{"id":"W4411055221","doi":"10.1109/access.2025.3576639","title":"Hierarchical Multi-Scale Patch Attention and Global Feature-Adaptive Fusion for Robust Occluded Face Recognition","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Face recognition and analysis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; University of Windsor","funders":"","keywords":"Computer science; Facial recognition system; Artificial intelligence; Face (sociological concept); Pattern recognition (psychology); Scale (ratio); Feature (linguistics); Fusion; Feature extraction; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007770786,0.0009643547,0.001317711,0.0009421432,0.0003040397,0.0005434849,0.001689431,0.0006865947,0.002311828],"category_scores_gemma":[0.001222795,0.0003367059,0.001020906,0.0008126512,0.0005817168,0.001171828,0.00151349,0.0008945282,0.0007508103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006100755,"about_ca_system_score_gemma":0.0005692401,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004358277,"about_ca_topic_score_gemma":0.005250115,"domain_scores_codex":[0.999488,0.00006782986,0.00001782064,0.0001851022,0.0001434364,0.00009773156],"domain_scores_gemma":[0.9996562,0.00009453908,0.00003666099,0.0000896573,0.00009394079,0.00002894487],"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":[0.0004053762,0.0002579514,0.001606493,0.0001142168,0.0001679101,0.0001276015,0.0001414437,0.1343321,0.08169719,0.003775133,0.005273997,0.7721006],"study_design_scores_gemma":[0.000010216,0.00009161045,0.0009886727,0.000005423835,0.00004516973,0.00007513812,0.00001841149,0.9834013,0.01209598,0.002284021,0.0009711409,0.00001282811],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03273527,0.0006991517,0.9631355,0.0001045526,0.00006323182,0.00005086531,0.00007005041,0.001951101,0.001190188],"genre_scores_gemma":[0.7694598,0.0005083105,0.2243287,0.0003764123,0.0001714801,0.0001185988,0.0004812639,0.0003311344,0.004224462],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004358277,"threshold_uncertainty_score":0.00866586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05106652928747446,"score_gpt":0.3206489229432232,"score_spread":0.2695823936557488,"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."}}