{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001388187,0.00006812224,0.00007222334,0.00005604902,0.0001211129,0.00002881253,0.0001680472,0.00004698161,0.00004912293],"category_scores_gemma":[0.00006279791,0.00003613387,0.00007029917,0.0001316198,0.00002475903,0.0004901521,0.00003715068,0.00004313037,0.00002300369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003174382,"about_ca_system_score_gemma":0.00003881048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003941121,"about_ca_topic_score_gemma":0.000145301,"domain_scores_codex":[0.9993915,0.00004020708,0.0001558675,0.0001707144,0.0001339358,0.0001077695],"domain_scores_gemma":[0.9993495,0.0001217082,0.0001456654,0.0001694126,0.0001896115,0.00002414259],"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":[0.00008426696,0.000070335,0.0001852974,0.00001925607,0.00002972485,3.652648e-7,0.0002227109,0.000005297058,0.01518846,0.01150811,0.007929432,0.9647567],"study_design_scores_gemma":[0.001555665,0.0003883658,0.009194592,0.0003224071,0.00003444846,0.00002496529,0.0002141643,0.005978362,0.8467748,0.1273597,0.007801015,0.0003515706],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1021452,0.00001217972,0.8917746,0.002386503,0.0006957686,0.0004115393,0.0000258873,0.0001129001,0.002435372],"genre_scores_gemma":[0.98651,0.00001285203,0.01196951,0.0002150628,0.0001130135,0.00002699835,0.000006966393,0.000005274557,0.001140308],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9644052,"threshold_uncertainty_score":0.1473496,"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."}}