{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006578679,0.00005623663,0.00005171572,0.00003180471,0.00004328323,0.00008442197,0.0001065112,0.000007600187,0.000001563765],"category_scores_gemma":[0.000009180781,0.00004172368,0.000005087192,0.0001515215,0.00001564144,0.000771215,0.00006885974,0.00003451738,0.000006556486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001819526,"about_ca_system_score_gemma":0.00002511308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001833627,"about_ca_topic_score_gemma":0.00002861132,"domain_scores_codex":[0.9995452,0.00001045448,0.00005875187,0.000168213,0.000118427,0.00009891314],"domain_scores_gemma":[0.9997162,0.000006833009,0.0000227721,0.0001427442,0.00003987774,0.00007153361],"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":[0.00001144962,0.00002212231,0.007967476,0.000008249411,0.000008359672,0.00002064047,0.001957425,0.0009469295,0.003202636,0.008998057,0.0002086756,0.976648],"study_design_scores_gemma":[0.001977813,0.0002443005,0.004666839,0.00005277588,0.000004526551,0.00008237796,0.001417503,0.9507111,0.02668124,0.00360372,0.01013879,0.0004190253],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01455922,0.0001204379,0.975935,0.0002161241,0.00003943811,0.00005782853,5.119415e-8,0.00009941935,0.008972489],"genre_scores_gemma":[0.4233592,0.00001021772,0.5760808,0.00030178,0.000006007408,0.00000261054,2.384741e-7,0.000003103199,0.0002361174],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.976229,"threshold_uncertainty_score":0.1701442,"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."}}