{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001277264,0.0005572821,0.0005708096,0.0008991511,0.0008102235,0.0002536393,0.0002073246,0.0003768764,0.005513519],"category_scores_gemma":[0.00003067459,0.0005943046,0.0003114752,0.0005034286,0.0001064651,0.0003889197,0.0002126219,0.001043277,0.0003820074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002113458,"about_ca_system_score_gemma":0.00007436057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000498952,"about_ca_topic_score_gemma":0.00008797847,"domain_scores_codex":[0.9952805,0.0008145697,0.001085943,0.001412888,0.0007251607,0.0006809296],"domain_scores_gemma":[0.9982139,0.0002606521,0.0005160363,0.0003364878,0.0004095069,0.0002633846],"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":[0.001260507,0.001874311,0.0007283742,0.00009716023,0.00006724939,0.00004248225,0.001590221,0.001175258,0.002238708,0.0001032533,0.006279816,0.9845427],"study_design_scores_gemma":[0.0102197,0.002982303,0.03284548,0.0009217487,0.0001009291,0.0002291831,0.0009708863,0.9398126,0.0002855893,0.009768634,0.0004456711,0.001417255],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.816213,0.00004326368,0.1754405,0.0009379687,0.004333974,0.001512925,0.0005235163,0.0002110824,0.0007837657],"genre_scores_gemma":[0.9885381,0.0001030851,0.001142635,0.002997535,0.0004724549,0.000908646,0.00425758,0.00008653064,0.001493439],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9831254,"threshold_uncertainty_score":0.9996508,"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."}}