{"id":"W4411114699","doi":"10.1016/j.eswa.2025.128459","title":"MFEL-YOLO for small object detection in UAV aerial images","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Infrared Target Detection Methodologies","field":"Engineering","cited_by":31,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Science Basic Research Program of Shaanxi Province; Key Research and Development Projects of Shaanxi Province; Alberta Innovates; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Computer vision; Artificial intelligence; Object detection; Object (grammar); Remote sensing; Aerial image; Pattern recognition (psychology); Image (mathematics); Geography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002822918,0.0004885424,0.0003461587,0.00049635,0.0002477754,0.0004755777,0.0004881644,0.0004812874,0.01489549],"category_scores_gemma":[0.0008196165,0.0001399713,0.0002948143,0.0002726839,0.0001281136,0.0003958904,0.0005347625,0.0003885303,0.005040763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002338057,"about_ca_system_score_gemma":0.0005195106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003814351,"about_ca_topic_score_gemma":0.007722925,"domain_scores_codex":[0.999872,0.00002037536,0.000006823057,0.00003211495,0.00004020944,0.00002856153],"domain_scores_gemma":[0.9998647,0.00004406468,0.00001145237,0.00001661339,0.00005223626,0.00001091432],"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":[0.0007365202,0.0001735088,0.0009784742,0.0004182334,0.00007033748,0.0001429757,0.0001040552,0.01630747,0.07732838,0.004624306,0.02847205,0.8706437],"study_design_scores_gemma":[0.00008962162,0.0002214092,0.003689753,0.00008579947,0.00003690565,0.0002126159,0.00008181328,0.871991,0.08135035,0.002298754,0.03990954,0.00003235363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03924106,0.0008788182,0.9298664,0.0002352531,0.0001970319,0.0001409893,0.001276963,0.0203749,0.007788519],"genre_scores_gemma":[0.1927879,0.0004031369,0.7807077,0.0002295546,0.0000926717,0.0004002175,0.003234857,0.0008558722,0.02128816],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01489549,"threshold_uncertainty_score":0.04983044,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02013418818256294,"score_gpt":0.2729607291042553,"score_spread":0.2528265409216923,"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."}}