{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006061069,0.00081694,0.000459875,0.0005226095,0.0001453034,0.0003907024,0.0008778588,0.0003635281,0.006270031],"category_scores_gemma":[0.0012007,0.0001786111,0.0005018282,0.0002694648,0.0002894795,0.0008604131,0.0007445811,0.0006922316,0.002375124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003400362,"about_ca_system_score_gemma":0.0004852703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001865126,"about_ca_topic_score_gemma":0.003397447,"domain_scores_codex":[0.9997185,0.00004451717,0.000009422915,0.0000759554,0.00009704296,0.00005460125],"domain_scores_gemma":[0.9998298,0.00004230707,0.00001531564,0.00003655221,0.00005784743,0.00001823105],"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":[0.0004666086,0.0001991676,0.001047437,0.0001431336,0.0000621163,0.0001406978,0.00007695911,0.01510932,0.1441633,0.00449622,0.01333194,0.8207631],"study_design_scores_gemma":[0.00004508395,0.0004515266,0.003710363,0.00004829192,0.00008856352,0.0006789312,0.0001073384,0.8105081,0.1628966,0.006119742,0.01528822,0.00005725883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03090835,0.0005118846,0.9557781,0.0001830211,0.000152232,0.0001785613,0.0006021221,0.005279575,0.006406107],"genre_scores_gemma":[0.5458819,0.000920789,0.4280851,0.0006028098,0.0001341069,0.0003420212,0.002742932,0.0004536808,0.02083663],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006270031,"threshold_uncertainty_score":0.02097529,"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."}}