{"id":"W3110787063","doi":"10.1109/smc42975.2020.9283020","title":"Instance-Based Learning for Human Action Recognition","year":2020,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Discriminative model; Kullback–Leibler divergence; Divergence (linguistics); Mixture model; Pattern recognition (psychology); Optical flow; Gaussian; Cluster analysis; Action recognition; Feature vector; Leverage (statistics); Vector quantization; Machine learning; Gesture recognition; Gesture; Image (mathematics); Class (philosophy)","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":[0.001324228,0.001089003,0.001560875,0.001248046,0.0003594852,0.001086428,0.002226732,0.001521285,0.003070914],"category_scores_gemma":[0.003056086,0.0003711685,0.001154082,0.001671525,0.000583386,0.001535582,0.0008726295,0.002230721,0.00131824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001182677,"about_ca_system_score_gemma":0.0008439823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007692047,"about_ca_topic_score_gemma":0.008090308,"domain_scores_codex":[0.9989961,0.0002539551,0.00006523288,0.0003879235,0.0001982949,0.00009849327],"domain_scores_gemma":[0.9989015,0.0005267634,0.0001131518,0.0002418864,0.0001479831,0.00006869101],"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":[0.0002643482,0.0003279716,0.002827282,0.0001691628,0.0001892473,0.0001064087,0.0000589122,0.2367774,0.004818671,0.006822513,0.01112994,0.7365081],"study_design_scores_gemma":[0.000007171763,0.00003343037,0.0004841766,0.00000897436,0.000007744577,0.0000325753,0.00001349536,0.9893519,0.001301189,0.007888665,0.0008625002,0.000008088969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0222616,0.001490793,0.9681919,0.0003081299,0.0001263063,0.0001164948,0.0008585891,0.005290941,0.001355347],"genre_scores_gemma":[0.5681431,0.0007881061,0.4226933,0.0003734901,0.0001705402,0.0002558401,0.004142893,0.0002370893,0.003195604],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007692047,"threshold_uncertainty_score":0.01529455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1476423700799036,"score_gpt":0.3068644526497591,"score_spread":0.1592220825698555,"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."}}