{"id":"W2107640784","doi":"","title":"Contextual Models for Object Detection Using Boosted Random Fields","year":2004,"lang":"en","type":"article","venue":"DSpace@MIT (Massachusetts Institute of Technology)","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":305,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia Hospital","funders":"Defense Advanced Research Projects Agency","keywords":"Conditional random field; Boosting (machine learning); Exploit; Computer science; Inference; Artificial intelligence; Object detection; Pixel; Graph; Random field; Pattern recognition (psychology); Cascade; Machine learning; Computer vision; Theoretical computer science; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002608535,0.0003245355,0.000538143,0.0007379106,0.0002746924,0.00006069454,0.001073793,0.0005441703,0.000001379605],"category_scores_gemma":[0.0004086282,0.0003153897,0.0002203188,0.001144164,0.0003510957,0.001657259,0.0003136816,0.0003912045,0.000002730541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001989538,"about_ca_system_score_gemma":0.0001908212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007986428,"about_ca_topic_score_gemma":0.00009116553,"domain_scores_codex":[0.9980668,0.00001963799,0.0005061161,0.0006221979,0.0002804425,0.0005048286],"domain_scores_gemma":[0.9982656,0.00005332167,0.0003367073,0.00093116,0.0003364307,0.00007674761],"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":[0.0006943966,0.0005744527,0.0001725784,0.0002881574,0.000480423,0.0001331549,0.0008672946,0.02181263,0.2032848,0.2335289,0.0004409117,0.5377223],"study_design_scores_gemma":[0.004360413,0.0006400515,0.00001198907,0.0001840619,0.00005376466,0.0000891801,0.00004974593,0.03366085,0.8135309,0.1322144,0.01469144,0.0005132001],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02880297,0.0005975578,0.9657874,0.001841554,0.0004757924,0.0009353707,0.00002077113,0.001241993,0.0002966425],"genre_scores_gemma":[0.7003778,0.00006736516,0.2992302,0.0001556228,0.00003715215,0.00006568168,0.00000307041,0.00001961068,0.00004345288],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6715748,"threshold_uncertainty_score":0.9999298,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0291059072421215,"score_gpt":0.286198180272219,"score_spread":0.2570922730300976,"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."}}