{"id":"W2559545830","doi":"10.1109/iccv.2017.327","title":"TorontoCity: Seeing the World with a Million Eyes","year":2017,"lang":"en","type":"article","venue":"","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":179,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"University of Toronto; Nvidia","keywords":"Benchmark (surveying); Computer science; Convolutional neural network; Segmentation; Artificial intelligence; Ground truth; Scale (ratio); Feature extraction; Drone; Variety (cybernetics); Deep learning; Image segmentation; Computer vision; Machine learning; Cartography; Geography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008389071,0.00004527951,0.00003556223,0.000003846617,0.0008018516,0.0001015713,0.0002008982,0.000009947145,0.0004677598],"category_scores_gemma":[0.000006518153,0.00002275603,0.00001447888,0.00002853821,0.0001881262,0.00009451203,0.00007075061,0.00004329303,0.000289481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003058333,"about_ca_system_score_gemma":0.000002240243,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00362,"about_ca_topic_score_gemma":0.02087829,"domain_scores_codex":[0.9996316,0.000008572387,0.00003992941,0.0001146759,0.0001094695,0.00009572445],"domain_scores_gemma":[0.9994358,0.0000171943,0.00003684005,0.0004796342,0.000002111291,0.00002836552],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00003753553,0.0001086889,0.2080739,0.000005204688,0.00004324337,0.000009494296,0.002178782,0.0008970686,0.01700344,0.006007321,0.08282472,0.6828106],"study_design_scores_gemma":[0.0001381555,0.00001841286,0.6064807,0.000009851026,0.00001144696,0.000007293606,0.0001536376,0.00285207,0.003169081,0.0005747849,0.3864547,0.0001298084],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2883669,0.00000585875,0.001465563,0.003885281,0.00002304444,0.0001092969,2.423131e-7,0.0000314191,0.7061124],"genre_scores_gemma":[0.9651607,0.000002197206,0.003075618,0.0002353067,0.00002813588,0.000001559996,3.300423e-7,0.000004310895,0.03149186],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6826808,"threshold_uncertainty_score":0.9969881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01177411459887781,"score_gpt":0.2472483353708786,"score_spread":0.2354742207720008,"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."}}