{"id":"W4416854622","doi":"10.1080/07038992.2025.2586320","title":"UBR-Net: Road Extraction from High-Resolution Remote Sensing Imagery Using Multi-Scale Attention and Cross-Residual Encoding","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Automated Road and Building Extraction","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Science Foundation of Gansu Province; National Natural Science Foundation of China","keywords":"Context (archaeology); Feature extraction; Segmentation; Encoding (memory); Block (permutation group theory); Process (computing); Intersection (aeronautics); Focus (optics); Channel (broadcasting)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003409045,0.001454117,0.0007620372,0.001477814,0.0003851301,0.000804217,0.001977952,0.0007817944,0.004214431],"category_scores_gemma":[0.0008574675,0.0004463885,0.001011029,0.001053531,0.0003033668,0.001491878,0.00145436,0.0008263828,0.00273987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007729554,"about_ca_system_score_gemma":0.0008259392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01960811,"about_ca_topic_score_gemma":0.04023466,"domain_scores_codex":[0.9997576,0.00001835799,0.000008343043,0.0001057018,0.00006477143,0.00004524129],"domain_scores_gemma":[0.9998266,0.00003519216,0.00001780259,0.00004801549,0.00005670166,0.00001576426],"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":[0.0003025699,0.0002751084,0.003288731,0.0002778095,0.0001852844,0.0002257389,0.0001291866,0.09127131,0.02538488,0.00291237,0.03734398,0.838403],"study_design_scores_gemma":[0.00003910307,0.00009875352,0.002984165,0.00003075535,0.00007136983,0.0001652349,0.00007132329,0.9577374,0.02151011,0.004534695,0.01272507,0.0000318753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09917017,0.001766221,0.8113111,0.0004511584,0.0003034122,0.0003736396,0.007227789,0.06688384,0.01251274],"genre_scores_gemma":[0.4205842,0.0006851479,0.5374897,0.000467434,0.0001220708,0.0003055526,0.02419632,0.001881582,0.01426787],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01960811,"threshold_uncertainty_score":0.03898793,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01526109816309899,"score_gpt":0.2583543469163672,"score_spread":0.2430932487532682,"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."}}