{"id":"W2117069191","doi":"10.1109/iccv.2013.53","title":"From Subcategories to Visual Composites: A Multi-level Framework for Object Detection","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Artificial intelligence; Object (grammar); Computer science; Discriminative model; Benchmark (surveying); Set (abstract data type); Object detection; Class (philosophy); Support vector machine; Annotation; Computer vision; Pattern recognition (psychology); Granularity; Cluster analysis; Natural language processing","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":[0.00008125792,0.0001590984,0.0001729008,0.00009686473,0.0001460577,0.0002996716,0.0004865459,0.00009531502,0.0000288911],"category_scores_gemma":[0.0002131206,0.0001346781,0.00007276286,0.0003835199,0.00002404474,0.0009256107,0.0001950669,0.0001161029,0.0001636274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000443799,"about_ca_system_score_gemma":0.0000201393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003962435,"about_ca_topic_score_gemma":0.00002619329,"domain_scores_codex":[0.9989329,0.00002368751,0.000204542,0.0004120113,0.0001462052,0.0002806394],"domain_scores_gemma":[0.9989114,0.0003438349,0.00005580254,0.0003587002,0.0002143491,0.000115948],"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":[0.00003750529,0.0001611959,0.0002430417,0.00001555084,0.00003294539,0.00000213853,0.001193582,0.00001037151,0.162234,0.0162537,0.001252324,0.8185636],"study_design_scores_gemma":[0.000194789,0.0003819695,0.002742303,0.00002087565,0.000004147108,0.000001737635,0.00009330081,0.02322739,0.8586624,0.1129077,0.001491522,0.0002719439],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007183124,0.00004050232,0.990641,0.0004082016,0.0002186384,0.0007375567,0.000005181543,0.0007077153,0.00005807206],"genre_scores_gemma":[0.381166,0.00000357542,0.61772,0.0006798845,0.0000857355,0.000157278,0.00000248914,0.000009653688,0.0001754065],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8182917,"threshold_uncertainty_score":0.5492014,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04228013874165451,"score_gpt":0.3420224697172411,"score_spread":0.2997423309755866,"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."}}