{"id":"W4405785492","doi":"10.1109/iros58592.2024.10801453","title":"Learning from Spatio-temporal Correlation for Semi-Supervised LiDAR Semantic Segmentation","year":2024,"lang":"en","type":"article","venue":"","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Samsung; National Research Foundation of Korea","keywords":"Lidar; Computer science; Segmentation; Artificial intelligence; Correlation; Image segmentation; Remote sensing; Geology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001026928,0.001607045,0.001617236,0.001774808,0.0008125063,0.001332953,0.002651625,0.001624891,0.001996587],"category_scores_gemma":[0.0030289,0.0008230566,0.00132341,0.002099775,0.0009434317,0.002223345,0.001839923,0.001895808,0.001869871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007483631,"about_ca_system_score_gemma":0.002141115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006287315,"about_ca_topic_score_gemma":0.01838859,"domain_scores_codex":[0.9988124,0.0001774221,0.00005181285,0.0005444802,0.0002422109,0.0001717575],"domain_scores_gemma":[0.9985523,0.0004698529,0.000197978,0.0003141786,0.0003711685,0.00009455778],"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":[0.0005728837,0.0004991817,0.006620726,0.0005147309,0.0002552067,0.0003048202,0.0004383254,0.2878016,0.03987947,0.004823463,0.01468598,0.6436037],"study_design_scores_gemma":[0.00001582564,0.00004268393,0.0009551015,0.00002376571,0.00002219746,0.000113036,0.00007051882,0.9854673,0.006526558,0.004689362,0.002053852,0.00001977211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06350309,0.0008990096,0.9248934,0.0002658263,0.0001055421,0.0001405573,0.0007456282,0.006431448,0.003015341],"genre_scores_gemma":[0.5200682,0.0005101912,0.4665366,0.0005600486,0.0002186809,0.0003313961,0.006343922,0.001043034,0.004387983],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006287315,"threshold_uncertainty_score":0.01250142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01407527275674862,"score_gpt":0.2442163585915164,"score_spread":0.2301410858347678,"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."}}