{"id":"W4409363673","doi":"10.1609/aaai.v39i18.34151","title":"OmniCount: Multi-label Object Counting with Semantic-Geometric Priors","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Prior probability; Object (grammar); Computer science; Artificial intelligence; Mathematics; Pattern recognition (psychology); Bayesian probability","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003315787,0.005321231,0.002770555,0.005969597,0.002177273,0.005463053,0.009993491,0.004551522,0.008236581],"category_scores_gemma":[0.01368552,0.001633051,0.002804771,0.005458224,0.001763249,0.006451815,0.006620713,0.004364329,0.007696816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004034068,"about_ca_system_score_gemma":0.00348407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0434686,"about_ca_topic_score_gemma":0.090151,"domain_scores_codex":[0.9950612,0.0006328169,0.0002741516,0.001860966,0.00166135,0.0005094608],"domain_scores_gemma":[0.9936402,0.001948538,0.0004246142,0.002464938,0.001158027,0.0003636574],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001318342,0.0007444996,0.01274948,0.002711465,0.0005404026,0.0004103217,0.0004723003,0.0599445,0.01705297,0.01633577,0.4124086,0.4753113],"study_design_scores_gemma":[0.0003435123,0.0002962059,0.005606516,0.0003197761,0.0001260288,0.0008675206,0.0004015242,0.7913219,0.02595071,0.02760039,0.1469981,0.0001678762],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05918763,0.005424188,0.5033812,0.001346792,0.001043222,0.00157445,0.07619249,0.3290085,0.02284144],"genre_scores_gemma":[0.1186938,0.0008039332,0.6709448,0.001135545,0.0002047918,0.0009197733,0.1881016,0.01123695,0.007958889],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0434686,"threshold_uncertainty_score":0.08643115,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06264939534395512,"score_gpt":0.296851819773628,"score_spread":0.2342024244296728,"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."}}