{"id":"W4281785683","doi":"10.1016/j.jag.2022.102837","title":"CapViT: Cross-context capsule vision transformers for land cover classification with airborne multispectral LiDAR data","year":2022,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Six Talent Peaks Project in Jiangsu Province; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Lidar; Land cover; Multispectral image; Remote sensing; Computer science; Feature extraction; Feature (linguistics); Ranging; Artificial intelligence; Computer vision; Geography; Engineering; Land use; Telecommunications","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":[0.0005500115,0.0001054065,0.000117034,0.00008864071,0.0002828188,0.0001380263,0.000280692,0.00003724467,0.0002081416],"category_scores_gemma":[0.00001880146,0.00009257557,0.00003559258,0.0001401975,0.0000801383,0.00109944,0.00006756232,0.000164757,0.00001921209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001038314,"about_ca_system_score_gemma":0.00004411866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008041515,"about_ca_topic_score_gemma":0.00007417427,"domain_scores_codex":[0.9986498,0.00001407024,0.0004642193,0.0001601869,0.0005876054,0.0001241213],"domain_scores_gemma":[0.9991839,0.00004314073,0.0004573488,0.000138849,0.0001103485,0.0000664277],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002591905,0.000335637,0.01666594,0.00003780174,0.0002080608,0.000003781676,0.005461757,0.09648825,0.02005795,0.003270318,0.004483171,0.8503954],"study_design_scores_gemma":[0.003849295,0.0003178968,0.4624459,0.00001774693,0.00004271513,0.0001072187,0.0009699228,0.3006432,0.001813776,0.0004351869,0.2290937,0.0002634344],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9535604,0.00001212279,0.04119129,0.00171606,0.000204365,0.0004152896,0.0001352809,0.00002028926,0.002744928],"genre_scores_gemma":[0.9928294,0.00002330291,0.005723604,0.0005771181,0.00007773026,0.000009516148,0.0005987406,0.000009967641,0.0001506038],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.850132,"threshold_uncertainty_score":0.3775122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02382575671268156,"score_gpt":0.2719157527693175,"score_spread":0.248089996056636,"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."}}