{"id":"W3199287962","doi":"10.1142/s0218001421600028","title":"Facial Beauty Prediction From Facial Parts Using Multi-Task and Multi-Stream Convolutional Neural Networks","year":2021,"lang":"en","type":"article","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Face recognition and analysis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Face (sociological concept); Benchmark (surveying); Deep learning; Pattern recognition (psychology); Facial recognition system; Facial attractiveness; Task (project management); Feature extraction; Attractiveness; Artificial neural network; Computer vision; Machine learning; Speech recognition; Psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002751467,0.0001905333,0.0002533179,0.0002197893,0.0001685874,0.0004657131,0.0002705397,0.000114837,0.0001954764],"category_scores_gemma":[0.0001579596,0.0001908419,0.0001628309,0.0001664733,0.000129226,0.0007955225,0.0001490888,0.0003104229,0.00001748557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006316882,"about_ca_system_score_gemma":0.00008113399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001063009,"about_ca_topic_score_gemma":0.0001722317,"domain_scores_codex":[0.9980031,0.0001649361,0.0007740134,0.0003704924,0.0004694028,0.0002180466],"domain_scores_gemma":[0.9981983,0.0001339543,0.0004160888,0.00009520257,0.0009520971,0.0002043644],"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":[0.000040599,0.0002929183,0.008457928,0.000004343904,0.0001997299,0.0001740364,0.000521166,0.002240028,0.004697298,0.00004449355,0.00001198137,0.9833155],"study_design_scores_gemma":[0.0003365451,0.0000541635,0.00466308,0.0001150075,0.0000608021,0.0003298039,0.0004054957,0.9838426,0.007799963,0.002059512,0.0001134766,0.000219584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.307257,0.0002434134,0.6902409,0.0005089289,0.001441578,0.00004623539,0.0002359867,0.00002050939,0.000005510095],"genre_scores_gemma":[0.9861099,0.0003945226,0.01206991,0.00055802,0.0007206973,0.000002733206,0.0001218222,0.000009115712,0.00001323468],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9830959,"threshold_uncertainty_score":0.7782308,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1165349567134984,"score_gpt":0.316478840621045,"score_spread":0.1999438839075467,"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."}}