{"id":"W2947369712","doi":"10.1109/smc.2019.8914172","title":"Memory Integrity of CNNs for Cross-Dataset Facial Expression Recognition","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Pattern recognition (psychology); Domain (mathematical analysis); Face (sociological concept); Process (computing); Expression (computer science); Facial expression recognition; Retraining; Domain adaptation; Fine-tuning; Facial recognition system; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00553092,0.00156468,0.001009156,0.001018362,0.0007251305,0.001704799,0.002551821,0.001364157,0.001948091],"category_scores_gemma":[0.02124785,0.000559344,0.0007724859,0.0008153551,0.0007852026,0.003730999,0.002489737,0.00162936,0.0008302831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001359738,"about_ca_system_score_gemma":0.001015325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006434101,"about_ca_topic_score_gemma":0.006261761,"domain_scores_codex":[0.9971911,0.000535532,0.0003859584,0.0008152717,0.0006916987,0.0003803975],"domain_scores_gemma":[0.9924492,0.002257365,0.0008270262,0.003134474,0.00111095,0.0002210856],"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":[0.004249369,0.0007035794,0.03414566,0.0007569332,0.001507269,0.0008073442,0.0005076777,0.1877996,0.06055531,0.002402028,0.00938012,0.697185],"study_design_scores_gemma":[0.0001439798,0.001534467,0.03235508,0.0001893365,0.0005470941,0.0007850129,0.0004642955,0.7997455,0.1506908,0.007539534,0.005886053,0.0001189188],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8594176,0.006932754,0.117755,0.001109363,0.000574577,0.0002985113,0.001444686,0.006223661,0.00624388],"genre_scores_gemma":[0.9750457,0.0005627135,0.01944018,0.000284826,0.00005121945,0.0001308214,0.002167654,0.0001847529,0.002131937],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006434101,"threshold_uncertainty_score":0.02925068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07763707824792546,"score_gpt":0.3408577876005032,"score_spread":0.2632207093525777,"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."}}