{"id":"W2963382234","doi":"10.24963/ijcai.2017/345","title":"Exemplar-centered Supervised Shallow Parametric Data Embedding","year":2017,"lang":"en","type":"article","venue":"","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Embedding; Computer science; Dimensionality reduction; Scalability; Pairwise comparison; Benchmark (surveying); Metric (unit); Machine learning; Speedup; Parametric statistics; Artificial intelligence; Computational complexity theory; Data point; Algorithm; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001048887,0.001262982,0.001413716,0.0007669129,0.0003431645,0.0008373249,0.002522101,0.001118441,0.002087806],"category_scores_gemma":[0.00444865,0.0004826606,0.0009799307,0.0008940209,0.00106716,0.002487529,0.002851729,0.001777207,0.001223036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006291955,"about_ca_system_score_gemma":0.0007859085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001724171,"about_ca_topic_score_gemma":0.003398836,"domain_scores_codex":[0.9987571,0.0003532755,0.0000785436,0.0003807023,0.0003412295,0.00008907542],"domain_scores_gemma":[0.9980738,0.0004567338,0.0002067585,0.0008336168,0.0003562111,0.00007284535],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001938153,0.0002449109,0.002084764,0.0001930488,0.00009238523,0.0001272428,0.0001944797,0.383821,0.02799773,0.01254107,0.004893547,0.567616],"study_design_scores_gemma":[0.000003806227,0.00006700613,0.00021917,0.000005841824,0.000005401671,0.00006234797,0.00001681407,0.9883035,0.005209448,0.005528263,0.0005680994,0.00001035067],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02369364,0.0001218948,0.9738123,0.0000587641,0.000016429,0.00006237486,0.0001502107,0.001487315,0.0005970072],"genre_scores_gemma":[0.5066439,0.0001649923,0.4872308,0.0001678576,0.00003614155,0.0003203896,0.001928077,0.000328373,0.003179437],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002522101,"threshold_uncertainty_score":0.006984413,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1486660496646793,"score_gpt":0.3537607889447627,"score_spread":0.2050947392800834,"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."}}