{"id":"W2948630381","doi":"10.5194/isprs-archives-xlii-2-w13-835-2019","title":"USING EDGECONV TO IMPROVE 3D OBJECT DETECTION FROM RGB-D DATA","year":2019,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Minimum bounding box; Artificial intelligence; Bounding overwatch; Point cloud; RGB color model; Computer vision; Computer science; Benchmark (surveying); Object (grammar); Object detection; Point (geometry); 3d model; Deep learning; Pattern recognition (psychology); Mathematics; Image (mathematics); Geography; Geometry; Cartography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006570197,0.001593842,0.001217825,0.002423152,0.0004094171,0.001155225,0.002114355,0.001134467,0.002009576],"category_scores_gemma":[0.001640031,0.0006542522,0.0009978504,0.001578614,0.0004689441,0.001405974,0.00197949,0.001104546,0.001739371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008642832,"about_ca_system_score_gemma":0.0009382336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0151247,"about_ca_topic_score_gemma":0.02117518,"domain_scores_codex":[0.999144,0.00009416966,0.00003462343,0.0002697356,0.0003589945,0.00009847272],"domain_scores_gemma":[0.9991859,0.0001837977,0.00007302561,0.0002037925,0.0003087725,0.00004474631],"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":[0.0002470278,0.0002035118,0.005955926,0.0002182035,0.0002046956,0.0001847642,0.0001127428,0.1126432,0.03753582,0.003969034,0.011907,0.826818],"study_design_scores_gemma":[0.000005373044,0.00001755864,0.0009839612,0.00001859392,0.00001178498,0.00006136002,0.00001225339,0.9822657,0.01304022,0.001285806,0.002283355,0.00001399042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02501591,0.0004833565,0.9659999,0.00008894565,0.00005859827,0.00007133956,0.0006322663,0.006652777,0.0009968255],"genre_scores_gemma":[0.2971727,0.0005531785,0.6923146,0.0004611784,0.00004271107,0.0001976904,0.004401827,0.0008987056,0.003957519],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0151247,"threshold_uncertainty_score":0.03007334,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02832829102890773,"score_gpt":0.2800696841264556,"score_spread":0.2517413930975478,"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."}}