{"id":"W4400259700","doi":"10.1007/s44268-024-00036-4","title":"Content annotation in images from outdoor construction jobsites using YOLO V8 and Swin transformer","year":2024,"lang":"en","type":"article","venue":"Smart Construction and Sustainable Cities","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Annotation; Segmentation; Artificial intelligence; Transformer; Image retrieval; Precision and recall; Information retrieval; Image (mathematics); Engineering","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":[0.0004530727,0.0007173872,0.0004893218,0.00300775,0.0004357112,0.0007635815,0.0004186548,0.0007419314,0.003247078],"category_scores_gemma":[0.0007897805,0.0002280165,0.0004520572,0.00131487,0.000288341,0.0005415184,0.0006094946,0.0003907445,0.002065504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003564271,"about_ca_system_score_gemma":0.0004226239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009303449,"about_ca_topic_score_gemma":0.02239165,"domain_scores_codex":[0.9996858,0.00003144535,0.00001911962,0.0001050244,0.00007115769,0.0000875987],"domain_scores_gemma":[0.9996364,0.0000776991,0.00003755968,0.00004434345,0.0001589144,0.00004498586],"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":[0.002127332,0.0004205357,0.01563102,0.001640237,0.0001975693,0.002433845,0.001217929,0.007102579,0.4115728,0.0007076107,0.02271893,0.5342297],"study_design_scores_gemma":[0.0001174974,0.0006166151,0.2204444,0.0006033163,0.0003632013,0.003239853,0.003636257,0.3702471,0.3395777,0.001221419,0.0597249,0.0002077584],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8348453,0.002109418,0.1286309,0.0004303511,0.0003744417,0.0005852975,0.00987394,0.01266346,0.01048684],"genre_scores_gemma":[0.7497276,0.001069722,0.2202933,0.0002232383,0.00009323607,0.0002755783,0.01910735,0.001175063,0.00803485],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009303449,"threshold_uncertainty_score":0.0184986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00919322285760569,"score_gpt":0.2040678147204739,"score_spread":0.1948745918628682,"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."}}