{"id":"W4398169558","doi":"10.3390/rs16111827","title":"GeoSparseNet: A Multi-Source Geometry-Aware CNN for Urban Scene Analysis","year":2024,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Geometry; Mathematics","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":[0.001085439,0.0002224928,0.0003866556,0.0006162946,0.0002016778,0.0005183567,0.0003399063,0.0001083922,0.000002401587],"category_scores_gemma":[0.0001595844,0.0002110111,0.0003951418,0.002709128,0.00003539443,0.0002230112,0.0001255566,0.000187987,0.0000354792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007659885,"about_ca_system_score_gemma":0.0000699267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001774143,"about_ca_topic_score_gemma":0.00007589715,"domain_scores_codex":[0.9980202,0.0001461008,0.0003070864,0.0007537992,0.0002713038,0.0005015054],"domain_scores_gemma":[0.9984093,0.0005232557,0.00007363954,0.0007383426,0.0001339486,0.0001214915],"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":[0.000003914247,0.000009040969,0.000191487,0.00006503695,0.0003735812,0.00006609406,0.0004618253,0.003740011,0.001035455,0.0001010172,0.0002751517,0.9936774],"study_design_scores_gemma":[0.0001723934,0.0000238344,0.0009774767,0.00009113386,0.0001341633,0.0000340926,0.00001694118,0.9814345,0.001546089,0.0003505065,0.01495305,0.0002658037],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01375129,0.001357475,0.982812,0.0005190289,0.0006586132,0.0001637125,0.000004946798,0.0006021819,0.0001307198],"genre_scores_gemma":[0.4475076,0.00001750175,0.5514446,0.0001828706,0.0002173541,3.72845e-8,0.000008317474,0.00002484359,0.0005968738],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9934116,"threshold_uncertainty_score":0.8604783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04202612936054859,"score_gpt":0.3204589400384319,"score_spread":0.2784328106778834,"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."}}