{"id":"W4304182941","doi":"10.1016/j.ins.2022.10.039","title":"Mesh Oversegmentation with Segmentation-Aware Loss","year":2022,"lang":"en","type":"article","venue":"Information Sciences","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Computer science; Polygon mesh; Artificial intelligence; Segmentation; Leverage (statistics); Pattern recognition (psychology); Artificial neural network; Point cloud; End-to-end principle; Cluster analysis; Feature extraction; Feature (linguistics); Deep learning; Face (sociological concept)","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":[0.0001787681,0.00004691085,0.00004301976,0.0001412635,0.0003319304,0.00009060551,0.00009862814,0.000006386556,0.0002982867],"category_scores_gemma":[0.0000022957,0.00004016018,0.00001597091,0.0004698298,0.00003020298,0.001099778,0.00001460337,0.00004399223,0.00003709099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000522636,"about_ca_system_score_gemma":0.00002307832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001807894,"about_ca_topic_score_gemma":0.00000469786,"domain_scores_codex":[0.9993504,0.00000875201,0.0001320099,0.00004487556,0.0003766674,0.00008726483],"domain_scores_gemma":[0.9998592,0.00001191867,0.00003622364,0.00004712586,0.0000252188,0.00002027658],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001376555,0.000002048917,0.0006722875,0.000005655676,0.00000697976,2.336735e-7,0.001463372,0.9919627,0.0000299081,0.0002269978,0.000578402,0.005050019],"study_design_scores_gemma":[0.0001790175,0.00004230016,0.0002216972,0.000003193745,0.000008526776,0.000006258196,0.01298841,0.9837742,0.0005707408,0.00006400169,0.002037591,0.0001039911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5380167,0.00003419186,0.4347466,0.0002848906,0.0003181348,0.0001732518,0.00005083928,0.0004013272,0.02597404],"genre_scores_gemma":[0.9988354,0.000006545882,0.0008689271,0.0001682682,0.000008266596,0.00002840999,0.00004335249,0.000001941419,0.00003889254],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4608186,"threshold_uncertainty_score":0.326603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01032155558908881,"score_gpt":0.2232816157349394,"score_spread":0.2129600601458506,"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."}}