{"id":"W2955796932","doi":"10.48550/arxiv.1907.02545","title":"ACNe: Attentive Context Normalization for Robust Permutation-Equivariant Learning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Normalization (sociology); Computer science; Point cloud; Equivariant map; Outlier; Artificial intelligence; Pattern recognition (psychology); Leverage (statistics); Machine learning; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001042703,0.001795625,0.0009253175,0.0008233982,0.0005902478,0.0008836073,0.002511865,0.001328423,0.004604341],"category_scores_gemma":[0.004801069,0.0005834089,0.0008982226,0.0008978589,0.001091242,0.002052155,0.002978227,0.002550692,0.001380282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000808104,"about_ca_system_score_gemma":0.0008861134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004665866,"about_ca_topic_score_gemma":0.007759869,"domain_scores_codex":[0.9992509,0.0001632194,0.00002599819,0.0003072735,0.0001631401,0.00008938563],"domain_scores_gemma":[0.9991497,0.0002822643,0.00008232782,0.0002730907,0.0001569136,0.00005582167],"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":[0.0003897472,0.0001982448,0.001904187,0.0002074332,0.0001794918,0.0002391247,0.0002133068,0.227604,0.02783576,0.03213441,0.01541719,0.6936771],"study_design_scores_gemma":[0.00001996035,0.00009823573,0.0006118452,0.00002112506,0.00002726675,0.0001059178,0.00002938061,0.9457174,0.01061825,0.03800788,0.004719826,0.00002285599],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01131101,0.0003220143,0.9834773,0.0001593287,0.00007792419,0.00005258042,0.0002018112,0.003096802,0.001301263],"genre_scores_gemma":[0.4342708,0.0005446341,0.5539551,0.0007561889,0.0002656738,0.0003363737,0.002093554,0.0009915797,0.00678606],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004665866,"threshold_uncertainty_score":0.01540303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09626596243221305,"score_gpt":0.1955414525281576,"score_spread":0.09927549009594458,"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."}}