{"id":"W4390873233","doi":"10.1109/iccv51070.2023.00075","title":"MemorySeg: Online LiDAR Semantic Segmentation with a Latent Memory","year":2023,"lang":"en","type":"article","venue":"","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Segmentation; Point cloud; Lidar; Artificial intelligence; Frame (networking); Representation (politics); Visibility; Semantics (computer science); Range (aeronautics); Point (geometry); Computer vision; Pattern recognition (psychology); Remote sensing","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":[0.0003199366,0.000980224,0.001159558,0.0009556339,0.0005445853,0.0009860322,0.002631066,0.0009253791,0.003181892],"category_scores_gemma":[0.001273523,0.000555256,0.0008150953,0.00146184,0.0005874551,0.002607135,0.002247704,0.001184389,0.001458763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007258118,"about_ca_system_score_gemma":0.001449947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01411372,"about_ca_topic_score_gemma":0.02468987,"domain_scores_codex":[0.9996419,0.00003221353,0.00001477622,0.0001329855,0.0001131686,0.00006493636],"domain_scores_gemma":[0.9996581,0.00006901933,0.00005104321,0.000132833,0.00005590667,0.0000331852],"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":[0.000608764,0.0003045365,0.001886024,0.0001708463,0.0001304416,0.0002746878,0.0002749717,0.1787814,0.02234945,0.009738585,0.01456365,0.7709166],"study_design_scores_gemma":[0.00003272037,0.00006636907,0.000398241,0.00001255493,0.00001896019,0.0001000688,0.00006225125,0.9819384,0.007304192,0.006563583,0.003482507,0.00002016733],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02845056,0.0005204998,0.9591154,0.0001795166,0.00007216076,0.00007673383,0.0006432928,0.009553587,0.001388197],"genre_scores_gemma":[0.4412778,0.0004258688,0.5484312,0.0003232997,0.0001041857,0.0002118718,0.003796718,0.0007600818,0.004668901],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01411372,"threshold_uncertainty_score":0.02806312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01502296277193868,"score_gpt":0.219523748402094,"score_spread":0.2045007856301553,"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."}}