{"id":"W4387415240","doi":"10.1109/tgrs.2023.3322579","title":"MCTNet: Multiscale Cross-Attention-Based Transformer Network for Semantic Segmentation of Large-Scale Point Cloud","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Data mining; Encoder; Transformer; Segmentation; Feature extraction; Security token; Pattern recognition (psychology); Computer network","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003048279,0.0001239848,0.0001689866,0.0001695609,0.0003616428,0.00004048701,0.00004598597,0.00006681969,0.000004131157],"category_scores_gemma":[0.000002163668,0.0001181894,0.0001416189,0.0005571146,0.00007640816,0.0001039141,3.432312e-7,0.00009551017,0.000005640207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002067087,"about_ca_system_score_gemma":0.00001432824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007583731,"about_ca_topic_score_gemma":0.0002019989,"domain_scores_codex":[0.9990385,0.00001534644,0.0002530928,0.00021906,0.0001646929,0.0003093272],"domain_scores_gemma":[0.9996591,0.00007573807,0.0000305552,0.0001195213,0.00005518667,0.00005986265],"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":[0.00001161241,0.00001254561,0.000008682833,0.00008888921,0.00001928165,9.197096e-7,0.0003298655,0.8854846,0.02078183,3.641212e-7,0.00001963786,0.09324173],"study_design_scores_gemma":[0.0004275318,0.00003494885,0.0002234934,0.0001209047,0.00005824265,0.000002411672,0.000239098,0.9707067,0.0279675,0.0000698658,0.00001764183,0.0001316765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3238757,0.00001632112,0.6754107,0.00006913602,0.0003623396,0.0001118727,0.00002769216,0.0001133744,0.0000128142],"genre_scores_gemma":[0.965943,0.00007551777,0.03365569,0.00003695483,0.00004797179,6.162321e-7,0.00001091529,0.00002015397,0.0002091276],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6420673,"threshold_uncertainty_score":0.4819624,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01293129356734765,"score_gpt":0.2634567325341741,"score_spread":0.2505254389668265,"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."}}