{"id":"W3198835173","doi":"10.1109/lra.2021.3136867","title":"Keeping an Eye on Things: Deep Learned Features for Long-Term Visual Localization","year":2021,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Pipeline (software); Generalizability theory; Computer vision; Robot; Estimator; Ground truth; Feature (linguistics); Term (time); Artificial neural network; Path (computing); Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003406509,0.001024629,0.0005703513,0.0004660784,0.0003611436,0.000666151,0.00139698,0.0008205625,0.001556795],"category_scores_gemma":[0.001865221,0.0003408845,0.0004275944,0.0007031527,0.0005130243,0.001504973,0.001183054,0.001425253,0.0009906056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007195491,"about_ca_system_score_gemma":0.0006447653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01070524,"about_ca_topic_score_gemma":0.01169762,"domain_scores_codex":[0.9997653,0.00002603908,0.000007725545,0.0001041324,0.00004488782,0.00005177319],"domain_scores_gemma":[0.9995191,0.0001131227,0.00007421838,0.0001220719,0.0001355034,0.00003603618],"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":[0.000333516,0.0002309403,0.005258379,0.0001006836,0.0001074628,0.0001890093,0.0001648796,0.3905206,0.02079133,0.00408005,0.01277356,0.5654496],"study_design_scores_gemma":[0.00001267337,0.0000762269,0.001183191,0.00001590281,0.00001206322,0.00004531697,0.00003580221,0.9862277,0.005134212,0.005674111,0.00157004,0.00001278209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08049919,0.0008385384,0.9097134,0.0005058828,0.0001445769,0.00003765814,0.0007606225,0.00558395,0.001916238],"genre_scores_gemma":[0.8908491,0.0002362921,0.102527,0.0002938878,0.00007029279,0.0000590062,0.002183179,0.0002404331,0.003540888],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01070524,"threshold_uncertainty_score":0.02128583,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01296954293326856,"score_gpt":0.259535263609319,"score_spread":0.2465657206760505,"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."}}