{"id":"W4221139382","doi":"10.1109/cvprw56347.2022.00278","title":"A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":101,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; École de Technologie Supérieure","funders":"","keywords":"Computer science; Leverage (statistics); Modalities; Canonical correlation; Artificial intelligence; Valence (chemistry); Concordance correlation coefficient; Audio visual; Correlation; Speech recognition; Arousal; Pattern recognition (psychology); Robustness (evolution); Affective computing; Machine learning; Mathematics; 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":[0.001907733,0.001242184,0.001061348,0.0008954271,0.0004311647,0.0009688732,0.001844894,0.00119217,0.002334136],"category_scores_gemma":[0.002274416,0.0004548469,0.001699895,0.0008654465,0.0005586277,0.001593012,0.001764117,0.001856548,0.0009552854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001073833,"about_ca_system_score_gemma":0.0006912213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009727654,"about_ca_topic_score_gemma":0.00865501,"domain_scores_codex":[0.9992323,0.0001767492,0.00004122862,0.0002873259,0.0001320303,0.0001304642],"domain_scores_gemma":[0.9994171,0.0002237765,0.00005314721,0.00005994646,0.000208749,0.00003736044],"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":[0.0006757015,0.0004039649,0.003814022,0.0001272669,0.0004826723,0.0002216502,0.0003183073,0.4121159,0.03529539,0.007631693,0.005962056,0.5329514],"study_design_scores_gemma":[0.000004519729,0.00004131309,0.0005745341,0.000004595653,0.00003159825,0.00002522511,0.000009655238,0.995427,0.001921477,0.001680014,0.0002712894,0.000008803208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0657979,0.001439894,0.9272496,0.0004875192,0.0001736776,0.00007301506,0.0002008806,0.001727305,0.002850248],"genre_scores_gemma":[0.9033057,0.0004860022,0.08914835,0.0005286322,0.0001366138,0.0001505341,0.0005887635,0.0001313115,0.005524051],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009727654,"threshold_uncertainty_score":0.01934206,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09482374814886126,"score_gpt":0.3480566243783005,"score_spread":0.2532328762294393,"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."}}