{"id":"W2767696612","doi":"10.1155/2017/8104386","title":"Efficient ConvNet Feature Extraction with Multiple RoI Pooling for Landmark-Based Visual Localization of Autonomous Vehicles","year":2017,"lang":"en","type":"article","venue":"Mobile Information Systems","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Hunan Provincial Innovation Foundation for Postgraduate; Natural Science Foundation of Hunan Province; National Natural Science Foundation of China","keywords":"Computer science; Landmark; Pooling; Artificial intelligence; Discriminative model; Leverage (statistics); Pattern recognition (psychology); Region of interest; Feature extraction; Computer vision; Convolutional neural network","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":[0.0003029743,0.001524683,0.0007923525,0.001166709,0.0002606137,0.0004982995,0.001207125,0.0005497398,0.001621304],"category_scores_gemma":[0.000784675,0.0005150268,0.0007884635,0.0009133984,0.0003414403,0.001233083,0.0009227959,0.0006676122,0.0009906736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005943117,"about_ca_system_score_gemma":0.0009673237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008476118,"about_ca_topic_score_gemma":0.01167639,"domain_scores_codex":[0.9997683,0.00001982663,0.00001122675,0.00007493196,0.00007256306,0.00005310275],"domain_scores_gemma":[0.9998457,0.00002432509,0.00002589237,0.00003493838,0.0000544873,0.00001459312],"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":[0.0002584519,0.0001146366,0.001526856,0.0002008283,0.0001720741,0.000439711,0.0001015421,0.1402642,0.144882,0.003915989,0.01068179,0.6974419],"study_design_scores_gemma":[0.00002073425,0.0001247881,0.001953791,0.00001865217,0.0000632138,0.0002266393,0.0000458942,0.9164773,0.0720398,0.003781388,0.005212225,0.00003565654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04341121,0.0005383002,0.9478079,0.0001263206,0.00007398081,0.0000758746,0.0004074171,0.005901188,0.001657894],"genre_scores_gemma":[0.6022599,0.0005541343,0.3884656,0.0001968043,0.000058788,0.0001717625,0.002688284,0.0005681561,0.005036553],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008476118,"threshold_uncertainty_score":0.01685357,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007158529332298079,"score_gpt":0.2295356083209494,"score_spread":0.2223770789886513,"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."}}