{"id":"W2210014073","doi":"10.1109/iccv.2015.196","title":"Learning to Combine Mid-Level Cues for Object Proposal Generation","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Parametric statistics; Computer science; Set (abstract data type); Artificial intelligence; Context (archaeology); Object (grammar); Perception; Machine learning; Pattern recognition (psychology); 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":[0.0003204054,0.00009086252,0.000105563,0.00006929856,0.00008539094,0.0001246407,0.0002999795,0.00003295379,0.000002688339],"category_scores_gemma":[0.000305598,0.00007461444,0.00003177863,0.0002236656,0.00001127526,0.0005684167,0.0001386537,0.00006319047,0.00002812136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004181126,"about_ca_system_score_gemma":0.00008947352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001597761,"about_ca_topic_score_gemma":0.00001232298,"domain_scores_codex":[0.9992299,0.000030009,0.0001376245,0.0002538333,0.0001657276,0.0001828806],"domain_scores_gemma":[0.9993536,0.00003282968,0.00003647053,0.0002049312,0.000260988,0.0001111663],"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":[0.00006351919,0.0001501504,0.0005765518,0.00002605347,0.00001986312,0.000008720681,0.002318853,0.0006504635,0.1392497,0.08567723,0.0910477,0.6802112],"study_design_scores_gemma":[0.0003917791,0.001288823,0.00006262388,0.000008817216,0.000002691435,0.000006679442,0.00004434394,0.03385493,0.9144368,0.01450063,0.03518889,0.0002130224],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002767557,0.00003215912,0.9935258,0.00148399,0.0001520299,0.0003947914,8.946584e-7,0.0004773483,0.001165429],"genre_scores_gemma":[0.2065553,0.000003083014,0.7878785,0.0004867137,0.0001232296,0.00004821006,0.000006689393,0.000008837216,0.004889515],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7751871,"threshold_uncertainty_score":0.3042688,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08988105809586411,"score_gpt":0.3408689191009366,"score_spread":0.2509878610050725,"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."}}