{"id":"W2946689049","doi":"10.1007/s10044-020-00901-9","title":"Spatio-temporal adversarial learning for detecting unseen falls","year":2020,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; Toronto Rehabilitation Institute; University Health Network","funders":"","keywords":"Autoencoder; Adversarial system; Classifier (UML); Deep learning; Rendering (computer graphics); Modalities; Class (philosophy); Adversarial machine learning; Feature learning","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001746721,0.00009665205,0.0002151429,0.0001069801,0.0002464986,0.0001935626,0.0002388996,0.0000364853,0.000015696],"category_scores_gemma":[0.00003384744,0.00009992331,0.0001477141,0.0007495352,0.00001462093,0.0001889793,0.00009375659,0.00009014511,0.00002745146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001371245,"about_ca_system_score_gemma":0.00001702952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002351621,"about_ca_topic_score_gemma":0.000314986,"domain_scores_codex":[0.9990476,0.00005576361,0.0002311548,0.0004054078,0.0001246859,0.0001354147],"domain_scores_gemma":[0.9992396,0.0001924473,0.0001710645,0.0001936286,0.00009343476,0.0001098434],"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":[0.000004453317,0.00002855445,0.12819,0.00002859213,0.0003240897,4.937931e-7,0.001118123,0.0002340975,0.0005080523,0.0002500885,0.00004249091,0.869271],"study_design_scores_gemma":[0.0007823273,0.00008915424,0.01210079,0.00001045905,0.000526776,0.000002809656,0.0004763305,0.9279351,0.001613045,0.0003181306,0.0556938,0.0004512274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01035058,0.00002348635,0.9877846,0.001265718,0.00001576143,0.0003287274,0.00001252203,0.0001167792,0.0001018485],"genre_scores_gemma":[0.9958867,0.000003687822,0.003215714,0.0003358384,0.0002028132,0.0002559695,0.00005510859,0.000006815195,0.0000373379],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9855362,"threshold_uncertainty_score":0.4074754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03176615309929862,"score_gpt":0.2679380683893751,"score_spread":0.2361719152900765,"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."}}