{"id":"W2947326555","doi":"10.1109/cvpr.2019.00832","title":"RF-Net: An End-To-End Image Matching Network Based on Receptive Field","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":112,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Pipeline (software); Computer science; Benchmark (surveying); Artificial intelligence; Matching (statistics); Net (polyhedron); Pattern recognition (psychology); Feature extraction; Feature (linguistics); Field (mathematics); Stability (learning theory); Block (permutation group theory); Receptive field; Computer vision; Machine learning; Mathematics","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":[0.0003314265,0.0001805485,0.0001890411,0.00009324274,0.00009439987,0.0001800505,0.0007815764,0.00007059183,0.0006462001],"category_scores_gemma":[0.00004555343,0.0001526031,0.00006599001,0.0004322465,0.00001502686,0.0009450918,0.0002050196,0.0002338243,0.0004347313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000406428,"about_ca_system_score_gemma":0.0000364113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005604612,"about_ca_topic_score_gemma":0.00001047743,"domain_scores_codex":[0.9985553,0.00005359111,0.0001884051,0.0005357428,0.0002810118,0.000385917],"domain_scores_gemma":[0.9985693,0.0003063866,0.00006084519,0.0008477598,0.00007126397,0.0001444485],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002371139,0.0002645623,0.001076168,0.00003673657,0.00002395378,0.00007774415,0.001011828,0.003741927,0.04214055,0.05304888,0.03314532,0.8651952],"study_design_scores_gemma":[0.001033127,0.006329214,0.002679612,0.0003462017,0.00001206745,0.00001338541,0.0001674031,0.09499065,0.7453977,0.07892975,0.06838115,0.001719701],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003448635,0.000009953489,0.9498249,0.001093918,0.0002309395,0.0003180711,0.000001456611,0.0005405865,0.04453153],"genre_scores_gemma":[0.37505,0.000006830468,0.6109788,0.01205641,0.0001514516,0.00001389686,0.000003849084,0.00001837692,0.001720429],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8634755,"threshold_uncertainty_score":0.7075438,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01177187693708818,"score_gpt":0.2865350643737353,"score_spread":0.2747631874366471,"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."}}