{"id":"W3005980554","doi":"10.3390/s20041087","title":"eXnet: An Efficient Approach for Emotion Recognition in the Wild","year":2020,"lang":"en","type":"article","venue":"Sensors","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":71,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Innovation, Science and Economic Development Canada","keywords":"Overfitting; Computer science; Benchmark (surveying); Convolutional neural network; Artificial intelligence; Deep learning; Generalization; Facial expression; Feature (linguistics); Key (lock); Machine learning; Pattern recognition (psychology); Feature extraction; Artificial neural network","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006403347,0.002345403,0.0007003226,0.001119813,0.0004836104,0.001154306,0.002578191,0.0009286171,0.008468355],"category_scores_gemma":[0.001282388,0.0006898919,0.0007963292,0.0007478901,0.0004037788,0.002884173,0.00143784,0.001547063,0.003992015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008992472,"about_ca_system_score_gemma":0.0007164754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009409202,"about_ca_topic_score_gemma":0.01560246,"domain_scores_codex":[0.9996017,0.00004429719,0.00003289176,0.0001420247,0.0001174756,0.00006170218],"domain_scores_gemma":[0.9997715,0.00004292088,0.00001920257,0.00006203745,0.00008954664,0.00001478294],"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":[0.0005936508,0.0003275994,0.002225308,0.0003787973,0.0002721389,0.0004791392,0.0001424805,0.06774811,0.03372274,0.009993157,0.1206984,0.7634184],"study_design_scores_gemma":[0.00005373851,0.0001088962,0.0009607358,0.00003623456,0.00004609469,0.000189855,0.00007382755,0.941494,0.02019795,0.01006681,0.02673611,0.0000356891],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03960808,0.001788753,0.8799397,0.0009357564,0.001082215,0.0003607728,0.006580482,0.05885269,0.01085147],"genre_scores_gemma":[0.2679861,0.00175866,0.664685,0.001142809,0.0002877982,0.0007466019,0.03172666,0.00259274,0.02907368],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009409202,"threshold_uncertainty_score":0.02832949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1007163132348364,"score_gpt":0.3182011157437317,"score_spread":0.2174848025088953,"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."}}