{"id":"W4413982673","doi":"10.1016/j.knosys.2025.114401","title":"FDGC: Fuzzy deep clustering with dual-granularity contrastive learning","year":2025,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Graduate Research and Innovation Projects of Jiangsu Province; Natural Science Research of Jiangsu Higher Education Institutions of China; National Natural Science Foundation of China; Qinglan Project of Jiangsu Province of China; Natural Science Foundation of Nantong City","keywords":"Granularity; Dual (grammatical number); Computer science; Artificial intelligence; Cluster analysis; Fuzzy logic; Fuzzy clustering; Linguistics; Philosophy","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":[0.001155439,0.001042104,0.000969043,0.001310509,0.0007310842,0.001036025,0.002987654,0.001767472,0.001675296],"category_scores_gemma":[0.002951567,0.0004785374,0.0008444593,0.0009117081,0.001049147,0.001603462,0.00192845,0.001874596,0.0005971065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001821017,"about_ca_system_score_gemma":0.001484219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0106375,"about_ca_topic_score_gemma":0.01456863,"domain_scores_codex":[0.9994111,0.00008857533,0.00002643326,0.000200258,0.0001870821,0.00008656244],"domain_scores_gemma":[0.9991652,0.0002282209,0.00008545577,0.0001897609,0.0002599476,0.00007157072],"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":[0.00029657,0.000265358,0.003069327,0.0001229999,0.0001490787,0.0001421911,0.0001751802,0.3895056,0.01806693,0.01503324,0.007269744,0.5659038],"study_design_scores_gemma":[0.000009394951,0.00003309395,0.0002064155,0.00000708509,0.00000745698,0.00002935134,0.000009577591,0.9921113,0.002761077,0.004200947,0.0006135381,0.0000107982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02819368,0.0003513778,0.9676346,0.0002322992,0.00005812911,0.0001005668,0.0001388202,0.001621059,0.001669561],"genre_scores_gemma":[0.4760069,0.0002315028,0.5177583,0.0006446054,0.0000711887,0.0002062117,0.0007852958,0.0002462681,0.004049682],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0106375,"threshold_uncertainty_score":0.02115113,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01009090458472542,"score_gpt":0.2414489203628171,"score_spread":0.2313580157780916,"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."}}