{"id":"W4400447955","doi":"10.1109/taffc.2024.3424882","title":"Exploring the Boundaries of Semi-Supervised Facial Expression Recognition Using In-Distribution, Out-of-Distribution, and Unconstrained Data","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Affective Computing","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Facial expression; Facial expression recognition; Distribution (mathematics); Pattern recognition (psychology); Emotion recognition; Artificial intelligence; Expression (computer science); Computer science; Speech recognition; Facial recognition system; Mathematics","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":[0.0006611423,0.000182636,0.0002350105,0.0001478984,0.0004579577,0.0002045261,0.000341955,0.00007003442,0.0000056439],"category_scores_gemma":[0.0000615297,0.0001515565,0.00007189093,0.0006474755,0.0002486738,0.001108897,0.00003244916,0.0003256866,0.000003697115],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008759939,"about_ca_system_score_gemma":0.0001518482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008654795,"about_ca_topic_score_gemma":0.00003221842,"domain_scores_codex":[0.9983575,0.0002489242,0.000410434,0.0004972597,0.0002622119,0.0002236957],"domain_scores_gemma":[0.9986993,0.0005935918,0.0001083952,0.0003826128,0.0001667325,0.00004937046],"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":[0.000108455,0.0002766008,0.0001188725,0.0004070586,0.0001057144,0.00001368127,0.007332036,0.01022507,0.07181846,0.00028323,0.0001770898,0.9091337],"study_design_scores_gemma":[0.0006600411,0.0001383547,0.0007266979,0.002017384,0.00005379057,0.00002269655,0.001041017,0.7158352,0.277759,0.001207496,0.0002408216,0.0002974674],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3544237,0.00006180504,0.6439095,0.00007359455,0.0008895107,0.0002063755,0.0003479724,0.00007528595,0.00001225999],"genre_scores_gemma":[0.9968323,0.00003613542,0.002932964,0.00001219008,0.00004826376,0.00001296967,0.0001139443,0.000009826455,0.000001474923],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9088362,"threshold_uncertainty_score":0.6180293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1173636523165885,"score_gpt":0.3011579387551304,"score_spread":0.183794286438542,"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."}}