{"id":"W3124332418","doi":"10.20944/preprints201810.0309.v1","title":"Highly Accurate and Fully Automatic 3–D Head Pose Estimation and Eye Gaze Estimation Using RGB-–D Sensors and 3D Morphable Models","year":2018,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Pose; Artificial intelligence; Computer science; Gaze; RGB color model; Computer vision; Head (geology); Estimator; 3D pose estimation; Face (sociological concept); Pattern recognition (psychology); Mathematics","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":[0.0002863505,0.0009475134,0.0006384383,0.001050525,0.0002401073,0.0006815311,0.000769267,0.0006744348,0.003525798],"category_scores_gemma":[0.001291635,0.0005777681,0.0006508187,0.0006385856,0.0002909803,0.0008353131,0.001314074,0.000579757,0.002285621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002689404,"about_ca_system_score_gemma":0.0005065205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002900877,"about_ca_topic_score_gemma":0.005602543,"domain_scores_codex":[0.9995677,0.00006115725,0.00002207767,0.0001315805,0.0001851962,0.00003235707],"domain_scores_gemma":[0.999585,0.00008052144,0.0000522211,0.0001311262,0.0001311554,0.00001994302],"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":[0.0002689617,0.00008933993,0.003657104,0.0002454584,0.0001636394,0.0001968922,0.0002223252,0.01843626,0.2281511,0.001635022,0.007704617,0.7392294],"study_design_scores_gemma":[0.000056026,0.0002347352,0.02623333,0.00009996529,0.000099011,0.0017641,0.0002596759,0.7264071,0.2187779,0.005148045,0.02077974,0.0001404952],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02712383,0.0005378741,0.9653467,0.0001243484,0.0000722395,0.00007005893,0.0005502331,0.0041374,0.0020374],"genre_scores_gemma":[0.3515292,0.0009816837,0.6380109,0.0002458704,0.00009849903,0.0001644016,0.001769504,0.0004929528,0.006706911],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003525798,"threshold_uncertainty_score":0.01179492,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1574434946435568,"score_gpt":0.3730588155714376,"score_spread":0.2156153209278808,"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."}}