{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000537588,0.0001789398,0.0003102564,0.000151375,0.00008365208,0.0004804372,0.0004223954,0.0002405074,0.00009855913],"category_scores_gemma":[0.0002763608,0.0001828566,0.0002055878,0.0003544319,0.000009263711,0.0003217805,0.0006084915,0.0004045822,0.00005532687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008156533,"about_ca_system_score_gemma":0.0001308259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005669456,"about_ca_topic_score_gemma":0.001224208,"domain_scores_codex":[0.9982957,0.0001718493,0.0003880222,0.000727771,0.0001973848,0.0002193174],"domain_scores_gemma":[0.9989624,0.000113755,0.0001833039,0.0003988976,0.000288146,0.00005352017],"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":[0.00003759356,0.001098231,0.0707758,0.0008927732,0.0005347781,0.0000871151,0.01008702,0.1923097,0.002924354,0.002389243,0.002977679,0.7158857],"study_design_scores_gemma":[0.0003828039,0.00001062935,0.002724787,0.000133206,0.00002658521,0.000001740909,0.0002350048,0.9938996,0.0003838985,0.00090218,0.000984933,0.0003146705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01668191,0.00005281783,0.9805692,0.0003526331,0.0003791104,0.0002584488,0.000002464541,0.0001089858,0.001594462],"genre_scores_gemma":[0.6409155,0.0001632158,0.3549373,0.0003618457,0.0001081191,0.0001529095,0.0007252254,0.00002111178,0.002614768],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8015899,"threshold_uncertainty_score":0.7456674,"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."}}