{"id":"W2994718079","doi":"10.1109/access.2019.2955637","title":"A Hybrid Latent Space Data Fusion Method for Multimodal Emotion Recognition","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":97,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"Shahrekord University","keywords":"Computer science; Canonical correlation; Artificial intelligence; Pattern recognition (psychology); Modality (human–computer interaction); Feature (linguistics); Field (mathematics); Feature vector; Modal; Modalities; Sensor fusion; Space (punctuation); Fusion; Speech recognition; Machine learning; Mathematics","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":[0.001688128,0.001043673,0.0009167892,0.001369921,0.0004649929,0.0009849421,0.0007835706,0.000719983,0.003448237],"category_scores_gemma":[0.002493314,0.0002549067,0.001662127,0.001420215,0.000366696,0.001476917,0.001626348,0.00136465,0.001613821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004810677,"about_ca_system_score_gemma":0.0005629704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001796452,"about_ca_topic_score_gemma":0.001756461,"domain_scores_codex":[0.9988834,0.0003333233,0.00007573058,0.0002913534,0.0003245072,0.00009171042],"domain_scores_gemma":[0.9993895,0.0001721499,0.00005199936,0.00008557553,0.0002692413,0.00003157625],"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":[0.0004661561,0.0002227034,0.001425597,0.0001576251,0.0002261414,0.00008759466,0.0002824561,0.03984488,0.03784833,0.008204278,0.00421296,0.9070213],"study_design_scores_gemma":[0.00001924127,0.0001436872,0.001732738,0.00001953449,0.00004953852,0.00009438462,0.0001120522,0.9734099,0.01384336,0.00699207,0.003538847,0.00004458294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006890904,0.0002227692,0.9914376,0.00008345762,0.00004408948,0.00004791394,0.0001264778,0.0006445321,0.0005022815],"genre_scores_gemma":[0.2857945,0.0004446117,0.7079468,0.0001384999,0.00009695985,0.0003731715,0.001240012,0.000174059,0.003791349],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003448237,"threshold_uncertainty_score":0.01153553,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1470668615012953,"score_gpt":0.4226811176535283,"score_spread":0.275614256152233,"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."}}