{"id":"W3121880205","doi":"10.15353/jcvis.v6i1.3535","title":"BenderNet and RingerNet: Highly Efficient Line Segmentation Deep Neural Network Architectures for Ice Rink Localization","year":2021,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Artificial neural network; Ice hockey; Market segmentation; Deep neural networks; Line (geometry); Architecture; Computer vision; Geography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.000445832,0.0001067936,0.0002272609,0.0001451401,0.0001729354,0.0004256625,0.00008435707,0.00002551697,0.000001017623],"category_scores_gemma":[0.00004870716,0.0000878081,0.00007116825,0.0002433104,0.00002290435,0.0001460133,0.0000543969,0.00007656823,2.17241e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002800791,"about_ca_system_score_gemma":0.00004886787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004304354,"about_ca_topic_score_gemma":0.000001663264,"domain_scores_codex":[0.9987181,0.0001214638,0.0005039399,0.0001757678,0.0003646337,0.0001161115],"domain_scores_gemma":[0.9986313,0.0002037033,0.0003813631,0.00007571295,0.0006178985,0.00009004703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001776169,0.00003356636,0.002274645,0.00005188931,0.00003250182,0.000007525632,0.0003381793,0.9717843,0.0001429958,0.002387175,0.0001795349,0.02274996],"study_design_scores_gemma":[0.0006930841,0.00008729864,0.009209099,0.00009088951,0.00003212208,0.0003845805,0.00008079436,0.9871091,0.00004984033,0.00183318,0.0003422973,0.00008770979],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08139283,0.002452418,0.9145731,0.001133488,0.0003145336,0.0001042351,0.000001344358,0.00001323046,0.00001481765],"genre_scores_gemma":[0.9677865,0.00002090682,0.03159374,0.0003426618,0.0002085492,0.0000017848,0.00001965393,0.000007195575,0.00001904132],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8863937,"threshold_uncertainty_score":0.4104674,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008292615145022532,"score_gpt":0.2582707516403677,"score_spread":0.2499781364953452,"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."}}