{"id":"W4411792965","doi":"10.18280/ts.420329","title":"A Multi-Task Learning Framework for Character Face Recognition and Emotion Analysis in Television Programs","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Face recognition and analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Character (mathematics); Task (project management); Face (sociological concept); Computer science; Facial recognition system; Psychology; Artificial intelligence; Speech recognition; Cognitive psychology; Natural language processing; Pattern recognition (psychology); Linguistics; Engineering; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004919411,0.0001366095,0.0002364879,0.0005774038,0.0001420594,0.0002286469,0.0001502943,0.00008659482,0.00004384732],"category_scores_gemma":[0.00004404703,0.0001298769,0.0001554262,0.001368243,0.00002176102,0.0003148354,0.00004052335,0.0001646645,0.00001294819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004278988,"about_ca_system_score_gemma":0.00002093413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002091322,"about_ca_topic_score_gemma":0.00003928857,"domain_scores_codex":[0.9987613,0.0001126349,0.0003115605,0.0004282247,0.0001619452,0.0002243453],"domain_scores_gemma":[0.9995112,0.0001232104,0.0001064684,0.0001127697,0.00009140376,0.00005498319],"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":[0.00002615313,0.0003442568,0.0109659,0.00005865701,0.000335408,0.00000237173,0.001272613,0.0005671899,0.001779381,0.000491047,0.000008974706,0.984148],"study_design_scores_gemma":[0.001239317,0.0001566505,0.04203282,0.0002389409,0.0003227693,8.157724e-7,0.0003864006,0.9515311,0.0007528736,0.002153415,0.0009172944,0.0002675852],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2205672,0.00004671048,0.7784071,0.0005263475,0.00003217353,0.000324996,0.000004435095,0.00007015258,0.00002095025],"genre_scores_gemma":[0.9218313,0.00006076243,0.07755458,0.0002109825,0.00002212188,0.00008736792,0.0001325484,0.000004894854,0.00009544768],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9838805,"threshold_uncertainty_score":0.5296229,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0343464631387401,"score_gpt":0.2812311591313446,"score_spread":0.2468846959926045,"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."}}