{"id":"W2574246647","doi":"10.1109/ism.2016.0042","title":"Adaptive Pooling of the Most Relevant Spatio-Temporal Features for Action Recognition","year":2016,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Pooling; Computer science; Artificial intelligence; Pattern recognition (psychology); Dynamic time warping; ENCODE; Construct (python library); Joint (building); Action recognition; Computer vision; Class (philosophy); Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006948379,0.00102108,0.001088051,0.001243475,0.0002670578,0.0005603103,0.001002255,0.0005100276,0.001870255],"category_scores_gemma":[0.001357825,0.0002848738,0.0009758305,0.001161372,0.0003272581,0.001094699,0.0009704613,0.0005010391,0.0008146313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004792419,"about_ca_system_score_gemma":0.0006023573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003348058,"about_ca_topic_score_gemma":0.005085432,"domain_scores_codex":[0.9995222,0.00005300539,0.00003164028,0.000165937,0.0001585522,0.00006851262],"domain_scores_gemma":[0.9997051,0.00005049429,0.00005561671,0.00008586123,0.00006904233,0.00003376581],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003991693,0.0002711889,0.002079814,0.000161381,0.0001579045,0.0001898137,0.00009400422,0.02763975,0.2142479,0.00202675,0.003431592,0.7493007],"study_design_scores_gemma":[0.00002051866,0.0002950296,0.01141971,0.00002725612,0.0001750799,0.0003812673,0.00007386546,0.8816225,0.09589183,0.00558385,0.004439301,0.00006978997],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06828129,0.000820111,0.9262705,0.00009606534,0.0001090805,0.0001015659,0.0004283574,0.002249689,0.001643363],"genre_scores_gemma":[0.6917366,0.0006437015,0.3035283,0.0001297783,0.0001026712,0.0001320075,0.0009873725,0.0001770687,0.00256242],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003348058,"threshold_uncertainty_score":0.006657124,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04932348965639656,"score_gpt":0.2678970728435351,"score_spread":0.2185735831871386,"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."}}