{"id":"W3126161118","doi":"10.1023/b:visi.0000027789.58057.14","title":"Learning Generative Models of Scene Features","year":2004,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Artificial intelligence; Computer science; Computer vision; Generative model; Measure (data warehouse); A priori and a posteriori; Probabilistic logic; Pattern recognition (psychology); Visualization; Object (grammar); Salient; Set (abstract data type); Statistical model; Generative grammar; Data mining","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":[0.0002852784,0.00008448337,0.0001496238,0.0002430367,0.00003570004,0.0001199318,0.0009653457,0.00004250598,0.000003904351],"category_scores_gemma":[0.00001955825,0.00006640989,0.000121771,0.0001405764,0.00003516693,0.0008767327,0.0001733192,0.0001959034,0.000002711975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007631821,"about_ca_system_score_gemma":0.00009667598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005162216,"about_ca_topic_score_gemma":2.116918e-7,"domain_scores_codex":[0.9987131,0.00005194499,0.0003980637,0.0001185172,0.0006382145,0.00008017452],"domain_scores_gemma":[0.9982219,0.00004467614,0.0004667509,0.000112423,0.001105906,0.00004839833],"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":[0.0001173372,0.0003932115,0.00006791569,0.00001065101,0.0001637911,0.0001263703,0.001893088,0.05758038,0.05727383,0.1653753,0.000752706,0.7162454],"study_design_scores_gemma":[0.001949092,0.002036795,0.003895777,0.0005623631,0.00001303666,0.000901734,0.00003436986,0.2483689,0.5941379,0.1455686,0.002232554,0.0002989106],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01063758,0.0001531656,0.986239,0.002058992,0.0005986064,0.00003507085,6.378235e-7,0.00002996571,0.0002469718],"genre_scores_gemma":[0.7068257,0.00009491155,0.2926895,0.0001426337,0.0002092858,3.167942e-7,9.003455e-7,0.000003632079,0.00003314699],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7159465,"threshold_uncertainty_score":0.2708117,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01519103776733947,"score_gpt":0.2978155752803361,"score_spread":0.2826245375129967,"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."}}