{"id":"W2951095449","doi":"10.48550/arxiv.1809.06217","title":"A Dataset and Preliminary Results for Umpire Pose Detection Using SVM Classification of Deep Features","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cricket; Support vector machine; Artificial intelligence; Computer science; Automatic summarization; Classifier (UML); Convolutional neural network; Pattern recognition (psychology); Machine learning; Feature extraction","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":[0.0009435977,0.002523742,0.0009570422,0.002573784,0.0008714354,0.000888016,0.001684077,0.001616018,0.005605745],"category_scores_gemma":[0.002152603,0.000265354,0.001102175,0.002073595,0.0004018546,0.000794233,0.0009028053,0.00128204,0.006099166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009757901,"about_ca_system_score_gemma":0.0008975904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01657881,"about_ca_topic_score_gemma":0.03812112,"domain_scores_codex":[0.9987352,0.0001764313,0.0001304147,0.0003155201,0.0004372946,0.0002051489],"domain_scores_gemma":[0.9987512,0.0001662704,0.0001048216,0.0003002132,0.0005068937,0.0001706926],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002751679,0.002836897,0.01505027,0.002275098,0.0003681955,0.001206248,0.0002663847,0.01271502,0.0645832,0.001447357,0.4369611,0.4595385],"study_design_scores_gemma":[0.001125803,0.004023268,0.1652081,0.0006458191,0.0004355161,0.003301475,0.001632966,0.2362103,0.1249164,0.003814821,0.458329,0.0003565596],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.3208404,0.004362558,0.05419486,0.001238331,0.002200678,0.003630875,0.5480214,0.03582788,0.02968303],"genre_scores_gemma":[0.1058943,0.0006244273,0.0670993,0.000228316,0.0001859335,0.001084841,0.8167446,0.0003958577,0.007742558],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01657881,"threshold_uncertainty_score":0.03296465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0874194716542897,"score_gpt":0.2241855343980195,"score_spread":0.1367660627437298,"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."}}