{"id":"W4415594217","doi":"10.1109/jstars.2025.3625259","title":"SAT-Former: An Efficient 3-D Transformer With Semantic Aggregated Point Tokenizer for Point Cloud Semantic Segmentation in Urban Scenes","year":2025,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Point cloud; Security token; Segmentation; Inference; Transformer; Semantic grid; Semantics (computer science); Cloud computing; Visualization","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004083042,0.001099467,0.001069677,0.00154035,0.0007629345,0.001612232,0.002825859,0.0008682205,0.01372057],"category_scores_gemma":[0.001296159,0.0006662136,0.00150804,0.001943005,0.0007898938,0.002742535,0.002634631,0.001086704,0.005710949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001442527,"about_ca_system_score_gemma":0.001649232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008436644,"about_ca_topic_score_gemma":0.01269984,"domain_scores_codex":[0.9995622,0.00004346695,0.00003202931,0.0001462743,0.0001500948,0.00006581421],"domain_scores_gemma":[0.9997113,0.00006708186,0.00002190698,0.00009422807,0.00007347348,0.00003185107],"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":[0.001016994,0.0002032542,0.001668293,0.0003180463,0.0001111482,0.0003502618,0.0003502134,0.08947969,0.04195258,0.04717315,0.03358904,0.7837874],"study_design_scores_gemma":[0.00006162315,0.000095518,0.0004289287,0.00001133621,0.00003856075,0.0002099979,0.0001112312,0.9304997,0.03455821,0.01472701,0.01922038,0.00003744465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006502648,0.00007343614,0.9752899,0.00005820312,0.00005949184,0.0001142646,0.0005464401,0.01544931,0.001906326],"genre_scores_gemma":[0.1735504,0.0001791686,0.8132042,0.0001775166,0.00004615543,0.0002481298,0.004050464,0.00208884,0.006455119],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01372057,"threshold_uncertainty_score":0.04589987,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0126226257180862,"score_gpt":0.2357612809915982,"score_spread":0.223138655273512,"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."}}