{"id":"W2153734993","doi":"","title":"Spatio-temporal object recognition using variational learning of an infinite statistical model","year":2013,"lang":"en","type":"article","venue":"European Signal Processing Conference","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Inference; Artificial intelligence; Bayesian inference; Machine learning; Statistical model; Bayes' theorem; Object (grammar); Statistical inference; Pattern recognition (psychology); Cognitive neuroscience of visual object recognition; Feature (linguistics); Activity recognition; Nonparametric statistics; Bayesian probability; Key (lock); Mathematics","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":[0.0008414881,0.0001756006,0.00020106,0.0001178849,0.0001916984,0.0004061332,0.0004446809,0.00004503919,0.0001063339],"category_scores_gemma":[0.00008627408,0.0001679372,0.000032417,0.0002242686,0.00008522079,0.001389266,0.000130764,0.0002844805,0.00003338438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002031374,"about_ca_system_score_gemma":0.0003536725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004607708,"about_ca_topic_score_gemma":0.000001243234,"domain_scores_codex":[0.9979164,0.0006557794,0.0004170711,0.0004246979,0.0003365532,0.0002495263],"domain_scores_gemma":[0.9987342,0.00009074823,0.0003057156,0.0001833234,0.0005486829,0.0001373593],"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":[0.0000159729,0.00009066865,0.0001727015,0.0000768996,0.00001034148,0.00001146592,0.001834031,0.007275467,0.007461374,0.01906949,0.00001876279,0.9639629],"study_design_scores_gemma":[0.0001905255,0.00009933995,0.0007627788,0.0001083224,0.000009546175,0.0000130349,0.00001501494,0.9415504,0.0004519337,0.05657899,0.00001183734,0.0002083126],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02311837,0.00001818089,0.97075,0.0000318879,0.0000321243,0.0001195026,0.000006520918,0.0001072273,0.005816173],"genre_scores_gemma":[0.5110486,7.316858e-7,0.4887945,0.00005648016,0.0000361345,0.000001905501,0.00002114694,0.00001133426,0.00002921745],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9637545,"threshold_uncertainty_score":0.684828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06534754987773936,"score_gpt":0.2898479345544215,"score_spread":0.2245003846766822,"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."}}