{"id":"W3193484423","doi":"10.3390/s21165452","title":"Multi-Modal Residual Perceptron Network for Audio–Video Emotion Recognition","year":2021,"lang":"en","type":"article","venue":"Sensors","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Modal; Computer science; Modality (human–computer interaction); Residual; Perceptron; Artificial intelligence; Speech recognition; Artificial neural network; Feature (linguistics); Multilayer perceptron; Representation (politics); Pattern recognition (psychology); Machine learning; Algorithm","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001015655,0.0007338414,0.0004616074,0.0002627747,0.0001715783,0.0004945485,0.00107781,0.0009115144,0.002113713],"category_scores_gemma":[0.001832786,0.0002282469,0.0006369706,0.0003091381,0.0003637022,0.0009392541,0.0006307482,0.001494732,0.0007382625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004837368,"about_ca_system_score_gemma":0.0003351817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002446988,"about_ca_topic_score_gemma":0.003001397,"domain_scores_codex":[0.9995965,0.0001321561,0.00002200962,0.0001108939,0.00008082357,0.00005761143],"domain_scores_gemma":[0.9996225,0.0001587496,0.00003374428,0.00004476645,0.0001186024,0.00002168777],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000579631,0.0003299626,0.001410563,0.0002124582,0.0001958631,0.000178235,0.0001367392,0.4446111,0.0453467,0.007368242,0.006374612,0.4932559],"study_design_scores_gemma":[0.000003055135,0.00004140698,0.0001788523,0.000004536952,0.00001065101,0.00001386358,0.000007371381,0.9954138,0.002755213,0.001206632,0.0003590079,0.000005619233],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02701251,0.0006574069,0.9683364,0.0002789416,0.0001212665,0.0000431065,0.0001134997,0.00138209,0.002054782],"genre_scores_gemma":[0.7872725,0.0004162584,0.205081,0.0003563607,0.00008740311,0.0001121621,0.0005546868,0.00009711526,0.006022645],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002446988,"threshold_uncertainty_score":0.007071018,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03740230738645329,"score_gpt":0.2724500849653563,"score_spread":0.235047777578903,"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."}}