{"id":"W3211666705","doi":"10.1109/fg52635.2021.9667055","title":"Cross Attentional Audio-Visual Fusion for Dimensional Emotion Recognition","year":2021,"lang":"en","type":"article","venue":"2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Modalities; Computer science; Leverage (statistics); Emotion recognition; Valence (chemistry); Affective computing; Salient; Arousal; Fusion; Speech recognition; Artificial intelligence; Modal; Feature (linguistics); Focus (optics); Pattern recognition (psychology); Machine learning; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005294411,0.000439407,0.0004183832,0.0003369069,0.0003849549,0.0003333352,0.0001665297,0.000448483,0.04305509],"category_scores_gemma":[0.0003193227,0.0004499621,0.0002939051,0.0002836876,0.0001416574,0.0003998259,0.00006653852,0.0004666873,0.002183911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001228304,"about_ca_system_score_gemma":0.0001812603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002197911,"about_ca_topic_score_gemma":0.00004926808,"domain_scores_codex":[0.99668,0.0003270963,0.0007978586,0.001033187,0.0007169787,0.0004448571],"domain_scores_gemma":[0.997071,0.0003863847,0.0004135147,0.0002423772,0.001657557,0.0002291792],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0004897702,0.001765819,0.0006841583,0.000177401,0.0006241298,0.0001010472,0.0008233603,0.00003597672,0.009952314,0.003143323,0.009344488,0.9728582],"study_design_scores_gemma":[0.06294271,0.007174015,0.3691527,0.01490487,0.002321837,0.005202924,0.02407407,0.1859958,0.059618,0.1869104,0.07080453,0.01089814],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.936642,0.0001836654,0.01136087,0.007181425,0.009513278,0.00113494,0.001574706,0.0002018328,0.03220731],"genre_scores_gemma":[0.9518266,0.0004719467,0.003238298,0.002173605,0.001652611,0.0005762223,0.01308862,0.00008321058,0.02688885],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9619601,"threshold_uncertainty_score":0.9997952,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07865010546663687,"score_gpt":0.3726191346843099,"score_spread":0.293969029217673,"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."}}