{"id":"W260801291","doi":"10.1109/iccv.2015.300","title":"Monocular Object Instance Segmentation and Depth Ordering with CNNs","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":142,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Monocular; Artificial intelligence; Benchmark (surveying); Markov random field; Convolutional neural network; Computer science; Segmentation; Pattern recognition (psychology); Image segmentation; Image (mathematics); Object (grammar); Computer vision; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004465056,0.001446413,0.00108647,0.0007650065,0.0002752227,0.0009552339,0.001950989,0.001326969,0.002269645],"category_scores_gemma":[0.001172045,0.0007837976,0.0008932273,0.000900083,0.0006108318,0.002101025,0.001034704,0.001308366,0.0007946766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001483088,"about_ca_system_score_gemma":0.0009553764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01285705,"about_ca_topic_score_gemma":0.01796801,"domain_scores_codex":[0.9996163,0.00003819746,0.00001038444,0.0001819427,0.00008292381,0.00007022467],"domain_scores_gemma":[0.999627,0.00009473667,0.00007119335,0.0001162185,0.00005330062,0.00003763279],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003920728,0.00009632728,0.002322467,0.000176001,0.0001515198,0.0001985019,0.00007583368,0.5384865,0.04195511,0.009250872,0.004941019,0.4019538],"study_design_scores_gemma":[0.000004939498,0.00002336495,0.0005758377,0.000007556095,0.00001008125,0.00004890995,0.000007732775,0.9880648,0.006288804,0.004288545,0.0006713276,0.00000805453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05539857,0.0009026026,0.9338277,0.0002599109,0.0000818413,0.00006714852,0.0007571791,0.005838911,0.002866075],"genre_scores_gemma":[0.6206639,0.0005862632,0.37092,0.0003471411,0.00009674095,0.0000639048,0.001794029,0.0004309127,0.005097129],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01285705,"threshold_uncertainty_score":0.02556443,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02439234388783449,"score_gpt":0.2746856989399569,"score_spread":0.2502933550521224,"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."}}