{"id":"W4310007442","doi":"10.1109/acii55700.2022.9953876","title":"Analysis of Semi-Supervised Methods for Facial Expression Recognition","year":2022,"lang":"en","type":"article","venue":"","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Context (archaeology); Supervised learning; Deep learning; Machine learning; Code (set theory); Field (mathematics); Artificial neural network; Semi-supervised learning; Labeled data; Facial expression; 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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006041462,0.00007026055,0.0002021713,0.0003954084,0.0001270155,0.000004623622,0.00007686322,0.00005515048,0.03911849],"category_scores_gemma":[0.00004428835,0.00006783206,0.0002529858,0.0005526831,0.0000151793,0.00003784158,0.00003598769,0.00007956714,0.00001753595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001995315,"about_ca_system_score_gemma":0.000009853539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000332255,"about_ca_topic_score_gemma":0.000007518478,"domain_scores_codex":[0.9988638,0.0004404583,0.0002562262,0.0002210252,0.00009556324,0.0001229735],"domain_scores_gemma":[0.9994341,0.0001914795,0.0001052876,0.0001484025,0.00008357398,0.000037185],"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":[0.0003638621,0.0004639247,0.0005793946,0.00001578727,0.0007205305,5.654073e-7,0.002423838,0.00005463587,0.07838203,0.0003768572,0.005387575,0.911231],"study_design_scores_gemma":[0.02260719,0.004463045,0.04784849,0.00005879951,0.01401811,0.00003635397,0.06789403,0.05837831,0.443229,0.02814702,0.3106931,0.002626493],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3137627,0.00008158493,0.610082,0.0002422598,0.001400628,0.0007159874,0.0004837595,0.000136343,0.07309473],"genre_scores_gemma":[0.9199008,0.000008099116,0.06862663,0.0008347527,0.00009700391,0.0007765651,0.002210168,0.00002540184,0.007520581],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9086045,"threshold_uncertainty_score":0.9617599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1045445542740813,"score_gpt":0.4233404485248222,"score_spread":0.3187958942507409,"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."}}