{"id":"W2251216540","doi":"","title":"Getting More from Segmentation Evaluation","year":2012,"lang":"en","type":"article","venue":"","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Segmentation; Measure (data warehouse); Artificial intelligence; Precision and recall; Window (computing); Sensitivity (control systems); Image segmentation; Pattern recognition (psychology); Computer vision; Data mining; Engineering","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":[0.0004738849,0.00004114522,0.00004538739,0.00004108145,0.00006385426,0.0000781843,0.0001211606,0.00002012494,0.0001745609],"category_scores_gemma":[0.00003445761,0.00003460619,0.0000249732,0.0001756214,0.000003541111,0.0009925095,0.00004039804,0.00002136527,0.0000725446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003432786,"about_ca_system_score_gemma":0.00001266716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009007379,"about_ca_topic_score_gemma":0.000008243051,"domain_scores_codex":[0.9993238,0.0000603192,0.0001132011,0.0001095703,0.0002933534,0.00009974924],"domain_scores_gemma":[0.9996486,0.00002807212,0.00004900962,0.0001691288,0.00006802543,0.00003722126],"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":[0.000001123363,0.00008113361,0.111502,0.000002369645,0.00004706468,1.995886e-7,0.004913121,0.001570918,0.02807735,0.02143013,0.002025545,0.830349],"study_design_scores_gemma":[0.0001328169,0.000003964131,0.06704041,0.000002469138,0.00002235294,2.219179e-7,0.0001557189,0.9208683,0.0103107,0.001169808,0.0002126565,0.00008056985],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1100133,0.00009066083,0.8861657,0.0005014082,0.0001558895,0.00006225713,2.869041e-7,0.00005236654,0.002958138],"genre_scores_gemma":[0.9352431,0.000002138022,0.0640776,0.0004224823,0.0001062283,0.000007350974,0.00003979495,0.000001975054,0.00009938185],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9192974,"threshold_uncertainty_score":0.1911319,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0298299330533433,"score_gpt":0.3007590947675822,"score_spread":0.2709291617142389,"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."}}