{"id":"W4391170797","doi":"10.20944/preprints202401.1672.v1","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":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Concordia University","funders":"","keywords":"Convolutional neural network; Aerial image; Computer science; Artificial intelligence; Pedestrian detection; Pedestrian; Scale (ratio); Mechanism (biology); Aerial imagery; Artificial neural network; Image (mathematics); Pattern recognition (psychology); Computer vision; Geography; Cartography; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004576838,0.000393521,0.0003112767,0.0002345564,0.0001973613,0.0001115034,0.0005272144,0.0002856583,0.00001595736],"category_scores_gemma":[0.00003318518,0.0003979574,0.00010161,0.0004904701,0.000107066,0.0002470573,0.00135031,0.001211817,0.0001066779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002796607,"about_ca_system_score_gemma":0.0001192657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007478853,"about_ca_topic_score_gemma":0.0002198624,"domain_scores_codex":[0.9969028,0.000202537,0.0004805414,0.001595325,0.0004026089,0.0004161679],"domain_scores_gemma":[0.9984009,0.0001010437,0.0002603485,0.0009927131,0.0001036665,0.0001412815],"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":[0.0007845456,0.000753398,0.1046546,0.0005322786,0.000119486,0.00009185574,0.0004431739,0.8090389,0.06215215,0.01090048,0.00005134784,0.01047778],"study_design_scores_gemma":[0.0007780584,0.00007177681,0.1625549,0.0002088975,0.0000299413,0.00002051445,0.000005938098,0.8174336,0.002632022,0.0159126,0.00004701635,0.0003047472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5179284,0.00003078853,0.478521,0.0005795283,0.001143994,0.00114776,0.00002496361,0.0004723814,0.0001511593],"genre_scores_gemma":[0.9751223,0.00002693115,0.0233764,0.00008802652,0.0004772501,0.0007226623,0.00005956704,0.00004129957,0.0000856219],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4571938,"threshold_uncertainty_score":0.9998472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05457190058564022,"score_gpt":0.3023423917639086,"score_spread":0.2477704911782684,"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."}}