{"id":"W2031760064","doi":"10.1145/2461912.2461933","title":"Learning part-based templates from large collections of 3D shapes","year":2013,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":240,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Division of Computer and Network Systems; Seventh Framework Programme; Natural Sciences and Engineering Research Council of Canada; Google; International Science and Technology Center; Adobe Systems; Division of Computing and Communication Foundations; Intel Corporation","keywords":"Computer science; Segmentation; Scalability; Template; Set (abstract data type); Point (geometry); Matching (statistics); Similarity (geometry); Data mining; Probabilistic logic; Artificial intelligence; Encoding (memory); Pattern recognition (psychology); Image (mathematics); Database; Mathematics","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":[0.002001805,0.002999566,0.004296761,0.005457142,0.001195951,0.003533347,0.006368743,0.004447428,0.0029311],"category_scores_gemma":[0.006227811,0.002785335,0.006588683,0.0074144,0.001867787,0.00430483,0.003830043,0.003264886,0.006492417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001658953,"about_ca_system_score_gemma":0.00213087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007114796,"about_ca_topic_score_gemma":0.01114432,"domain_scores_codex":[0.9971541,0.0002862243,0.0001673576,0.001339029,0.0008631302,0.0001901265],"domain_scores_gemma":[0.9953403,0.00123034,0.0004224831,0.002205212,0.0005641229,0.0002375496],"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":[0.0003536848,0.0003113711,0.00747263,0.0003107894,0.0004642608,0.0005569034,0.0003417585,0.246413,0.02204964,0.004511397,0.01971369,0.6975009],"study_design_scores_gemma":[0.00002361718,0.0000864001,0.001597111,0.00002620392,0.000071435,0.0005423435,0.0001103388,0.9730758,0.008654933,0.0118626,0.003901119,0.00004819146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02118742,0.0005129905,0.9627149,0.0001980179,0.00007697855,0.0002284105,0.001585438,0.01265124,0.0008446191],"genre_scores_gemma":[0.1537202,0.0007885832,0.8257638,0.0003443789,0.0001379719,0.0004321228,0.01406944,0.002071314,0.002672227],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007114796,"threshold_uncertainty_score":0.01414675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01362342377121343,"score_gpt":0.2102778423845592,"score_spread":0.1966544186133457,"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."}}