{"id":"W4406291830","doi":"10.1016/j.eswa.2025.126432","title":"MTCloud: Multi-type convolutional linkage network for point cloud instance segmentation","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Xiamen Southern Oceanographic Center; China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Linkage (software); Point cloud; Segmentation; Type (biology); Artificial intelligence; Convolutional neural network; Cloud computing; Data mining; Pattern recognition (psychology); Operating system","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001032594,0.0001348719,0.0001779978,0.00006213416,0.0001887684,0.00004255319,0.0001166625,0.0000694036,0.000004929175],"category_scores_gemma":[0.00000569663,0.0001245242,0.00004798069,0.000410698,0.0000233388,0.00005516061,0.000009197252,0.0000711363,0.00002163375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001279308,"about_ca_system_score_gemma":0.0000334339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003556642,"about_ca_topic_score_gemma":0.00002729075,"domain_scores_codex":[0.9992062,0.00001473018,0.0002735727,0.0002134471,0.00009824108,0.0001937716],"domain_scores_gemma":[0.9994346,0.00006359904,0.00004539957,0.000260513,0.0001472724,0.00004856137],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001388243,0.00005769053,0.000356928,0.0001372713,0.0002005671,2.221616e-7,0.000245838,0.9694211,0.002862116,0.00838736,0.01737154,0.0009454982],"study_design_scores_gemma":[0.0005615714,0.0000185706,0.00006135606,0.0001342966,0.00004005995,0.000001458815,0.0003386018,0.9416297,0.0004183101,0.0001362263,0.05645187,0.0002079604],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001141738,0.004380153,0.9921514,0.0001208384,0.0003407358,0.0008409335,0.00003031177,0.0003159308,0.0006780013],"genre_scores_gemma":[0.9547995,0.0001062522,0.03933183,0.0001245904,0.0005635131,0.003333958,0.0002361446,0.00003241466,0.001471783],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9536577,"threshold_uncertainty_score":0.5077951,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01406384592608546,"score_gpt":0.261084336711436,"score_spread":0.2470204907853505,"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."}}