{"id":"W4402980239","doi":"10.1109/icme57554.2024.10687371","title":"Cross-Attention is not always needed: Dynamic Cross-Attention for Audio-Visual Dimensional Emotion Recognition","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Audio visual; Speech recognition; Visual attention; Emotion recognition; Human–computer interaction; Multimedia; Psychology; Perception","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":[0.001316346,0.001318358,0.001122987,0.0007686125,0.0005021146,0.0009592674,0.001662703,0.0009282203,0.002854754],"category_scores_gemma":[0.001977916,0.0003392363,0.0008086389,0.000670149,0.0004840613,0.001659806,0.002119737,0.001639503,0.0007489788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006924463,"about_ca_system_score_gemma":0.0005575675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0061127,"about_ca_topic_score_gemma":0.008879686,"domain_scores_codex":[0.9993278,0.0001008184,0.00002740501,0.0003130647,0.00008976061,0.0001412259],"domain_scores_gemma":[0.9993694,0.0002438915,0.00004783041,0.000119148,0.0001548626,0.00006485678],"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":[0.001640985,0.0007712666,0.0076507,0.0002774733,0.0003416761,0.0004916079,0.0003002681,0.04519059,0.1053595,0.003134202,0.01367086,0.8211708],"study_design_scores_gemma":[0.0000654071,0.0003173911,0.008704973,0.00003267825,0.0001770727,0.0004398193,0.000115112,0.9549454,0.02604653,0.005150529,0.003967959,0.00003712592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2775614,0.005594791,0.6980214,0.001000849,0.0005440192,0.0002353139,0.0005203021,0.00571427,0.01080756],"genre_scores_gemma":[0.9314582,0.0004565559,0.06139703,0.0008659424,0.0001796941,0.0000999749,0.0008188263,0.0002192065,0.004504628],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0061127,"threshold_uncertainty_score":0.01215422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02506385482528575,"score_gpt":0.3320986240909823,"score_spread":0.3070347692656966,"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."}}