{"id":"W2965088860","doi":"10.1109/crv.2019.00035","title":"Pose-Projected Action Recognition Hourglass Network (PARHN) in Soccer","year":2019,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Hourglass; Artificial intelligence; Action (physics); Pose; Focus (optics); Computer vision; Pattern recognition (psychology); Action recognition; Component (thermodynamics)","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":[0.0002769096,0.00149273,0.0005448613,0.0003887746,0.0002790999,0.0004772989,0.001198852,0.000733777,0.004570371],"category_scores_gemma":[0.0006610161,0.0003783061,0.0005109156,0.0003684783,0.0003893638,0.0009157769,0.0007523951,0.0009094112,0.00113957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006706838,"about_ca_system_score_gemma":0.0008658143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0147598,"about_ca_topic_score_gemma":0.02241836,"domain_scores_codex":[0.9997719,0.00002596035,0.000006745631,0.0001125939,0.00002999515,0.00005274877],"domain_scores_gemma":[0.9998754,0.00003526393,0.00001657227,0.00002671639,0.00002813054,0.00001783452],"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":[0.0006325321,0.0002720492,0.002860407,0.0002634245,0.0002144336,0.0003545129,0.0001173452,0.1547489,0.02431719,0.003492923,0.02857645,0.7841499],"study_design_scores_gemma":[0.00004438524,0.0003558544,0.005283173,0.0000520061,0.0001046259,0.0001808537,0.00008725079,0.9537705,0.0199874,0.005723836,0.01436461,0.00004553211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3424451,0.008442821,0.5894515,0.001251016,0.001590782,0.0004819405,0.006467526,0.02025381,0.02961547],"genre_scores_gemma":[0.8574808,0.002136772,0.09940808,0.0006991552,0.0002168639,0.0003321445,0.01113696,0.000294929,0.02829421],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0147598,"threshold_uncertainty_score":0.02934778,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04195005019537178,"score_gpt":0.2620257828075488,"score_spread":0.2200757326121771,"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."}}