{"id":"W2904630635","doi":"10.1109/crv.2018.00051","title":"HyperStackNet: A Hyper Stacked Hourglass Deep Convolutional Neural Network Architecture for Joint Player and Stick Pose Estimation in Hockey","year":2018,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Ice hockey; Computer science; Pose; Joint (building); Artificial intelligence; Hourglass; Convolutional neural network; Computer vision; Deep learning; Engineering; Physical medicine and rehabilitation","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":[0.0001875189,0.000134451,0.0001437429,0.0001230794,0.0001801531,0.0001337817,0.0001284288,0.00007032044,0.00007087815],"category_scores_gemma":[0.00004635741,0.000117687,0.00004162205,0.0001747597,0.0000782623,0.000361995,0.0000695597,0.0001136879,0.00003214129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004069535,"about_ca_system_score_gemma":0.00003974011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002246382,"about_ca_topic_score_gemma":0.0002074239,"domain_scores_codex":[0.9989542,0.00005063924,0.0002208186,0.0003243243,0.0001557602,0.0002942736],"domain_scores_gemma":[0.9994553,0.0001219537,0.00006753627,0.0001552985,0.0001127816,0.00008713682],"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":[0.0008441122,0.0007618912,0.00602673,0.0002160298,0.0002099609,0.00003826277,0.008373811,0.1003735,0.006736792,0.109526,0.0399612,0.7269318],"study_design_scores_gemma":[0.001006566,0.0002481571,0.01097058,0.00002344724,0.000008440427,0.00004517891,0.00004091631,0.9648108,0.0003816326,0.02076319,0.001497985,0.000203037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2924428,0.00003417791,0.7055526,0.0008944717,0.0003165861,0.0002940104,0.000004129744,0.00008025174,0.000380939],"genre_scores_gemma":[0.8859264,0.00000319294,0.1124219,0.001111619,0.0003432182,0.00003309452,0.00001985685,0.000009567896,0.0001311631],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8644374,"threshold_uncertainty_score":0.4799136,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02233927392920447,"score_gpt":0.2452530967018579,"score_spread":0.2229138227726535,"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."}}