{"id":"W3167258964","doi":"10.1016/j.patcog.2022.108646","title":"Non-volume preserving-based fusion to group-level emotion recognition on crowd videos","year":2022,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":26,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Cisco Systems Canada; U.S. Department of Energy; U.S. Department of Defense; National Science Foundation","keywords":"Computer science; Crowds; Artificial intelligence; Robustness (evolution); Benchmark (surveying); Pattern recognition (psychology); Feature extraction; Probabilistic logic; Generative model; Crowd psychology; Computer vision; Machine learning; Generative grammar; Geography","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009179069,0.0004195575,0.0003346714,0.0008452433,0.0007175544,0.00009720294,0.0003144153,0.000222284,0.03929989],"category_scores_gemma":[0.00009334063,0.0004945567,0.0002553776,0.0006720098,0.00003603187,0.0002441173,0.0001616124,0.0006852816,0.01180477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003411727,"about_ca_system_score_gemma":0.00003862771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004643259,"about_ca_topic_score_gemma":0.0001550376,"domain_scores_codex":[0.9961606,0.0007069917,0.0006759539,0.001055728,0.0007462688,0.0006544358],"domain_scores_gemma":[0.9984087,0.0001460136,0.0003453896,0.000543724,0.0002685138,0.0002875967],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0008566257,0.001964623,0.0026336,0.00009743271,0.00006985291,0.00005645619,0.001314851,0.0001334778,0.00374537,0.000004077325,0.04721089,0.9419128],"study_design_scores_gemma":[0.03039313,0.0219874,0.7962106,0.002289488,0.0008866526,0.0005199204,0.0089012,0.0176924,0.02346972,0.01029579,0.08018634,0.007167389],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.920166,0.00001786391,0.0490872,0.002507794,0.004383689,0.002137562,0.001496393,0.0004910074,0.01971256],"genre_scores_gemma":[0.9779612,0.000005013988,0.00056693,0.009380328,0.0006424584,0.001870058,0.007454047,0.0001245509,0.001995451],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9347454,"threshold_uncertainty_score":0.9997506,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07994588949359642,"score_gpt":0.3043791936559478,"score_spread":0.2244333041623514,"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."}}