{"id":"W4390874348","doi":"10.1109/acii59096.2023.10388093","title":"Active Learning with Contrastive Pre-training for Facial Expression Recognition","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Artificial intelligence; Facial expression recognition; Facial expression; Speech recognition; Natural language processing; Pattern recognition (psychology); Facial recognition system","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":[0.0002321999,0.0001051362,0.0001194866,0.00009277938,0.0002847492,0.00009677537,0.0001745289,0.00004238084,0.00001894165],"category_scores_gemma":[0.0001613583,0.00007840754,0.00003650752,0.0002836035,0.00002052462,0.0003305452,0.00006567854,0.0001900105,0.00004340267],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001376924,"about_ca_system_score_gemma":0.00004070257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001585812,"about_ca_topic_score_gemma":0.000003511833,"domain_scores_codex":[0.9990824,0.00006489659,0.00009750941,0.0003208707,0.0001664239,0.0002678532],"domain_scores_gemma":[0.9993941,0.0003009797,0.00007240901,0.00009205103,0.00008042846,0.00006006232],"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":[0.00009025351,0.00001486951,0.0001817197,0.00001016158,0.00001752646,0.000006307253,0.006995769,0.00227927,0.002955168,0.0004009246,0.0002579158,0.9867901],"study_design_scores_gemma":[0.00217834,0.001103513,0.009283407,0.0001833119,0.0000124442,0.00001546242,0.002523445,0.9512137,0.0232455,0.003147498,0.006595823,0.0004975127],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08151607,0.000002157166,0.9138479,0.0003017838,0.0001462843,0.0002373607,0.000004477009,0.0008065794,0.003137435],"genre_scores_gemma":[0.9225402,0.000002579785,0.07402043,0.00008229253,0.0001943942,0.0001162524,0.00004851121,0.00001560482,0.00297975],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9862926,"threshold_uncertainty_score":0.3197367,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03273952067144982,"score_gpt":0.286682792528655,"score_spread":0.2539432718572052,"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."}}