{"id":"W2772390091","doi":"10.1007/s11263-019-01165-5","title":"Learning from Longitudinal Face Demonstration—Where Tractable Deep Modeling Meets Inverse Reinforcement Learning","year":2019,"lang":"en","type":"preprint","venue":"International Journal of Computer Vision","topic":"Face recognition and analysis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Face (sociological concept); Reinforcement learning; Convolutional neural network; Path (computing); Deep learning; Probabilistic logic; Generative model; Machine learning; Bayesian probability; Trajectory; Generative grammar","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":[0.0014995,0.000950107,0.001561153,0.0003460408,0.0004823147,0.001147383,0.001656116,0.002425894,0.004235435],"category_scores_gemma":[0.0102481,0.0009582919,0.0005653673,0.0003343898,0.001446393,0.002800341,0.002641501,0.003448961,0.0006064934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001062445,"about_ca_system_score_gemma":0.00161842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007741715,"about_ca_topic_score_gemma":0.007123583,"domain_scores_codex":[0.9996147,0.0001140751,0.00001650529,0.0001213534,0.00006702485,0.0000662871],"domain_scores_gemma":[0.9970071,0.002109808,0.0001909965,0.0002869738,0.0002168937,0.0001882299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002237181,0.000119363,0.00157423,0.0001100417,0.00004544694,0.0001659347,0.000100015,0.9095134,0.002413997,0.03342349,0.002862957,0.0494474],"study_design_scores_gemma":[0.000004463965,0.000008081731,0.0000412631,0.000003007994,0.000001649543,0.00000779788,0.000003309617,0.9911153,0.0001369578,0.008599361,0.00007677677,0.000001977886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04050111,0.0002981458,0.9551916,0.0009358078,0.00005752803,0.00004466171,0.0001136081,0.0005731263,0.002284469],"genre_scores_gemma":[0.9141859,0.0001754292,0.07959381,0.0002841084,0.00006889839,0.0001506536,0.0002134076,0.0001660521,0.005161838],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007741715,"threshold_uncertainty_score":0.01539332,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02653599767657171,"score_gpt":0.2850311849948104,"score_spread":0.2584951873182387,"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."}}