{"id":"W3093367424","doi":"10.48550/arxiv.2010.06264","title":"A Scale and Rotational Invariant Key-point Detector based on Sparse Coding","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Scale-invariant feature transform; Detector; Artificial intelligence; Scale invariance; Computer vision; Pixel; Computer science; Invariant (physics); Robustness (evolution); Affine transformation; Coding (social sciences); Algorithm; Mathematics; Pattern recognition (psychology); Feature extraction; Geometry","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":[0.0008794944,0.0007005976,0.001535442,0.001667882,0.0003450791,0.0007060267,0.001323068,0.001051452,0.001315783],"category_scores_gemma":[0.002516735,0.000486372,0.0007776654,0.001831997,0.0005962629,0.001462514,0.001193868,0.001359927,0.001532686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000519885,"about_ca_system_score_gemma":0.001157098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001736891,"about_ca_topic_score_gemma":0.002142021,"domain_scores_codex":[0.9990507,0.0001170877,0.00004540478,0.000196852,0.0005128382,0.00007715383],"domain_scores_gemma":[0.9988869,0.0002338505,0.0001024848,0.0002027569,0.0005074773,0.00006647271],"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":[0.0002570012,0.0001542407,0.001263805,0.0002237674,0.00009742097,0.000169164,0.00005506065,0.04091602,0.1320718,0.01231071,0.006467002,0.8060141],"study_design_scores_gemma":[0.00003813261,0.0002070489,0.001076158,0.00001489582,0.00004324998,0.0005990649,0.00002019719,0.9396817,0.0488342,0.003609465,0.005818823,0.00005716506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00415283,0.0001572085,0.9946838,0.00006259395,0.00006338864,0.00005489698,0.00006343067,0.0003738787,0.0003879897],"genre_scores_gemma":[0.1210793,0.0004230496,0.8748087,0.00019582,0.00008842717,0.0001611487,0.0006781867,0.00007813753,0.002487239],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001736891,"threshold_uncertainty_score":0.004651248,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07622076492116911,"score_gpt":0.2092766162797709,"score_spread":0.1330558513586018,"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."}}