{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000237518,0.0001185194,0.0001351428,0.00004050288,0.000304767,0.0002338982,0.0001742626,0.00008170782,0.00002324269],"category_scores_gemma":[0.0001735797,0.0001224948,0.000079952,0.0002801458,0.00002907995,0.0002850094,0.00006835277,0.0001083156,0.00008404435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004387201,"about_ca_system_score_gemma":0.0001024977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007837537,"about_ca_topic_score_gemma":0.00004053504,"domain_scores_codex":[0.9988225,0.00007392864,0.0001815823,0.0004183392,0.0001451338,0.0003585159],"domain_scores_gemma":[0.9993262,0.00008569153,0.00007585593,0.0002524154,0.000196587,0.00006330641],"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":[0.0000716217,0.0002241322,0.001692019,0.0001560059,0.00007141097,0.0001146012,0.003172229,0.007757109,0.07086467,0.0002541982,0.02273169,0.8928903],"study_design_scores_gemma":[0.005078001,0.0004837967,0.05462311,0.0006314646,0.0001023297,0.0003988043,0.001285226,0.2045927,0.6825915,0.02073771,0.02766038,0.001814946],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6935943,0.0001970631,0.3030212,0.001609016,0.0007955265,0.0001639566,0.0000082387,0.0002320505,0.0003786443],"genre_scores_gemma":[0.1954016,0.00002514368,0.8008525,0.0007517677,0.0009374606,0.00001352813,0.0000593219,0.00001961821,0.001939078],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8910754,"threshold_uncertainty_score":0.4995192,"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."}}