{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003457048,0.001174714,0.001012731,0.0008536877,0.0004442546,0.0006964473,0.001914018,0.0008370202,0.002352959],"category_scores_gemma":[0.001117086,0.0004380665,0.0008486005,0.0008686805,0.0005408445,0.001830836,0.001958078,0.001246541,0.0004340368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009966219,"about_ca_system_score_gemma":0.0008047857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01135153,"about_ca_topic_score_gemma":0.01439624,"domain_scores_codex":[0.9997186,0.00002465083,0.000008031304,0.0001032105,0.00008865169,0.00005691304],"domain_scores_gemma":[0.9998212,0.00003602436,0.00002089154,0.00004077504,0.00005715278,0.00002389313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003449732,0.0002159028,0.002807581,0.0001595286,0.000172682,0.0002144904,0.0001371728,0.3926568,0.05403946,0.01415575,0.00726803,0.5278277],"study_design_scores_gemma":[0.00000793277,0.00004499667,0.0005065093,0.000006970361,0.00002102094,0.00004008244,0.00001356381,0.9868574,0.005736608,0.005766879,0.000988574,0.000009339452],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05624877,0.000872567,0.9374886,0.0003153438,0.00009578586,0.0000531753,0.0002791884,0.002576412,0.002070188],"genre_scores_gemma":[0.8225284,0.0005606473,0.1737784,0.0003159135,0.00008730528,0.00007232528,0.0005583382,0.0001250711,0.001973651],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01135153,"threshold_uncertainty_score":0.02257091,"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."}}