{"id":"W4405778930","doi":"10.1109/tmm.2024.3521788","title":"FER-Former: Multimodal Transformer for Facial Expression Recognition","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"China Scholarship Council","keywords":"Computer science; Facial expression recognition; Facial expression; Transformer; Facial recognition system; Speech recognition; Artificial intelligence; Feature extraction; Pattern recognition (psychology); Electrical engineering; Voltage; Engineering","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002099096,0.0002830347,0.0002207597,0.0004022918,0.0002566073,0.0000639394,0.000101555,0.0003642399,0.006269921],"category_scores_gemma":[0.000007726889,0.0002603522,0.0003814885,0.0002299871,0.00007918381,0.0002967329,2.947073e-7,0.0004373954,0.003236461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007488637,"about_ca_system_score_gemma":0.00004563291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003854026,"about_ca_topic_score_gemma":0.00005874527,"domain_scores_codex":[0.9982988,0.00008229892,0.0003967481,0.0005664207,0.0002278561,0.000427864],"domain_scores_gemma":[0.9991846,0.0003113017,0.00004133229,0.0001910355,0.00009339449,0.0001783064],"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":[0.0005026943,0.0004796988,0.000001367293,0.00007782052,0.0001105341,0.000008129786,0.003215819,0.00005175664,0.03059911,0.00001162692,0.003149582,0.9617919],"study_design_scores_gemma":[0.01338796,0.002124371,0.000568158,0.001032503,0.000800736,0.0001483465,0.00289988,0.03461527,0.8261353,0.001746765,0.1144363,0.002104477],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0432652,0.0001123786,0.933796,0.0004566761,0.01156148,0.001434153,0.001262205,0.0007362969,0.007375622],"genre_scores_gemma":[0.9867583,0.00007860799,0.006065308,0.000257059,0.0005190572,0.001111411,0.0002689169,0.0000883458,0.004853032],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9596874,"threshold_uncertainty_score":0.9999849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0486150697305601,"score_gpt":0.3325632962002604,"score_spread":0.2839482264697003,"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."}}