{"id":"W4402473501","doi":"10.1109/access.2024.3459629","title":"Enhancing Object Detection in Dense Images: Adjustable Non-Maximum Suppression for Single-Class Detection","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Seoul National University of Science and Technology","keywords":"Object detection; Computer science; Class (philosophy); Artificial intelligence; Computer vision; Object-class detection; Pattern recognition (psychology); Face detection","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":[0.0004957917,0.0002511273,0.000279899,0.0005619979,0.0001422453,0.0004834969,0.0001472667,0.0003309287,0.00002201648],"category_scores_gemma":[0.00009489384,0.000245207,0.0001355072,0.0008063668,0.00001303268,0.001081557,0.00002626579,0.000371699,0.00004638995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000453689,"about_ca_system_score_gemma":0.00003060263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003493356,"about_ca_topic_score_gemma":0.0008599085,"domain_scores_codex":[0.9984216,0.00005261971,0.0004895283,0.000397179,0.0002152595,0.0004238139],"domain_scores_gemma":[0.9993305,0.0002326559,0.00005151713,0.0002320935,0.00008033668,0.00007295633],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007301944,0.00001424701,0.00001025983,0.000397062,0.0000193889,0.00001533568,0.0001507719,0.01065414,0.9081863,4.106671e-7,0.0003838109,0.08009526],"study_design_scores_gemma":[0.0004853928,0.0001281572,0.00006979272,0.0004506395,0.00002510493,0.00003578302,0.0001102092,0.07858271,0.9163097,0.0001154945,0.003419741,0.0002673401],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6154832,0.0003165296,0.3716285,0.000006444774,0.01022032,0.0007666234,0.00001350206,0.0006568397,0.0009081186],"genre_scores_gemma":[0.9984102,0.00002028043,0.00005494969,0.000009441792,0.00100908,0.0002698371,0.000004430674,0.00008859108,0.0001332353],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.382927,"threshold_uncertainty_score":0.9999253,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02379445296394214,"score_gpt":0.2747826563352934,"score_spread":0.2509882033713513,"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."}}