{"id":"W4403570206","doi":"10.1109/iccv51701.2025.00949","title":"SynFER: Towards Boosting Facial Expression Recognition With Synthetic Data","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada); Kootenay Association for Science & Technology","funders":"National Natural Science Foundation of China; King Abdullah University of Science and Technology; Guangdong Provincial Key Laboratory of Urology","keywords":"Boosting (machine learning); Facial expression recognition; Computer science; Facial expression; Artificial intelligence; Pattern recognition (psychology); Facial recognition system","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000447655,0.0003670675,0.0003864988,0.0002679147,0.0001425286,0.0001107235,0.000612116,0.0006208863,0.008600765],"category_scores_gemma":[0.0001821894,0.0003003394,0.00008529967,0.0001223835,0.00006916053,0.0001408286,0.001164007,0.0008444163,0.0006266633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005261077,"about_ca_system_score_gemma":0.0001968102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003613801,"about_ca_topic_score_gemma":0.0001091041,"domain_scores_codex":[0.9973695,0.0003018515,0.000444239,0.001262945,0.0002869178,0.0003345626],"domain_scores_gemma":[0.9978338,0.0001089208,0.0002605034,0.001475038,0.0002167077,0.0001049987],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000314041,0.0004115407,0.0001317864,0.0004012488,0.0002310047,0.00004117793,0.0008771959,0.000007700162,0.0002197444,0.0001669494,0.03347064,0.963727],"study_design_scores_gemma":[0.04159239,0.004346551,0.03842898,0.1103916,0.01247833,0.001942277,0.03829088,0.01725611,0.09891719,0.09883769,0.5106099,0.02690806],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.02284227,0.0002053504,0.04374508,0.0007848605,0.004502162,0.001224298,0.002096529,0.0007461075,0.9238533],"genre_scores_gemma":[0.9046991,0.0002473619,0.02150703,0.001530489,0.001362701,0.0005188566,0.02197327,0.0001166176,0.0480445],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.9368189,"threshold_uncertainty_score":0.9999449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1440123440278689,"score_gpt":0.3705121266819698,"score_spread":0.2264997826541009,"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."}}