{"id":"W2952074843","doi":"10.48550/arxiv.1906.01592","title":"Dominant Set Clustering and Pooling for Multi-View 3D Object Recognition","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pooling; Cluster analysis; Computer science; Artificial intelligence; Pattern recognition (psychology); Object (grammar); Cognitive neuroscience of visual object recognition; Set (abstract data type); Feature (linguistics); Layer (electronics); Key (lock); Machine learning; Data mining","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002744127,0.0002462748,0.0002972095,0.0002453513,0.0001951271,0.0001769913,0.000421843,0.0002227647,0.00001740914],"category_scores_gemma":[0.00002760335,0.0002848803,0.0001489418,0.0001580131,0.00003468752,0.0004837631,0.0007286623,0.0003038011,0.00009740422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001044149,"about_ca_system_score_gemma":0.00008009273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005551977,"about_ca_topic_score_gemma":0.00005889355,"domain_scores_codex":[0.9985233,0.00008313831,0.0001933857,0.0008788449,0.00005142455,0.0002699175],"domain_scores_gemma":[0.9989778,0.00009300127,0.0002394018,0.0004386689,0.000156446,0.00009470054],"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":[0.001078878,0.001406197,0.003236785,0.01383868,0.001916089,0.001097315,0.00932972,0.2334256,0.003056479,0.02426164,0.002468381,0.7048842],"study_design_scores_gemma":[0.001098,0.00006793823,0.0002603963,0.0004700552,0.0000943295,0.00001510576,0.00007967914,0.9898247,0.0004541754,0.006348297,0.0008238593,0.000463429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.123344,0.00007757674,0.874541,0.00002718005,0.0008394839,0.0006204859,0.00004869316,0.000122547,0.0003790665],"genre_scores_gemma":[0.9835377,0.0005471364,0.01477132,0.0001389571,0.0001065655,0.000004961022,0.00008741658,0.00001999793,0.0007859556],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8601937,"threshold_uncertainty_score":0.9999604,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1636443158930559,"score_gpt":0.2326491904001286,"score_spread":0.06900487450707268,"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."}}