{"id":"W4410454723","doi":"10.20944/preprints202505.1095.v1","title":"Efficient Dynamic Emotion Recognition from Facial Expressions Using Statistical Spatio-Temporal Geometric Features","year":2025,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre intégré de santé et de services sociaux de Chaudière-Appalaches","funders":"","keywords":"Computer science; Pattern recognition (psychology); Artificial intelligence; Facial expression; Emotion recognition; Speech recognition","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":[0.0005386524,0.0005454858,0.0005880172,0.0009466982,0.0003945272,0.0002004013,0.001211772,0.0007048122,0.0008411731],"category_scores_gemma":[0.0006436786,0.0005615423,0.0002597328,0.0007341355,0.00009069771,0.0002148891,0.003639387,0.001312038,0.0008039158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000378014,"about_ca_system_score_gemma":0.0004086055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001028167,"about_ca_topic_score_gemma":0.00004533734,"domain_scores_codex":[0.9954557,0.0004954229,0.0008100034,0.001860517,0.000840092,0.0005382381],"domain_scores_gemma":[0.9971009,0.0003438789,0.0005402478,0.001415545,0.0003511925,0.0002482028],"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":[0.0008286973,0.004557515,0.09841806,0.001726958,0.001031291,0.0003127576,0.00827605,0.4125425,0.04444622,0.0006180447,0.002772454,0.4244694],"study_design_scores_gemma":[0.001516096,0.00005287188,0.2775215,0.003141976,0.0002727834,0.00001511602,0.0002238588,0.6702321,0.02570211,0.01839039,0.001024469,0.001906788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6830391,0.00009152694,0.3121458,0.0001681841,0.001909609,0.0006600482,0.0008874787,0.0003526903,0.0007455152],"genre_scores_gemma":[0.952525,0.00006274138,0.04448279,0.0001260495,0.0001430641,0.0001296439,0.002223045,0.00002564001,0.0002820029],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4225627,"threshold_uncertainty_score":0.9999741,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09988299566617437,"score_gpt":0.3502574771313564,"score_spread":0.250374481465182,"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."}}