{"id":"W4410773142","doi":"10.1016/j.neucom.2025.130504","title":"Synergy-driven multi-modal prompting for weakly supervised semantic segmentation","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"Key Technology Research and Development Program of Shandong; National Natural Science Foundation of China","keywords":"Computer science; Segmentation; Modal; Artificial intelligence; Natural language processing; Pattern recognition (psychology); Computer vision","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":[0.0002586904,0.0001892365,0.0001967885,0.0001910215,0.0005140365,0.0002684255,0.0008164496,0.00005867663,0.000001173805],"category_scores_gemma":[0.0001626363,0.0002041948,0.00009626413,0.0005364,0.00002529328,0.0001970027,0.0003772021,0.0002292091,0.00001401577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005486975,"about_ca_system_score_gemma":0.00007118936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009658992,"about_ca_topic_score_gemma":0.000009089761,"domain_scores_codex":[0.9983209,0.0001008068,0.0003698145,0.0006601244,0.0001701893,0.0003781861],"domain_scores_gemma":[0.9987821,0.0004411445,0.0001452299,0.000454374,0.0001140984,0.00006305847],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001565789,0.0003833788,0.0248128,0.0004445277,0.00007647498,0.0000142256,0.002079566,0.1930352,0.2023714,0.05608752,0.0002735729,0.5204056],"study_design_scores_gemma":[0.0006715744,0.00003206998,0.03286013,0.00006163677,0.00001124623,0.000003868568,0.00002846509,0.9632506,0.002190195,0.0004215548,0.0003049351,0.000163677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2298561,0.00001014027,0.7671751,0.0012462,0.000239375,0.0007232656,0.000001202875,0.0004916536,0.0002570082],"genre_scores_gemma":[0.6280618,4.002543e-7,0.3712995,0.0003803197,0.00005603183,0.00009686552,0.000009554295,0.00001356037,0.00008199739],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7702154,"threshold_uncertainty_score":0.8326823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01945021987538133,"score_gpt":0.3093893573511156,"score_spread":0.2899391374757343,"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."}}