{"id":"W2950274094","doi":"10.48550/arxiv.1412.1194","title":"Gradient Boundary Histograms for Action Recognition","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Histogram; Artificial intelligence; Computer science; Boundary (topology); Pattern recognition (psychology); Action recognition; Action (physics); Computer vision; Motion (physics); Image (mathematics); Mathematics; Physics","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":[0.0003642748,0.0005548862,0.0007703214,0.001543371,0.0002343848,0.0007034477,0.0007368718,0.0004765817,0.004752899],"category_scores_gemma":[0.001478598,0.0002109058,0.0003906404,0.001746208,0.000407014,0.001225857,0.0006410995,0.0006704626,0.002159479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004535751,"about_ca_system_score_gemma":0.0005402327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00380227,"about_ca_topic_score_gemma":0.002878371,"domain_scores_codex":[0.9996485,0.00005460783,0.00002152214,0.00008966602,0.0001437412,0.00004197587],"domain_scores_gemma":[0.99968,0.00007910328,0.00003938867,0.00007749003,0.00008748374,0.00003644719],"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":[0.0002643817,0.00009295286,0.00164786,0.000229957,0.00005402033,0.000102208,0.00004354138,0.02841777,0.05248825,0.01654468,0.01477256,0.8853418],"study_design_scores_gemma":[0.00005665805,0.0002164979,0.006489716,0.0000767456,0.00005785272,0.0005639226,0.00009971621,0.8591471,0.05981429,0.04392369,0.02947408,0.00007974672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02447156,0.002832185,0.962519,0.0002144769,0.0002284752,0.0001301272,0.001338977,0.003962305,0.004302874],"genre_scores_gemma":[0.5213981,0.002528453,0.4642168,0.0002816531,0.0002585866,0.0002614337,0.005229228,0.0005532494,0.005272604],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004752899,"threshold_uncertainty_score":0.01590008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1444959800099551,"score_gpt":0.2107624596502893,"score_spread":0.06626647964033411,"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."}}