{"id":"W3005630416","doi":"10.1049/iet-cvi.2019.0622","title":"SRP‐AKAZE: an improved accelerated KAZE algorithm based on sparse random projection","year":2020,"lang":"en","type":"article","venue":"IET Computer Vision","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China","keywords":"Scale-invariant feature transform; Robustness (evolution); Random projection; Artificial intelligence; Pattern recognition (psychology); Algorithm; Computer science; Computational complexity theory; Benchmark (surveying); Feature matching; Feature (linguistics); Stability (learning theory); Feature extraction; Mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002947214,0.0003237865,0.0003424494,0.0001551096,0.0001930453,0.0004485417,0.0008844924,0.0001354277,0.00001643054],"category_scores_gemma":[0.00003494007,0.0002795156,0.0001258059,0.0008903166,0.00003725665,0.001524838,0.0002687702,0.0003506174,0.00005345243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006788246,"about_ca_system_score_gemma":0.00008476249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001116685,"about_ca_topic_score_gemma":6.165685e-7,"domain_scores_codex":[0.9976849,0.0001998588,0.0003844159,0.0009431345,0.0004130707,0.0003745991],"domain_scores_gemma":[0.9985635,0.00009796711,0.0001672489,0.0006893547,0.0002264795,0.000255412],"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":[0.0002775006,0.0002264839,0.00001104009,0.00001774566,0.000008663224,0.00005110875,0.0001938231,0.0006387883,0.009219819,0.00004811709,0.003466575,0.9858403],"study_design_scores_gemma":[0.001961609,0.0032786,0.0002321903,0.00004983567,0.000005550668,0.000007609684,0.000002710017,0.9302099,0.05555113,0.0002796291,0.008091022,0.0003302318],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001373124,0.00002486945,0.9945333,0.001275852,0.0004425252,0.0007036838,0.000005512972,0.001503169,0.0001379543],"genre_scores_gemma":[0.2012096,0.00002265015,0.7916954,0.006297119,0.0006364005,0.00003028812,0.000039688,0.00004016784,0.00002877283],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9855101,"threshold_uncertainty_score":0.9999657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03240530535998247,"score_gpt":0.3076611477076121,"score_spread":0.2752558423476296,"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."}}