{"id":"W2749038514","doi":"10.1109/tpami.2017.2737423","title":"Photorealistic Monocular Gaze Redirection Using Machine Learning","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Gaze; Computer science; Monocular; Artificial intelligence; Computer vision; Deep learning; Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003086668,0.0002413145,0.0003495443,0.0005213361,0.001101392,0.000348407,0.0006835485,0.0001023338,0.00005058097],"category_scores_gemma":[0.00002410151,0.0002206746,0.0002286831,0.0004180251,0.000145221,0.0002792716,0.00001463054,0.0004726899,0.00001411551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005197106,"about_ca_system_score_gemma":0.00001493415,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00935137,"about_ca_topic_score_gemma":0.002102597,"domain_scores_codex":[0.9984813,0.00009414958,0.0003085303,0.0006195009,0.000224032,0.0002724653],"domain_scores_gemma":[0.9986419,0.00007682857,0.0002430799,0.0008506226,0.00008191167,0.0001056638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001056933,0.0001296189,0.009649087,0.000014434,0.000499945,0.00003817569,0.0001324967,0.0217726,0.002453262,0.00009829956,0.000001403791,0.9652001],"study_design_scores_gemma":[0.00008704346,0.00009442928,0.004828499,0.0000294113,0.0003757111,0.00002775926,0.00001317819,0.8687319,0.1252047,0.0002772527,0.00008294923,0.0002471768],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02018746,0.0001055811,0.9787851,0.0002668824,0.0002603875,0.00007650909,0.00001857008,0.0002084317,0.00009105079],"genre_scores_gemma":[0.9955075,0.0002598127,0.003938299,0.00007109839,0.00002070023,0.00001076378,0.000003533961,0.00001344014,0.0001748289],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.97532,"threshold_uncertainty_score":0.9972454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03594395738738556,"score_gpt":0.292963527423259,"score_spread":0.2570195700358735,"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."}}