{"id":"W2804872164","doi":"10.1016/j.isprsjprs.2018.05.004","title":"Toward better boundary preserved supervoxel segmentation for 3D point clouds","year":2018,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":168,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Segmentation; Initialization; Point cloud; Computer science; Artificial intelligence; Boundary (topology); Image segmentation; Point (geometry); Pattern recognition (psychology); Computer vision; Mathematics; Geometry","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":[0.0004742168,0.0001564392,0.0002842681,0.0002023299,0.0001507075,0.0001258275,0.00007377309,0.00009329474,0.00001050512],"category_scores_gemma":[0.00005121539,0.0001336164,0.0001861815,0.0001862654,0.00007481259,0.0001617114,0.00001823862,0.00020677,0.000001649613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003938867,"about_ca_system_score_gemma":0.00002042864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008826669,"about_ca_topic_score_gemma":0.00003353301,"domain_scores_codex":[0.9989784,0.00003679937,0.0004277659,0.0001243875,0.0001805256,0.0002521744],"domain_scores_gemma":[0.9993716,0.00006825735,0.0001011892,0.0001101521,0.0002301047,0.0001186378],"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":[0.0001038662,0.00001568451,0.00008119622,0.0001752302,0.0003811057,0.00003136242,0.001329854,0.001701208,0.09280728,6.691039e-7,0.0006891457,0.9026834],"study_design_scores_gemma":[0.0008279881,0.0002018659,0.00005188975,0.0001992493,0.0002099023,0.0002217687,0.0004896866,0.9399934,0.0544882,0.0008275041,0.002276283,0.0002121961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.431942,0.0005132034,0.5668859,0.0001282259,0.0003561392,0.00005614052,0.000002630833,0.00002704651,0.00008879862],"genre_scores_gemma":[0.8391667,0.0001337892,0.1597922,0.0001717619,0.0006832565,3.43106e-8,0.000003949408,0.00002827665,0.0000200497],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9382923,"threshold_uncertainty_score":0.544872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0215857660182152,"score_gpt":0.2538991467415287,"score_spread":0.2323133807233135,"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."}}