{"id":"W2126374126","doi":"10.1109/cvpr.2008.4587362","title":"Latent topic random fields: Learning using a taxonomy of labels","year":2008,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Classifier (UML); Probabilistic logic; Pattern recognition (psychology); Representation (politics); Contextual image classification; Feature learning; Image (mathematics); Hierarchy; Context model; Graphical model; Object detection; Machine learning; Object (grammar)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006325192,0.001388986,0.002068855,0.002828555,0.001095574,0.002439239,0.00333429,0.003133876,0.001808168],"category_scores_gemma":[0.01731851,0.0009250097,0.001742243,0.003146857,0.001527458,0.007406564,0.002161215,0.003951197,0.001093403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001663522,"about_ca_system_score_gemma":0.001254357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0035629,"about_ca_topic_score_gemma":0.004518019,"domain_scores_codex":[0.9968051,0.001557938,0.0001070712,0.0009273392,0.000429828,0.0001727753],"domain_scores_gemma":[0.9902751,0.007244871,0.0005868089,0.001094145,0.0005584565,0.000240463],"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":[0.0005781977,0.00059598,0.01273351,0.0006785108,0.0003426979,0.0002992821,0.001312365,0.2447658,0.005040346,0.1426707,0.02285573,0.568127],"study_design_scores_gemma":[0.0000464643,0.00006912861,0.0008009208,0.00006499844,0.00003539223,0.0001055924,0.00008171226,0.8488067,0.0008532627,0.1458855,0.003214647,0.00003582694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009623772,0.0007439742,0.9876425,0.0004714003,0.00005269345,0.00008079596,0.0002935626,0.0005615909,0.000529766],"genre_scores_gemma":[0.3701406,0.001978084,0.6168749,0.000724621,0.0007236059,0.0009321107,0.004454885,0.0003116994,0.003859388],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006325192,"threshold_uncertainty_score":0.0334512,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08348291829754127,"score_gpt":0.2504180563305242,"score_spread":0.1669351380329829,"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."}}