{"id":"W3036922662","doi":"10.1109/cvprw50498.2020.00339","title":"Forgery Detection in Hyperspectral Document Images using Graph Orthogonal Nonnegative Matrix Factorization","year":2020,"lang":"en","type":"article","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Hyperspectral imaging; Non-negative matrix factorization; Orthogonality; Computer science; Graph; Matrix decomposition; Artificial intelligence; Pattern recognition (psychology); Cluster analysis; Exploit; Algorithm; Theoretical computer science; Mathematics; Eigenvalues and eigenvectors","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":[0.0007991479,0.001094588,0.0007841756,0.0009001267,0.0003378947,0.0006733387,0.0008524855,0.0008762108,0.0007505092],"category_scores_gemma":[0.001870585,0.0002538116,0.001049361,0.0007394335,0.0006415112,0.001183922,0.0005775361,0.001008693,0.0004493142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003906735,"about_ca_system_score_gemma":0.0006352064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003006929,"about_ca_topic_score_gemma":0.004664731,"domain_scores_codex":[0.999338,0.0001549873,0.00002797157,0.0002003799,0.0002101201,0.0000685177],"domain_scores_gemma":[0.9992898,0.0002417715,0.0001552703,0.0001050377,0.000173246,0.0000349436],"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":[0.0004795229,0.0002599328,0.003297416,0.0003912248,0.0001930461,0.0003728447,0.0002568663,0.249617,0.1105482,0.0118708,0.00714862,0.6155645],"study_design_scores_gemma":[0.000007371463,0.00003338082,0.000723269,0.000007867067,0.00001357605,0.00009656621,0.00002938757,0.9884719,0.007287873,0.00248335,0.0008296753,0.00001582662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02581272,0.0002387321,0.9727432,0.00013949,0.0000419533,0.00004210823,0.00008638835,0.0003419928,0.0005535045],"genre_scores_gemma":[0.3281879,0.0005232343,0.668358,0.0001338275,0.00009012902,0.00009497831,0.0005790364,0.00007883461,0.001954066],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003006929,"threshold_uncertainty_score":0.005978882,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02089614503881847,"score_gpt":0.2464546077608068,"score_spread":0.2255584627219883,"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."}}