{"id":"W4416235061","doi":"10.48550/arxiv.2511.08833","title":"Enhancing Rotation-Invariant 3D Learning with Global Pose Awareness and Attention Mechanisms","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Robustness (evolution); Segmentation; Feature (linguistics); Point cloud; Rotation (mathematics); Convolution (computer science); Point (geometry)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007700359,0.001298367,0.001086191,0.0007104865,0.0002986162,0.0008392588,0.002074511,0.0009441827,0.001805125],"category_scores_gemma":[0.002097989,0.000502245,0.001169699,0.0008315618,0.001021861,0.00170343,0.002604492,0.001234568,0.0006949374],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007633389,"about_ca_system_score_gemma":0.000835339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005698818,"about_ca_topic_score_gemma":0.006257348,"domain_scores_codex":[0.9995798,0.0000616064,0.00001516133,0.0001618633,0.0001162804,0.00006522552],"domain_scores_gemma":[0.9993448,0.0001951616,0.00007924639,0.0002250866,0.0001026432,0.00005301186],"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":[0.000149574,0.0001389398,0.002121307,0.0001081827,0.0001090515,0.0001008351,0.0001510542,0.4626398,0.0447272,0.008065651,0.00293577,0.4787526],"study_design_scores_gemma":[0.000005873596,0.00004204343,0.0003603202,0.000004333435,0.00001290028,0.00003780913,0.00001027279,0.9887,0.005802071,0.004404038,0.0006128789,0.000007571624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03037731,0.0002558716,0.9661759,0.0001482143,0.00002993752,0.00002774935,0.00007389911,0.001836166,0.001074947],"genre_scores_gemma":[0.7660062,0.0005052239,0.2285192,0.0004426252,0.0001247391,0.00008133029,0.0006249328,0.0004058385,0.003289959],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005698818,"threshold_uncertainty_score":0.01133132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01415604305499542,"score_gpt":0.2363993647983153,"score_spread":0.2222433217433199,"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."}}