{"id":"W2963287896","doi":"10.1109/cvprw.2019.00310","title":"Temporal Hockey Action Recognition via Pose and Optical Flows","year":2019,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Pose; Optical flow; Computer science; Artificial intelligence; Action recognition; Action (physics); Pattern recognition (psychology); Computer vision; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003667659,0.001681566,0.0006498196,0.001310971,0.0002652435,0.000738062,0.001120173,0.0005579452,0.003941007],"category_scores_gemma":[0.00084477,0.0003166005,0.0005809485,0.0007048731,0.0003716153,0.001143401,0.0007370562,0.0007142502,0.001787066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007041626,"about_ca_system_score_gemma":0.000940843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00853793,"about_ca_topic_score_gemma":0.01500434,"domain_scores_codex":[0.9996639,0.00002281216,0.00001028498,0.0001428383,0.00009158098,0.00006861349],"domain_scores_gemma":[0.9998098,0.0000335357,0.00002732407,0.00003256939,0.00006692436,0.00002984588],"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":[0.0005295833,0.000357254,0.005814499,0.0001763702,0.0001057787,0.0001663523,0.00008258329,0.04092139,0.06175873,0.00278802,0.01062078,0.8766786],"study_design_scores_gemma":[0.0000260466,0.0003433613,0.01615381,0.00007543031,0.00009771431,0.0003143458,0.0001194513,0.8948455,0.07176246,0.005656195,0.01054751,0.00005819765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1084666,0.0009091825,0.8651065,0.0002534984,0.000516807,0.0003269272,0.002398477,0.01236991,0.009652059],"genre_scores_gemma":[0.7460921,0.0009388881,0.2299744,0.0002723506,0.0002096035,0.0002906588,0.005935268,0.000276311,0.01601049],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00853793,"threshold_uncertainty_score":0.01697642,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02823862967632128,"score_gpt":0.2515174331714506,"score_spread":0.2232788034951294,"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."}}