{"id":"W4402116421","doi":"10.20944/preprints202401.1672.v2","title":"Pedestrian Detection in Aerial Image Based on Convolutional Neural Network with Attention Mechanism and Multi-scale Prediction","year":2024,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Remote Sensing and Land Use","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Concordia University","funders":"Henan Provincial Science and Technology Research Project; Henan University","keywords":"Convolutional neural network; Pedestrian detection; Artificial intelligence; Computer science; Aerial image; Pattern recognition (psychology); Scale (ratio); Pedestrian; Mechanism (biology); Computer vision; Artificial neural network; Aerial imagery; Image (mathematics); Cartography; Geography; Engineering; Transport engineering","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":[0.0005671717,0.000282367,0.0002616782,0.0001769458,0.0001452478,0.00008533311,0.000111411,0.0002859648,0.0001966136],"category_scores_gemma":[0.00003490246,0.0002365743,0.00008276806,0.0001584519,0.00007973881,0.00007950557,0.00007778015,0.0008694019,0.0001753825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003072097,"about_ca_system_score_gemma":0.00009212255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003450081,"about_ca_topic_score_gemma":0.007227306,"domain_scores_codex":[0.9980125,0.0002250572,0.0003164517,0.0008222668,0.0003096249,0.0003140402],"domain_scores_gemma":[0.9993157,0.00006472682,0.0001309223,0.0003204008,0.00004499163,0.000123208],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008138653,0.0000559856,0.8435407,0.0001754784,0.00003745195,0.00005034094,0.0001370388,0.1477271,0.0009785404,0.000007074632,0.00001011248,0.006466206],"study_design_scores_gemma":[0.0004884204,0.00006781574,0.5348465,0.0001696968,0.00003236215,0.00001463366,0.00001602561,0.4633715,0.0002015553,0.0006220035,0.00002790795,0.0001416675],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9948514,0.00005268307,0.001186588,0.0001692168,0.002019519,0.0005136993,0.00009829502,0.0001615291,0.0009471131],"genre_scores_gemma":[0.9979531,0.00003880013,0.0008981969,0.00004615872,0.0005785443,0.000004044428,0.0003372024,0.00001332384,0.0001306312],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3156443,"threshold_uncertainty_score":0.9647222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04799815239874679,"score_gpt":0.2609461023755789,"score_spread":0.2129479499768321,"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."}}