{"id":"W4402963229","doi":"10.1145/3664647.3680815","title":"Text-Region Matching for Multi-Label Image Recognition with Missing Labels","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"RIKEN; Natural Science Foundation of Anhui Province; National Natural Science Foundation of China","keywords":"Computer science; Bridging (networking); Pascal (unit); Artificial intelligence; Matching (statistics); Semantics (computer science); Benchmark (surveying); Class (philosophy); Margin (machine learning); Pattern recognition (psychology); Image (mathematics); Visualization; Semantic gap; Natural language processing; Machine learning; Image retrieval; Mathematics","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":[0.001999699,0.001608556,0.00167657,0.002033539,0.0008156656,0.001439148,0.00457093,0.002531866,0.007004326],"category_scores_gemma":[0.005637338,0.0005902492,0.001857125,0.001828146,0.001226241,0.003218587,0.002723663,0.002336043,0.00504892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00155009,"about_ca_system_score_gemma":0.001379667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004163029,"about_ca_topic_score_gemma":0.006217479,"domain_scores_codex":[0.9979818,0.0003413743,0.0000898656,0.0009781638,0.0003993784,0.0002094367],"domain_scores_gemma":[0.9979529,0.0005555233,0.0002025154,0.0007752894,0.0004056336,0.0001081053],"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":[0.0008883115,0.0003838068,0.001292433,0.0004845911,0.0001208465,0.0003126691,0.0002697186,0.05376077,0.06558403,0.008495124,0.02302991,0.8453778],"study_design_scores_gemma":[0.00006393231,0.0001568551,0.0007327238,0.00003998932,0.00005369213,0.0002693448,0.0001318465,0.9136119,0.05192203,0.02374622,0.009229021,0.0000424783],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01701223,0.0007820742,0.963499,0.0002481418,0.0001478277,0.000185894,0.0006550626,0.01528331,0.002186501],"genre_scores_gemma":[0.225242,0.0003824337,0.7589232,0.0007967235,0.000169106,0.0004609833,0.004646002,0.00180049,0.007579069],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007004326,"threshold_uncertainty_score":0.02343178,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07659082094066458,"score_gpt":0.3466163301374486,"score_spread":0.270025509196784,"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."}}