{"id":"W3109233421","doi":"10.1109/lgrs.2020.3037509","title":"Adaptive Pyramid Context Fusion for Point Cloud Perception","year":2020,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Softmax function; Pyramid (geometry); Point cloud; Artificial intelligence; Robustness (evolution); Margin (machine learning); Cloud computing; Segmentation; Context (archaeology); Feature (linguistics); Machine learning; Pattern recognition (psychology); Deep learning","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":[0.0001206054,0.0001219546,0.0001495545,0.00005277356,0.0001722958,0.00005641679,0.00005995768,0.00004443598,0.000001602961],"category_scores_gemma":[0.00001889583,0.0001098359,0.00007261794,0.000155475,0.00009602962,0.00009545735,0.00001163986,0.000105431,0.00001036634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002729648,"about_ca_system_score_gemma":0.00000639062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001049213,"about_ca_topic_score_gemma":0.00001263639,"domain_scores_codex":[0.9992341,0.00001323666,0.0001388971,0.0002561965,0.0001255514,0.0002319688],"domain_scores_gemma":[0.9997321,0.00002739578,0.00002389791,0.00008633676,0.0000298951,0.0001003853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001791104,0.000002077181,0.000002873004,0.00003598675,0.00001614087,0.000008189372,0.002973373,0.03714957,0.531418,0.000001943527,0.002253293,0.4261207],"study_design_scores_gemma":[0.0001579702,0.00003520056,0.00003356379,0.00004505646,0.00002292091,0.000007200295,0.0006312584,0.996719,0.001786718,0.00003875843,0.0003663471,0.0001559913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4424089,0.00002990695,0.553933,0.003210816,0.000238995,0.000056505,0.000002461467,0.0000951917,0.00002421538],"genre_scores_gemma":[0.9777701,0.00005076238,0.01684735,0.004979096,0.0003138341,6.412775e-8,0.000002745122,0.0000151809,0.0000208677],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9595695,"threshold_uncertainty_score":0.4478979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02103665431646614,"score_gpt":0.2118835178459033,"score_spread":0.1908468635294372,"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."}}