304,0.03156522,0.0002550194],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04346466,0.001572067,0.9431946,0.0001329511,0.0001194479,0.0002107838,0.002669374,0.004448224,0.004187768],"genre_scores_gemma":[0.3258508,0.002166831,0.6582767,0.000143339,0.0000656679,0.000520193,0.002483709,0.0004310437,0.01006173],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004319671,"threshold_uncertainty_score":0.01403546,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03360572298039999,"score_gpt":0.286727441025584,"score_spread":0.253121718045184,"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."}}