{"id":"W2999170936","doi":"10.1007/s11760-020-01636-0","title":"Image splicing detection using mask-RCNN","year":2020,"lang":"en","type":"article","venue":"Signal Image and Video Processing","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Artificial intelligence; Discriminative model; Backbone network; Initialization; Feature (linguistics); Residual neural network; Pattern recognition (psychology); Pyramid (geometry); Convolutional neural network; Set (abstract data type); Feature vector; Computer vision; Network architecture; Mathematics; Telecommunications","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":[0.0001921855,0.0001738212,0.000172169,0.00009212737,0.0002447215,0.001026168,0.0002149543,0.00005291544,0.000005477943],"category_scores_gemma":[0.0001122622,0.0001693056,0.00004450295,0.0005200697,0.00008980403,0.003489213,0.000193221,0.0001846932,0.00002387634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003728994,"about_ca_system_score_gemma":0.00006245545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002210596,"about_ca_topic_score_gemma":0.000002579667,"domain_scores_codex":[0.9987138,0.00003569333,0.0002335232,0.0004723227,0.0002502393,0.0002944539],"domain_scores_gemma":[0.9994142,0.00004131351,0.0001214304,0.0001298327,0.0001108983,0.0001823157],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001114524,0.000007460048,0.00001980056,0.00009269601,0.00000426725,0.00002964553,0.0007349365,0.00001025583,0.5339035,0.00002056919,0.00001101985,0.4651547],"study_design_scores_gemma":[0.0002702263,0.0001240825,0.0001058597,0.0001067606,0.00001741912,0.00009128759,0.0001787857,0.6527023,0.344569,0.001385388,0.0001878396,0.0002610832],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1162457,0.0001602032,0.8816519,0.000370991,0.0001153414,0.0001061081,6.809834e-7,0.0002718089,0.001077349],"genre_scores_gemma":[0.9235547,0.000003005093,0.07558039,0.0005901056,0.0002368697,0.000004283708,6.255427e-7,0.00001864382,0.00001141908],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.807309,"threshold_uncertainty_score":0.989536,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01990819478323003,"score_gpt":0.2486485119037041,"score_spread":0.2287403171204741,"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."}}