{"id":"W2944403092","doi":"10.1109/access.2019.2910604","title":"A Spatiotemporal Heterogeneous Two-Stream Network for Action Recognition","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Action recognition; Heterogeneous network; Artificial intelligence; Residual; Network architecture; Pattern recognition (psychology); Data mining; Computer network; Algorithm","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":[0.000390248,0.0009591404,0.0005342758,0.001015718,0.0002861297,0.0004409435,0.001130386,0.0006312079,0.00204996],"category_scores_gemma":[0.0008502788,0.000258778,0.0005851067,0.001012375,0.0002779605,0.001100116,0.000612437,0.0007903098,0.0005510466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006868996,"about_ca_system_score_gemma":0.0006046671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01242832,"about_ca_topic_score_gemma":0.01255233,"domain_scores_codex":[0.9997868,0.00002743695,0.00001007283,0.00009885742,0.00004436699,0.00003242199],"domain_scores_gemma":[0.9998177,0.00004097752,0.00002080511,0.00003179667,0.00006872005,0.00001994272],"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":[0.0004473937,0.0002698797,0.003662301,0.0001190806,0.0001400665,0.0002377833,0.00007729831,0.2524784,0.02236684,0.007283303,0.009212337,0.7037053],"study_design_scores_gemma":[0.000005289536,0.00002835585,0.0005136,0.000004124904,0.00001657162,0.00003690112,0.00000932063,0.9941751,0.002793554,0.001571446,0.0008394062,0.000006300985],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03752698,0.0007280774,0.9561754,0.0002755956,0.0001877564,0.0001084326,0.0007989014,0.001479508,0.002719372],"genre_scores_gemma":[0.704238,0.001015272,0.2816856,0.0002959754,0.0001954217,0.0002246583,0.003333148,0.0001099405,0.008902002],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01242832,"threshold_uncertainty_score":0.02471197,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07743029492135187,"score_gpt":0.3345494306104105,"score_spread":0.2571191356890586,"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."}}