{"id":"W4415748352","doi":"10.1109/taffc.2025.3627534","title":"Progressive Multi-Source Domain Adaptation for Personalized Facial Expression Recognition","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Affective Computing","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Bell (Canada); HEC Montréal","funders":"","keywords":"Exploit; Domain (mathematical analysis); Forgetting; Focus (optics); Similarity (geometry); Facial expression; Adaptation (eye); Face (sociological concept)","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":[],"consensus_categories":[],"category_scores_codex":[0.0003198593,0.0002329743,0.0002352721,0.00036095,0.0006364387,0.00004583032,0.00008489942,0.0002131694,0.0001881224],"category_scores_gemma":[0.00003124121,0.0002407841,0.0002434573,0.0003166501,0.00009065735,0.0001054703,0.000001684723,0.0003100415,0.00006642115],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000145183,"about_ca_system_score_gemma":0.00003995466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001934223,"about_ca_topic_score_gemma":0.0000196495,"domain_scores_codex":[0.9983059,0.0004218848,0.0002888953,0.000534195,0.0001402916,0.000308833],"domain_scores_gemma":[0.9988155,0.000562867,0.0001710807,0.0001438484,0.000239859,0.000066787],"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":[0.001316378,0.001276258,0.00003131647,0.0000937654,0.0002422181,0.000005271767,0.01054532,0.002489538,0.01109699,0.0001954295,0.0003070186,0.9724005],"study_design_scores_gemma":[0.09056752,0.005467063,0.01105059,0.007329083,0.001511952,0.0002053139,0.08784117,0.3588032,0.4128616,0.008848283,0.01109884,0.004415361],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1258166,0.00005265281,0.8689219,0.0001000739,0.002158615,0.001519365,0.00006041527,0.0002835373,0.001086841],"genre_scores_gemma":[0.9824222,0.000002380137,0.01496353,0.0002555362,0.0001307073,0.00043004,0.00005641791,0.00003315879,0.001706016],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9679852,"threshold_uncertainty_score":0.9818892,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05386957407189527,"score_gpt":0.3495630202703141,"score_spread":0.2956934461984188,"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."}}