{"id":"W3162116812","doi":"10.1016/j.isprsjprs.2021.04.006","title":"Aerial scene understanding in the wild: Multi-scene recognition via prototype-based memory networks","year":2021,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"H2020 European Research Council; Helmholtz Association; Helmholtz Artificial Intelligence Cooperation Unit; Bundesministerium für Bildung und Forschung; European Commission","keywords":"Computer science; Artificial intelligence; Aerial image; Task (project management); Computer vision; Representation (politics); Key (lock); Categorization; Image (mathematics); Pattern recognition (psychology)","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":[0.001191778,0.0001691587,0.0002817982,0.000226799,0.0001923234,0.0003022772,0.000223874,0.000118716,0.000001632002],"category_scores_gemma":[0.0002050418,0.0001259652,0.0001263157,0.0009401632,0.00007865486,0.000517729,0.00006083348,0.0005754338,3.10421e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001167724,"about_ca_system_score_gemma":0.00009709189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007523384,"about_ca_topic_score_gemma":0.00006115718,"domain_scores_codex":[0.9983416,0.0003551091,0.0004645148,0.0002379304,0.000296472,0.0003043527],"domain_scores_gemma":[0.9988905,0.0002518769,0.0003219622,0.0002353804,0.0002096908,0.00009063786],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001194377,0.00005246435,0.00001866853,0.00002511,0.00001600196,0.0007231327,0.0001913243,0.00009029874,0.01099729,0.000006871746,0.00001329978,0.9877461],"study_design_scores_gemma":[0.002812836,0.0005617625,0.0001520874,0.001259314,0.00005595156,0.003204067,0.00071535,0.7257621,0.25465,0.009849233,0.0005271387,0.00045018],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006613249,0.0007856798,0.9914545,0.0004155609,0.0003815509,0.000265678,4.335176e-7,0.00003290693,0.00005042561],"genre_scores_gemma":[0.5692573,0.0002615958,0.4296575,0.000620233,0.0001872196,8.93185e-8,0.000001455314,0.00001070962,0.000003987021],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9872959,"threshold_uncertainty_score":0.5136713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05142899833786894,"score_gpt":0.2941437742978845,"score_spread":0.2427147759600155,"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."}}