{"id":"W3158545781","doi":"10.1109/iccv48922.2021.01198","title":"Vector Neurons: A General Framework for SO(3)-Equivariant Networks","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":205,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Equivariant map; Computer science; Generalization; Pooling; Simplicity; Code (set theory); Artificial neural network; State (computer science); Artificial intelligence; Rotation (mathematics); Simple (philosophy); Theoretical computer science; Limit (mathematics); Segmentation; State vector; Process (computing); Algorithm; Pattern recognition (psychology); Mathematics; Programming language; Pure mathematics","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001499077,0.0003035406,0.0003425836,0.0001547435,0.0001330052,0.0004992452,0.0004463987,0.0001826926,0.001015143],"category_scores_gemma":[0.00004357197,0.0003061068,0.0002907166,0.0002179789,0.000026982,0.000137291,0.0001008686,0.0004188308,0.0001132889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001120097,"about_ca_system_score_gemma":0.00008513631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001049943,"about_ca_topic_score_gemma":0.00001201187,"domain_scores_codex":[0.9981729,0.00006096939,0.0004493966,0.0005547768,0.0004048014,0.0003571596],"domain_scores_gemma":[0.9987503,0.0002031016,0.00007448831,0.0003928244,0.0004334692,0.0001458463],"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":[0.00004108785,0.0001385403,0.00002502854,0.00002615611,0.0003309375,0.00009934504,0.0001107131,0.8750364,0.002269314,0.04948678,0.01436295,0.05807278],"study_design_scores_gemma":[0.0003501918,0.00009751272,0.0001060352,0.0002456543,0.00003133958,0.00001464246,0.00001178422,0.9901227,0.0006189396,0.00348009,0.004619416,0.0003016814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01138966,0.0001383401,0.9801055,0.002094343,0.004973873,0.0001180071,0.00005569421,0.0001683324,0.0009562535],"genre_scores_gemma":[0.9376518,0.0003350531,0.05667028,0.001126168,0.00282748,0.00004825994,0.0002175851,0.00006347903,0.001059884],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9262621,"threshold_uncertainty_score":0.9999391,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03456609211711004,"score_gpt":0.2956440832736745,"score_spread":0.2610779911565644,"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."}}