{"id":"W3194477706","doi":"10.1145/3475722.3482794","title":"Multi-task Learning for Jersey Number Recognition in Ice Hockey","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Task (project management); Numerical digit; Computer science; Function (biology); Artificial intelligence; Digit recognition; Machine learning; Arithmetic; Artificial neural network; Engineering; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008106337,0.0008584707,0.0005978839,0.0006383844,0.0004342433,0.0005235453,0.0008972927,0.000905177,0.001983377],"category_scores_gemma":[0.00186686,0.0001839799,0.0004931608,0.0004835708,0.0003778619,0.0012033,0.0005487911,0.001023517,0.000773155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006511434,"about_ca_system_score_gemma":0.000566314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006270933,"about_ca_topic_score_gemma":0.009978627,"domain_scores_codex":[0.9996966,0.00006618664,0.00001300501,0.0001219069,0.00004095315,0.00006136455],"domain_scores_gemma":[0.9994428,0.0002653511,0.00005198344,0.0000640107,0.0001193482,0.0000565604],"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":[0.001358764,0.0005975568,0.0030097,0.000311229,0.0001334159,0.0004051631,0.0002401824,0.1752569,0.05496677,0.001994461,0.012516,0.7492099],"study_design_scores_gemma":[0.00001929793,0.0001930884,0.002049194,0.000009867866,0.00002643905,0.00004628857,0.0001019354,0.9806827,0.01344173,0.002212928,0.001202291,0.0000142554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.445504,0.001769851,0.5395774,0.0008531176,0.0003555943,0.0002341569,0.0008496793,0.0041415,0.006714629],"genre_scores_gemma":[0.8865711,0.0002813116,0.1027226,0.0002673765,0.0001150813,0.0001155548,0.002268047,0.0001152449,0.007543744],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006270933,"threshold_uncertainty_score":0.01246887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04313193310445002,"score_gpt":0.287317760362266,"score_spread":0.244185827257816,"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."}}