{"id":"W4416250486","doi":"10.1109/ijcnn64981.2025.11229091","title":"Learning a Discriminative Grassmannian Neural Network for Visual Classification","year":2025,"lang":"","type":"article","venue":"","topic":"Face recognition and analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Research and Development; Fundamental Research Funds for the Central Universities; Ministry of Education; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Grassmannian; Discriminative model; Pattern recognition (psychology); Metric (unit); Subspace topology; Artificial neural network; Matching (statistics); Similarity (geometry); Ambiguity","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006039585,0.0002787192,0.0003605401,0.000293705,0.0008937203,0.000684726,0.0005055167,0.0001346983,0.0001151329],"category_scores_gemma":[0.0002256047,0.0002643471,0.0003853221,0.001767598,0.0001192249,0.0005255595,0.0002097064,0.0003157818,0.00006546823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009414182,"about_ca_system_score_gemma":0.0001517613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003122345,"about_ca_topic_score_gemma":0.00007960969,"domain_scores_codex":[0.9974896,0.0003052104,0.000586312,0.0007929832,0.0002380581,0.0005878094],"domain_scores_gemma":[0.9985454,0.0003863844,0.0002478938,0.0002658974,0.0004206387,0.0001337558],"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":[0.00003457928,0.0002092259,0.001956063,0.00008929201,0.0002110376,0.000001604677,0.0008895455,0.006197422,0.0002018778,0.08759328,0.00599371,0.8966224],"study_design_scores_gemma":[0.0005085916,0.0002451908,0.005938532,0.0001051882,0.0001745792,8.075833e-7,0.001522885,0.9807985,0.0002028942,0.003655638,0.006561009,0.00028612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005111273,0.0001754614,0.9709969,0.01201867,0.0008653193,0.0004717265,0.000003278185,0.0001586353,0.01019879],"genre_scores_gemma":[0.9543761,0.00007902264,0.01237916,0.001096996,0.0001860608,0.0001010813,0.00004158449,0.00001158568,0.03172844],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9746011,"threshold_uncertainty_score":0.9999809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03544685457005556,"score_gpt":0.325693014416871,"score_spread":0.2902461598468155,"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."}}