{"id":"W4407097658","doi":"10.1109/jsen.2025.3534319","title":"ELMF-Net: Semantic Segmentation of Large-Scale Point Clouds via Efficient Local Feature Learner and Multiscale Fusion","year":2025,"lang":"en","type":"article","venue":"IEEE Sensors Journal","topic":"Image Processing and 3D Reconstruction","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Scale (ratio); Point cloud; Segmentation; Computer science; Feature (linguistics); Artificial intelligence; Fusion; Point (geometry); Pattern recognition (psychology); Net (polyhedron); Computer vision; Mathematics; Geography; Cartography","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004183286,0.0001279444,0.0001820711,0.0001961491,0.0003173738,0.0001385715,0.0001650722,0.0000967905,0.000007825871],"category_scores_gemma":[0.00001438416,0.000105536,0.00007095219,0.0002998104,0.0001042106,0.0001984218,0.00005795485,0.0003578764,0.000005234055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004669181,"about_ca_system_score_gemma":0.00007552691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008520251,"about_ca_topic_score_gemma":0.000006815211,"domain_scores_codex":[0.9988745,0.0001194626,0.0002770712,0.0002389618,0.0002554605,0.0002345359],"domain_scores_gemma":[0.9993731,0.00003801249,0.000189655,0.0001519845,0.0001674286,0.00007983424],"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":[0.0001268916,0.0003875234,0.003577425,0.0003010694,0.00009635345,0.000075005,0.006737046,0.05474442,0.2647134,0.0001569026,0.003878665,0.6652053],"study_design_scores_gemma":[0.001215601,0.00008170139,0.003148642,0.0002654652,0.00003286813,0.001225505,0.0006862976,0.8662387,0.1261787,0.0005319202,0.0002262152,0.0001684011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4390556,0.0002355394,0.5591057,0.0005323702,0.000873358,0.00005097855,8.524325e-7,0.00002272624,0.0001228525],"genre_scores_gemma":[0.9663271,0.0000488853,0.03264481,0.000101008,0.00009615956,8.307847e-7,7.633849e-7,0.000006744334,0.000773681],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8114942,"threshold_uncertainty_score":0.4303633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004435033679263574,"score_gpt":0.2404852759124987,"score_spread":0.2360502422332352,"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."}}