{"id":"W4407583119","doi":"10.1002/sys.21800","title":"Two‐Stage Approach to Small‐Object Detection","year":2025,"lang":"en","type":"article","venue":"Systems Engineering","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; University of Calgary","keywords":"Object detection; Computer science; Background subtraction; Artificial intelligence; Field (mathematics); Object (grammar); Computer vision; Deep learning; Video tracking; Real-time computing; Pattern recognition (psychology); Pixel","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":[0.0004554568,0.0008142247,0.0006419041,0.0008238338,0.000384511,0.0009181918,0.001742292,0.001206227,0.003369109],"category_scores_gemma":[0.0007811141,0.0005008285,0.0007153991,0.0005077619,0.0003961652,0.001028675,0.001189622,0.0009966418,0.001401935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000636221,"about_ca_system_score_gemma":0.0009752524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004126978,"about_ca_topic_score_gemma":0.005899578,"domain_scores_codex":[0.9994885,0.00004520798,0.00002431079,0.000162178,0.0002031431,0.000076696],"domain_scores_gemma":[0.9994867,0.0001138528,0.00004079912,0.00008435693,0.0002349832,0.00003935725],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003635194,0.0002879881,0.002470722,0.0001850547,0.000128058,0.0003243375,0.0001565347,0.1259981,0.2083703,0.008665386,0.004767512,0.6482825],"study_design_scores_gemma":[0.00000750766,0.00007319147,0.0004996933,0.000005643672,0.0000141181,0.00007959337,0.00000862169,0.9741769,0.02191289,0.001360114,0.001847647,0.00001393658],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01333502,0.0001836397,0.983402,0.0001015151,0.00005447459,0.00007685593,0.00004469426,0.001385727,0.001416024],"genre_scores_gemma":[0.3542741,0.0002736824,0.6335993,0.0002689307,0.00007045777,0.0001571279,0.0002480459,0.000128734,0.01097969],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004126978,"threshold_uncertainty_score":0.01127082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01280016910598661,"score_gpt":0.2283887388199488,"score_spread":0.2155885697139622,"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."}}