{"id":"W3211056702","doi":"10.5220/0010657000003059","title":"POOF: Efficient Goalie Pose Annotation using Optical Flow","year":2021,"lang":"en","type":"article","venue":"","topic":"Robot Manipulation and Learning","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Annotation; Optical flow; Computer vision; Artificial intelligence; Image (mathematics)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004964094,0.0000613884,0.00006460915,0.00003484403,0.00004157616,0.00004435961,0.00002395751,0.00003703752,0.0006096711],"category_scores_gemma":[0.00003134642,0.00006391434,0.00002904211,0.000144076,0.000005582697,0.00004258177,0.00001200588,0.00008078011,0.0001157744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003960162,"about_ca_system_score_gemma":0.00001139587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000217306,"about_ca_topic_score_gemma":0.000002300955,"domain_scores_codex":[0.9995649,0.00001358571,0.0001113647,0.00008997726,0.00009956062,0.0001206541],"domain_scores_gemma":[0.9998035,0.00002112283,0.000006676383,0.00008535889,0.00003761729,0.00004575551],"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":[7.651576e-7,0.000008033267,0.0001027297,0.000008885546,0.000006175593,0.00001064387,0.00009818873,0.9818543,0.01366457,0.001110674,0.0001279504,0.00300707],"study_design_scores_gemma":[0.0001186567,0.000002842047,0.002466361,0.000008713585,0.000005937058,0.00001291825,0.00008314673,0.9902439,0.006279272,0.00001147073,0.0006816863,0.0000850993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.293985,0.00008627296,0.6834586,0.00008776818,0.0003927827,0.00003717768,1.558371e-7,0.0002614419,0.02169086],"genre_scores_gemma":[0.9702036,0.00000181297,0.02926376,0.00006891148,0.00008372723,7.348178e-7,0.00001281199,0.00001523065,0.0003493548],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6762186,"threshold_uncertainty_score":0.667547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02262168249013886,"score_gpt":0.240062453183935,"score_spread":0.2174407706937961,"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."}}