{"id":"W4413765695","doi":"10.21203/rs.3.rs-7333218/v1","title":"Pedestrian Detection in Aerial Image Based on Convolutional Neural Network with Attention Mechanism and Multi-scale Prediction","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Remote Sensing and Land Use","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Convolutional neural network; Pedestrian detection; Computer science; Artificial intelligence; Pedestrian; Aerial image; Scale (ratio); Image (mathematics); Mechanism (biology); Computer vision; Pattern recognition (psychology); Cartography; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002439798,0.0005675331,0.0005736322,0.0007248569,0.0002300068,0.0003724851,0.0005340617,0.0005195952,0.001381133],"category_scores_gemma":[0.0004134702,0.0002756505,0.000428054,0.0005814061,0.000200916,0.0005276617,0.0003852155,0.0004000798,0.0003048202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000446562,"about_ca_system_score_gemma":0.000416537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01407319,"about_ca_topic_score_gemma":0.01773505,"domain_scores_codex":[0.9998659,0.000009828834,0.000003733602,0.00005319091,0.00002744697,0.00003998145],"domain_scores_gemma":[0.9998567,0.00003602159,0.00001678367,0.00002090499,0.00005220413,0.00001727988],"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":[0.0009340408,0.0003187039,0.01517425,0.0001765596,0.0002344578,0.0005316209,0.00008490964,0.1828588,0.09798098,0.002527871,0.006934321,0.6922436],"study_design_scores_gemma":[0.000004539692,0.00002490063,0.00353208,0.000003417745,0.00002071138,0.00004532919,0.000006379551,0.989996,0.005730418,0.0004364414,0.0001948758,0.00000496232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4788566,0.001217137,0.5115176,0.0003833086,0.0002737072,0.00007707319,0.0004957422,0.002171493,0.005007281],"genre_scores_gemma":[0.9448494,0.0002898231,0.0507351,0.00007532104,0.00007200328,0.00001751025,0.0004123668,0.00003460176,0.003513922],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01407319,"threshold_uncertainty_score":0.02798253,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03498153891595115,"score_gpt":0.297084334794484,"score_spread":0.2621027958785329,"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."}}