{"id":"W2140278677","doi":"10.1109/crv.2011.12","title":"Using Line and Ellipse Features for Rectification of Broadcast Hockey Video","year":2011,"lang":"en","type":"article","venue":"","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"McGill University","keywords":"Computer vision; Robustness (evolution); Computer science; Artificial intelligence; Ellipse; Homography; Bundle adjustment; Image (mathematics); 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":[0.0001728066,0.00004663183,0.00008795431,0.00007301122,0.00005167386,0.00003164926,0.000124486,0.00003206253,0.00000658979],"category_scores_gemma":[0.00004006581,0.00003761577,0.00003202195,0.0001833065,0.00001480091,0.000223181,0.00003520532,0.0000197575,6.392631e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005893142,"about_ca_system_score_gemma":0.00001380951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001854607,"about_ca_topic_score_gemma":0.00005731402,"domain_scores_codex":[0.9995478,0.00001827314,0.0001419939,0.0001612269,0.00006575805,0.00006491469],"domain_scores_gemma":[0.99955,0.00002826716,0.00007929472,0.0001973179,0.0001197036,0.00002539061],"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":[0.00006972211,0.0002634057,0.007487294,0.0001016965,0.0001186999,9.905473e-7,0.006501686,0.0006420034,0.1235225,0.1837863,0.00191501,0.6755906],"study_design_scores_gemma":[0.0004342342,0.0001885092,0.01200946,0.00002918167,0.00006542189,0.000007279084,0.0001427709,0.6631445,0.3118201,0.01083204,0.001083643,0.0002429382],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03213783,0.0001118711,0.9668651,0.00008600613,0.0000515178,0.00008222158,8.814146e-7,0.00002070659,0.0006439139],"genre_scores_gemma":[0.779426,0.00002735283,0.2201215,0.00004838308,0.00002033182,0.000002430453,0.000002713003,0.000002829068,0.0003484436],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7472882,"threshold_uncertainty_score":0.1533927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1009780922878621,"score_gpt":0.2856016001602165,"score_spread":0.1846235078723544,"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."}}