{"id":"W4386712828","doi":"10.54254/2755-2721/6/20230751","title":"A channel attention and feature manipulation network for facial expression recognition","year":2023,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Interpretability; Feature (linguistics); Computer science; Artificial intelligence; Facial expression; Pattern recognition (psychology); Confusion matrix; Residual; Network architecture; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.00009994443,0.00008409409,0.00007654499,0.00008662257,0.0001079153,0.00002350903,0.00001499731,0.00008386678,0.00001073157],"category_scores_gemma":[0.000005330328,0.00009057958,0.0000212763,0.0001168703,0.000007886915,0.0000463716,0.00001283874,0.00006196342,0.00002276372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006840895,"about_ca_system_score_gemma":0.000002651091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.568866e-7,"about_ca_topic_score_gemma":4.491595e-7,"domain_scores_codex":[0.9995148,0.000007013739,0.000098113,0.0001812858,0.00006633557,0.0001324556],"domain_scores_gemma":[0.9997945,0.00007548017,0.00003467798,0.00002778724,0.00002861603,0.00003895813],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000501282,0.0001273777,0.000428097,0.0004938454,0.0002091148,0.00000767651,0.002900031,0.4815781,0.01312048,0.05810609,0.02077171,0.4217562],"study_design_scores_gemma":[0.004003035,0.0001344236,0.3230773,0.000195637,0.0000681317,0.00004522329,0.0006355006,0.5907089,0.0001534555,0.07661504,0.003738846,0.0006245775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5434191,0.0001071796,0.4531663,0.0004026822,0.0008608088,0.0007064535,0.00004805746,0.0004281203,0.0008613499],"genre_scores_gemma":[0.9939524,0.00001022715,0.004042394,0.00008458582,0.0003860733,0.0001622859,0.001218705,0.00001729004,0.000126039],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4505333,"threshold_uncertainty_score":0.3693728,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02987601697186876,"score_gpt":0.2608175978116469,"score_spread":0.2309415808397782,"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."}}