{"id":"W2047618665","doi":"10.1145/2393347.2396320","title":"Depth estimation for semi-automatic 2D to 3D conversion","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Computer vision; Artificial intelligence; 2D to 3D conversion; Task (project management); Process (computing); Semi automatic; Stereoscopy; Depth map; Image (mathematics); 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":[0.0001366742,0.0000580406,0.00006313797,0.00005582657,0.00007358045,0.0000442871,0.0001909408,0.0000143149,0.00003309104],"category_scores_gemma":[0.00006402146,0.00004791676,0.00002207168,0.0001349776,0.000005353261,0.0008990776,0.00009216267,0.0000228291,0.0002854516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002723244,"about_ca_system_score_gemma":0.00001014431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002145687,"about_ca_topic_score_gemma":3.518095e-7,"domain_scores_codex":[0.9994761,0.000009461595,0.0000968605,0.0001190585,0.0001039041,0.0001946628],"domain_scores_gemma":[0.9995592,0.00007141932,0.00002754259,0.0001955117,0.00003404063,0.0001122626],"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":[0.000001566662,0.0000316078,0.0004253185,0.00002228236,0.000002289547,1.675361e-7,0.0005547722,0.0003645428,0.001179088,0.009954929,0.007370282,0.9800932],"study_design_scores_gemma":[0.0001514505,0.00002431963,0.00100635,0.00001354246,0.000001650841,0.000003165315,0.00002532492,0.9786622,0.007443651,0.0004207598,0.01216672,0.00008089478],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002311433,0.00001823724,0.9940154,0.0006732974,0.0002986169,0.0001861724,2.320645e-7,0.0001979143,0.002298721],"genre_scores_gemma":[0.3519785,4.878415e-7,0.6463429,0.001285624,0.00001977658,0.000008726654,9.720912e-7,0.000003078766,0.0003599109],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9800122,"threshold_uncertainty_score":0.3668998,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02139832541117124,"score_gpt":0.3129263149896551,"score_spread":0.2915279895784839,"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."}}