{"id":"W772929749","doi":"10.1016/j.neucom.2015.04.015","title":"Likelihood-based feature relevance for figure-ground segmentation in images and videos","year":2015,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke; Université du Québec en Outaouais","funders":"","keywords":"Artificial intelligence; Computer science; Segmentation; Pattern recognition (psychology); Image segmentation; Feature (linguistics); Computer vision; Scale-space segmentation; Segmentation-based object categorization; Image (mathematics); Relevance (law)","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":[0.0003299939,0.0001466745,0.0001576649,0.0001118429,0.00008413701,0.0001638026,0.0002896539,0.0000537215,2.155125e-7],"category_scores_gemma":[0.0002956838,0.0001451198,0.00003272985,0.0003377037,0.00002561964,0.000631827,0.0001232558,0.0001727283,0.000001796934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004988176,"about_ca_system_score_gemma":0.0000549508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000843981,"about_ca_topic_score_gemma":0.000002501651,"domain_scores_codex":[0.9988555,0.00005606233,0.0001893873,0.0004373887,0.0001727917,0.0002888425],"domain_scores_gemma":[0.9991205,0.0003355375,0.0001123225,0.0002275963,0.0001141865,0.00008981504],"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":[0.00006533215,0.00008655989,0.00340629,0.0001373107,0.000004855997,0.00005313279,0.0005904007,0.0009715657,0.02937647,0.0009182045,0.004432536,0.9599574],"study_design_scores_gemma":[0.004306606,0.0011625,0.00979199,0.0003575416,0.00001391555,0.00005454819,0.0001290305,0.5368411,0.3937844,0.02908916,0.02354287,0.0009263754],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0218103,0.0003777968,0.9756685,0.00113003,0.000123823,0.000483341,0.000001684598,0.0002698582,0.0001346761],"genre_scores_gemma":[0.3624494,0.00001635002,0.6359501,0.001372426,0.00009909942,0.0000331097,0.000004276063,0.00001797156,0.00005724818],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.959031,"threshold_uncertainty_score":0.5917815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02556042433532175,"score_gpt":0.3029990851636428,"score_spread":0.277438660828321,"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."}}