{"id":"W4400276083","doi":"10.1109/jstsp.2024.3422823","title":"Incongruity-Aware Cross-Modal Attention for Audio-Visual Fusion in Dimensional Emotion Recognition","year":2024,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Signal Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Audio visual; Modal; Speech recognition; Emotion recognition; Artificial intelligence; Sensor fusion; Visual attention; Fusion; Pattern recognition (psychology); Computer vision; Perception; Psychology; Multimedia","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":[],"consensus_categories":[],"category_scores_codex":[0.0009879761,0.0001756846,0.000264587,0.0006904928,0.0001636256,0.0006239587,0.0002892954,0.0001668178,0.000008131045],"category_scores_gemma":[0.0001039216,0.0001629274,0.00009178431,0.001323667,0.00003927131,0.002230147,0.00004138086,0.0005916299,0.000002931652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002983023,"about_ca_system_score_gemma":0.0006601297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007232606,"about_ca_topic_score_gemma":0.0000226648,"domain_scores_codex":[0.9980065,0.00008507819,0.0007857334,0.0003326225,0.0004469402,0.0003431831],"domain_scores_gemma":[0.9986078,0.0001291707,0.0003229556,0.0000618531,0.0008008755,0.00007736152],"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":[0.0001378598,0.0002222342,0.007008422,0.0005476532,0.00001768703,0.0001651789,0.0005845269,0.001722604,0.1197737,0.00002326172,0.00006742514,0.8697294],"study_design_scores_gemma":[0.0035995,0.001116824,0.04366389,0.008371307,0.00004955551,0.0009637707,0.0001271556,0.6366845,0.2628404,0.04149735,0.0002507585,0.0008350227],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6428968,0.0005445956,0.3554825,0.0003387466,0.0005547003,0.0001125175,0.000001378664,0.0000417027,0.00002706525],"genre_scores_gemma":[0.9796944,0.00001922624,0.0193321,0.00007829921,0.0007838634,0.000006186739,0.000007588217,0.00001643074,0.00006193601],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8688944,"threshold_uncertainty_score":0.6643987,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02453449477891871,"score_gpt":0.3160550002741921,"score_spread":0.2915205054952734,"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."}}