{"id":"W2957144205","doi":"10.1109/fg.2019.8756609","title":"Self-Supervised Learning of Face Representations for Video Face Clustering","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Face recognition and analysis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Cluster analysis; Artificial intelligence; Face (sociological concept); Benchmark (surveying); Identification (biology); Pattern recognition (psychology); Identity (music); Unsupervised learning; Facial recognition system; Face detection; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008985153,0.0009752352,0.000869189,0.001222767,0.0005026612,0.0007606387,0.001815971,0.001235473,0.002401627],"category_scores_gemma":[0.002857887,0.0003724376,0.0008825102,0.0008949942,0.0006222907,0.001167605,0.0009412222,0.001494181,0.001676581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001182969,"about_ca_system_score_gemma":0.0008746922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005845741,"about_ca_topic_score_gemma":0.009860963,"domain_scores_codex":[0.9993135,0.0001296989,0.00002389585,0.0003109198,0.0001275903,0.00009434961],"domain_scores_gemma":[0.9991629,0.000212696,0.00009035304,0.0002295775,0.0002523235,0.00005210848],"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":[0.0003540376,0.0005232245,0.003179217,0.0001543534,0.0001741247,0.00007922618,0.0001466516,0.3075529,0.01989007,0.005660461,0.0168581,0.6454276],"study_design_scores_gemma":[0.000006112841,0.00002401393,0.0003898822,0.00000531064,0.000007172177,0.00003334681,0.00001997563,0.99288,0.003803209,0.00230666,0.0005185368,0.000005758128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06766559,0.0005029269,0.9249153,0.0002379438,0.00008538972,0.0001394069,0.0005891093,0.003319735,0.002544648],"genre_scores_gemma":[0.6348537,0.000348928,0.3513392,0.0003346999,0.000151072,0.0002565505,0.004748687,0.0003996885,0.007567411],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005845741,"threshold_uncertainty_score":0.01162344,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03540712105866694,"score_gpt":0.2971534925698953,"score_spread":0.2617463715112283,"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."}}