{"id":"W2772126356","doi":"10.1007/s10846-017-0755-7","title":"Combining Multiple Image Descriptions for Loop Closure Detection","year":2017,"lang":"en","type":"article","venue":"Journal of Intelligent & Robotic Systems","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Weighting; Image (mathematics); Closure (psychology); Artificial intelligence; Pattern recognition (psychology); Loop (graph theory); Computer science; Obstacle; Mathematics; Data mining; Algorithm","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":[0.00092944,0.0001617351,0.0003747805,0.0001831069,0.0005087051,0.0007581663,0.001181482,0.0000839654,0.000001541967],"category_scores_gemma":[0.001082523,0.0001329292,0.0002622662,0.00009841836,0.00006324263,0.001566209,0.0001249843,0.0002348893,0.00001085127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001366116,"about_ca_system_score_gemma":0.00006239187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003248691,"about_ca_topic_score_gemma":0.00000651755,"domain_scores_codex":[0.9984149,0.00006829492,0.0007422484,0.0001980721,0.0003157664,0.0002607573],"domain_scores_gemma":[0.99694,0.0002337568,0.001226383,0.0006259119,0.0008460975,0.000127906],"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":[0.0006769744,0.001575853,0.02170709,0.001421025,0.001242167,0.0005596271,0.003657472,0.05419496,0.3569125,0.02576226,0.01025986,0.5220302],"study_design_scores_gemma":[0.001599932,0.002341143,0.002302981,0.001497971,0.0001341887,0.00155866,0.0006743163,0.4972193,0.4760807,0.006006015,0.009880152,0.0007045821],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003046862,0.0007432052,0.9925215,0.0001717711,0.002942816,0.0003777662,0.000001351311,0.00006443398,0.0001303081],"genre_scores_gemma":[0.9149035,0.0001364149,0.08424014,0.00002691481,0.0003544322,0.00001436602,4.040568e-7,0.00001669302,0.0003071695],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9118566,"threshold_uncertainty_score":0.7311015,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05517083742240822,"score_gpt":0.3237214067685577,"score_spread":0.2685505693461495,"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."}}