{"id":"W3153976895","doi":"10.1109/cvprw53098.2021.00510","title":"Contrastive Learning for Sports Video: Unsupervised Player Classification","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"York University","keywords":"Computer science; Artificial intelligence; Unsupervised learning; Margin (machine learning); Embedding; Machine learning; Frame (networking); A priori and a posteriori; Pattern recognition (psychology)","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005980174,0.0002789897,0.0007051075,0.000209101,0.0001388628,0.0002526688,0.0002166616,0.0003553419,0.002720379],"category_scores_gemma":[0.00009518942,0.00032206,0.0003242686,0.00009893425,0.00003451771,0.0001334126,0.0001364769,0.0004797315,0.0000692051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001167263,"about_ca_system_score_gemma":0.00009180734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002125856,"about_ca_topic_score_gemma":0.00003962811,"domain_scores_codex":[0.9979043,0.000006028221,0.0008875257,0.0008229935,0.00005788474,0.000321291],"domain_scores_gemma":[0.99856,0.00006193516,0.0006764175,0.0004387846,0.0001669819,0.00009590574],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000137316,0.0003780066,0.6274071,0.0008064453,0.0007238336,0.00002430003,0.002065268,0.05322511,0.00006672046,0.3013983,0.005291185,0.008476403],"study_design_scores_gemma":[0.000806294,0.00005428101,0.2299592,0.0001273627,0.00004854651,0.000002725514,0.0005920936,0.6434979,0.00009817848,0.008889015,0.1150345,0.0008898953],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6472746,0.004188898,0.2664927,0.001363571,0.003058429,0.001433044,0.000305709,0.0001820846,0.07570098],"genre_scores_gemma":[0.9891505,0.001113249,0.001321479,0.0002756965,0.0003130309,0.0001474534,0.000795246,0.00005057476,0.006832782],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5902728,"threshold_uncertainty_score":0.9999232,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0639847983599984,"score_gpt":0.2485529312368201,"score_spread":0.1845681328768217,"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."}}