{"id":"W4417271794","doi":"10.1038/s41598-025-27441-8","title":"Pedestrian detection in aerial image based on convolutional neural network with attention mechanism and multi-scale prediction","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Henan Provincial Science and Technology Research Project","keywords":"Pedestrian detection; Convolutional neural network; Object detection; Pedestrian; Aerial image; Object (grammar); Deep learning; Pattern recognition (psychology)","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":[0.0005860614,0.000133127,0.0001228296,0.0002148967,0.0004696998,0.000268263,0.000144162,0.00005991896,0.000002908707],"category_scores_gemma":[0.00003007807,0.0001238174,0.00003402946,0.001201244,0.0001477896,0.0004502652,0.00007878384,0.0001514719,0.000002388628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009650864,"about_ca_system_score_gemma":0.00009208408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001533577,"about_ca_topic_score_gemma":0.0002158151,"domain_scores_codex":[0.998134,0.00007217781,0.0003414823,0.0008704704,0.0003081507,0.0002737018],"domain_scores_gemma":[0.999006,0.00004900829,0.0001841881,0.0005872775,0.0001043599,0.00006910679],"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":[0.0005161631,0.001290184,0.06183069,0.0001464855,0.00004615721,0.0004983259,0.0002938574,0.4776894,0.3570367,0.02178989,0.003982318,0.07487984],"study_design_scores_gemma":[0.0005668844,0.00006769706,0.03250256,0.00005311895,0.000008030796,0.00005810994,0.000007043719,0.9463818,0.003654278,0.01613571,0.0004376675,0.0001270667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2012998,0.00001393136,0.7943057,0.0003096437,0.003284187,0.0005171862,0.000001569178,0.0001479408,0.0001199393],"genre_scores_gemma":[0.9617842,0.000001152204,0.03764835,0.00005859517,0.0000772532,0.0001182112,0.00002489706,0.000006562021,0.0002808197],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7604843,"threshold_uncertainty_score":0.5049129,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01007135589966537,"score_gpt":0.238496489659087,"score_spread":0.2284251337594217,"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."}}