{"id":"W4388657569","doi":"10.1145/3632960","title":"Contrastive Learning of View-invariant Representations for Facial Expressions Recognition","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Multimedia Computing Communications and Applications","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Mitacs","keywords":"Invariant (physics); Computer science; Facial expression; Artificial intelligence; Pattern recognition (psychology); Inference; Embedding; Redundancy (engineering); Expression (computer science); Speech recognition; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004174379,0.0001770743,0.0002447176,0.000393904,0.00125674,0.00003271376,0.0004418827,0.0001457665,0.0001278133],"category_scores_gemma":[0.0001681989,0.0001921379,0.0001417181,0.0007662497,0.0002816601,0.00009028747,0.00004464147,0.0003738544,0.0001684241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002405338,"about_ca_system_score_gemma":0.00004090921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007560937,"about_ca_topic_score_gemma":0.00002557759,"domain_scores_codex":[0.9983901,0.0002587627,0.0005557201,0.0003979788,0.0001333327,0.0002640501],"domain_scores_gemma":[0.9951161,0.003118813,0.0002666278,0.001050155,0.0003266661,0.0001216196],"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":[0.00004588889,0.0006821033,0.0001289581,0.00003527806,0.0001549416,2.460775e-7,0.004043845,0.0004596323,0.004844065,0.002916302,0.0002869195,0.9864018],"study_design_scores_gemma":[0.02659646,0.002648104,0.07509629,0.00194941,0.002668627,0.0001410359,0.09583022,0.4299946,0.0171287,0.06201137,0.2814402,0.004494975],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01057521,0.0001310998,0.9812084,0.002019795,0.0002384274,0.002101421,0.0006001794,0.000504553,0.002620868],"genre_scores_gemma":[0.9423955,0.0006615768,0.05259733,0.0000968942,0.0000981399,0.002362072,0.001194579,0.00004134125,0.0005525886],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9819068,"threshold_uncertainty_score":0.9665952,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0864255137729336,"score_gpt":0.3801012519177925,"score_spread":0.2936757381448589,"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."}}