{"id":"W3185277158","doi":"10.1109/tkde.2021.3100353","title":"On the Benefits of Two Dimensional Metric Learning","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Western University; Université Laval; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Boosting (machine learning); Computer science; Metric (unit); Dimension (graph theory); Benchmark (surveying); Generalization; Intrinsic dimension; Algorithm; Rank (graph theory); Data structure; Artificial intelligence; Feature learning; External Data Representation; Learning to rank; Machine learning; Curse of dimensionality; Mathematics; Ranking (information retrieval)","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":[0.01048229,0.001745118,0.001765538,0.001811726,0.001051572,0.003047011,0.001998127,0.002504868,0.002184152],"category_scores_gemma":[0.05245426,0.0007478216,0.0009413218,0.002463653,0.004129481,0.007815516,0.005739058,0.004819986,0.001161809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00160141,"about_ca_system_score_gemma":0.001223103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001166701,"about_ca_topic_score_gemma":0.0009672145,"domain_scores_codex":[0.9911107,0.004906781,0.0003232078,0.001015986,0.0023717,0.0002715398],"domain_scores_gemma":[0.9535139,0.03347854,0.002211625,0.00646269,0.003418941,0.0009142986],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000362238,0.000254105,0.004140109,0.0004700111,0.0001515799,0.0002575727,0.0004158295,0.2809484,0.005147925,0.427819,0.006074657,0.2739585],"study_design_scores_gemma":[0.00002563614,0.0001893926,0.0006393701,0.00004752815,0.00001385747,0.0001978896,0.00004904799,0.7693379,0.002132364,0.2230205,0.004306463,0.00004006626],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01645768,0.002732859,0.9744714,0.001962281,0.000104412,0.00005935207,0.00008644607,0.0003599684,0.0037656],"genre_scores_gemma":[0.4630604,0.002833615,0.527212,0.001729937,0.000735583,0.000279028,0.0004351623,0.000300065,0.00341409],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01048229,"threshold_uncertainty_score":0.05543625,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02995721154589971,"score_gpt":0.2583198251666257,"score_spread":0.228362613620726,"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."}}