{"id":"W4362672512","doi":"10.1016/j.cviu.2023.103690","title":"SCA-Net: Spatial and channel attention-based network for 3D point clouds","year":2023,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Point cloud; Computer science; Pooling; Artificial intelligence; Upsampling; Geometric networks; Channel (broadcasting); Geometric modeling; Key (lock); Geometric data analysis; Data mining; Point (geometry); Mathematics; Complex network; Image (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":[0.0002256595,0.0001409382,0.0001819492,0.0001379954,0.0002360437,0.0001736315,0.00004901618,0.00005164287,0.000007658888],"category_scores_gemma":[0.000004968575,0.0001322507,0.00006950438,0.0001878138,0.00003338185,0.00009097617,0.00004228988,0.00007236793,0.000005898455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004259255,"about_ca_system_score_gemma":0.000005454334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005470965,"about_ca_topic_score_gemma":0.000005413648,"domain_scores_codex":[0.9992563,0.00001493523,0.0001671536,0.0002172882,0.0000923156,0.0002520203],"domain_scores_gemma":[0.9996721,0.0001013259,0.00002243466,0.00009807053,0.00002172157,0.00008439935],"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":[0.0001154684,0.00005474594,0.0009833492,0.0009871067,0.0003570465,0.00004706449,0.0009894725,0.8446159,0.003055147,0.001375148,0.06351103,0.08390857],"study_design_scores_gemma":[0.0005817832,0.00006170341,0.0002027439,0.0001347678,0.00002735974,0.000001808021,0.00008239949,0.9965311,0.00001777517,0.002052147,0.0001429401,0.000163517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01338248,0.0001423641,0.9853759,0.0002738117,0.0003378606,0.0001052672,0.000008307961,0.0003012056,0.00007283738],"genre_scores_gemma":[0.9812269,0.00008620667,0.01813599,0.0001033477,0.0003359298,0.000004941767,0.00004564842,0.00003035766,0.00003074268],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9678444,"threshold_uncertainty_score":0.5393028,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02736372862404576,"score_gpt":0.2469127396543635,"score_spread":0.2195490110303178,"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."}}