{"id":"W2963830382","doi":"10.1007/978-3-030-01225-0_4","title":"Local Spectral Graph Convolution for Point Set Feature Learning","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":380,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Pooling; Computer science; Graph; Spectral clustering; Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Point cloud; Cluster analysis; Convolution (computer science); Segmentation; Theoretical computer science; Artificial neural network","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":[0.000453691,0.0006329347,0.0009367244,0.0007664107,0.0002700648,0.0007848499,0.001322913,0.0009690393,0.004596915],"category_scores_gemma":[0.00161923,0.000329341,0.0007431637,0.001601263,0.0006626333,0.001743756,0.001500652,0.001353422,0.002611917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006225689,"about_ca_system_score_gemma":0.0004561463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001884262,"about_ca_topic_score_gemma":0.002480935,"domain_scores_codex":[0.9997018,0.000058896,0.00001335923,0.0000836891,0.0001141392,0.00002805012],"domain_scores_gemma":[0.9994611,0.0001994049,0.00003384169,0.0001600871,0.0001118848,0.00003370163],"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":[0.0001301773,0.00008350492,0.0003764332,0.0002219403,0.00007690736,0.00007830972,0.00006925395,0.124646,0.02074942,0.09235216,0.01313346,0.7480824],"study_design_scores_gemma":[0.000003053674,0.00002293821,0.0001761427,0.000007685162,0.00001088037,0.00007833873,0.000009618223,0.9344276,0.003696626,0.05784961,0.003707687,0.000009750551],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003337995,0.0003167089,0.9944747,0.00006900325,0.00003591403,0.000009588951,0.00005129349,0.0006696925,0.00103508],"genre_scores_gemma":[0.2610901,0.001534238,0.7188036,0.0002547723,0.0002123654,0.0001355744,0.001003748,0.0007546496,0.01621105],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004596915,"threshold_uncertainty_score":0.01537824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01196481781771614,"score_gpt":0.2211784362470469,"score_spread":0.2092136184293308,"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."}}