{"id":"W4391308406","doi":"10.1109/smc53992.2023.10393905","title":"Object Semantics Give Us the Depth We Need: Multi-Task Approach to Aerial Depth Completion","year":2023,"lang":"en","type":"article","venue":"","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of Ottawa; University of Victoria","funders":"","keywords":"Computer science; Task (project management); Semantics (computer science); Object (grammar); Artificial intelligence; Computer vision; Programming language; Natural language processing; 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":[0.0001398483,0.0001633916,0.0001611453,0.000116506,0.000116604,0.00008516391,0.0001504998,0.00008145017,0.0000123529],"category_scores_gemma":[0.00003285119,0.0001232026,0.00005944012,0.0005542538,0.0000215425,0.00004602231,0.00003973646,0.0001129833,0.0002596638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000047926,"about_ca_system_score_gemma":0.00001137941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001118194,"about_ca_topic_score_gemma":0.0002473438,"domain_scores_codex":[0.9990733,0.00003900353,0.0002058398,0.0001790429,0.0002091869,0.0002935781],"domain_scores_gemma":[0.9995465,0.00005600751,0.00001906929,0.0002501527,0.00004826843,0.00008004693],"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":[0.000006257132,0.00002186951,0.0003889955,0.00003496966,0.00002645694,0.000001877709,0.0004619285,0.9876637,0.003349219,0.001005009,0.006433493,0.0006061601],"study_design_scores_gemma":[0.0003483357,0.00002383696,0.007685788,0.0000107406,0.00001937509,0.000003252877,0.0004793048,0.9861104,0.001645027,0.00003100726,0.003451958,0.0001909785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1121263,0.00003088704,0.8762928,0.0004520302,0.0009573558,0.0006624792,0.0000151029,0.001027288,0.008435795],"genre_scores_gemma":[0.9918362,0.00005728055,0.007176315,0.0001676486,0.0002208921,0.0000216841,0.000126727,0.00005255914,0.0003407131],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8797099,"threshold_uncertainty_score":0.5024058,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03708786121564106,"score_gpt":0.2433039426049789,"score_spread":0.2062160813893378,"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."}}