{"id":"W3193719728","doi":"10.1145/3462244.3479955","title":"Self-supervised Contrastive Learning of Multi-view Facial Expressions","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Robustness (evolution); Artificial intelligence; Facial expression; Encoder; Invariant (physics); Pattern recognition (psychology); Exploit; Training set; Labeled data; Face (sociological concept); Component (thermodynamics); Speech recognition; Computer vision; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001061876,0.001077234,0.0008517749,0.0004215675,0.0001730918,0.0004428439,0.0009711148,0.0006137266,0.001239493],"category_scores_gemma":[0.002286348,0.0002956768,0.0007441619,0.0003124883,0.0004783118,0.0006687269,0.0009524762,0.001207248,0.0007266686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003407073,"about_ca_system_score_gemma":0.000336517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001117225,"about_ca_topic_score_gemma":0.002112258,"domain_scores_codex":[0.9993559,0.0001964391,0.00001942623,0.0002441952,0.0001065682,0.00007750754],"domain_scores_gemma":[0.9994932,0.0001874164,0.00006722366,0.0001033873,0.0001133175,0.00003548047],"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":[0.0008151775,0.0004946471,0.006156588,0.0001865133,0.0002787702,0.0002224494,0.0001926734,0.1141802,0.1075809,0.003872285,0.01305116,0.7529687],"study_design_scores_gemma":[0.0000184779,0.0001728032,0.002973436,0.00001453384,0.00002982855,0.0001742112,0.00003363448,0.9780669,0.01472708,0.002501798,0.001273233,0.00001416762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1349888,0.0009521418,0.8584418,0.0003633742,0.0001576776,0.0001182437,0.0003731253,0.0014108,0.003194021],"genre_scores_gemma":[0.845523,0.0005260285,0.1442512,0.0003924477,0.000147727,0.0001478932,0.001616168,0.0002005717,0.007194888],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001239493,"threshold_uncertainty_score":0.005615771,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06554403347052203,"score_gpt":0.3495080473286774,"score_spread":0.2839640138581553,"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."}}