{"id":"W4414568524","doi":"10.1016/j.neucom.2025.131621","title":"FACET–VLM: Facial emotion learning with text-guided multiview fusion via vision-language model for 3D/4D facial expression recognition","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"King Fahd University of Petroleum and Minerals","keywords":"Facial expression; Emotion recognition; Coherence (philosophical gambling strategy); Component (thermodynamics); Feature learning; Representation (politics); Key (lock); Consistency (knowledge bases); Pattern recognition (psychology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007051424,0.001537192,0.00139908,0.000942449,0.0003688698,0.0008576841,0.001800822,0.001066947,0.007346647],"category_scores_gemma":[0.001151762,0.0004441627,0.001555008,0.001072922,0.0003370792,0.001161023,0.002227367,0.001414408,0.004598724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004934187,"about_ca_system_score_gemma":0.0008588175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007505915,"about_ca_topic_score_gemma":0.01086111,"domain_scores_codex":[0.9994922,0.00005899534,0.00002298018,0.0001799067,0.00014449,0.0001014457],"domain_scores_gemma":[0.9997355,0.00005000438,0.00002089473,0.00006890544,0.00009511653,0.00002954609],"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":[0.0004704707,0.0002698753,0.0008379028,0.0001375595,0.0002291005,0.00008797865,0.00007618958,0.02601014,0.0638345,0.001869397,0.01642026,0.8897567],"study_design_scores_gemma":[0.00002709307,0.0001140544,0.0009710014,0.00001526523,0.00005827503,0.0001000911,0.00005077093,0.9658164,0.02564343,0.003350159,0.003821178,0.00003231671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01356354,0.0005297145,0.9744127,0.0001744001,0.000182695,0.0001226536,0.0009357042,0.008599288,0.001479339],"genre_scores_gemma":[0.2487405,0.0006313072,0.73461,0.0005798228,0.0001523612,0.0003981625,0.00574518,0.0008661991,0.008276491],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007505915,"threshold_uncertainty_score":0.02457702,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04002556132345352,"score_gpt":0.3439748233923891,"score_spread":0.3039492620689356,"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."}}