{"id":"W2086504823","doi":"10.1109/tpami.2014.2321376","title":"Scalable Nearest Neighbor Algorithms for High Dimensional Data","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":1415,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Best bin first; k-nearest neighbors algorithm; Nearest-neighbor chain algorithm; Nearest neighbor search; Cover tree; Scalability; Matching (statistics); Cluster analysis; Artificial intelligence; Algorithm; Large margin nearest neighbor; Set (abstract data type); Data mining; Pattern recognition (psychology); Canopy clustering algorithm; Correlation clustering; 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":[0.002565212,0.001118496,0.002325685,0.002579625,0.001424583,0.001995156,0.003213601,0.001893063,0.004164001],"category_scores_gemma":[0.01156938,0.000837005,0.001420963,0.005025299,0.0008416918,0.004624987,0.003442186,0.001920601,0.002897039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001313892,"about_ca_system_score_gemma":0.001843372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008225355,"about_ca_topic_score_gemma":0.009342107,"domain_scores_codex":[0.996648,0.0005922002,0.0002578518,0.0007669153,0.001574107,0.0001609832],"domain_scores_gemma":[0.9970856,0.0009589641,0.0002496922,0.001006475,0.0006194036,0.00007981759],"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":[0.000244973,0.0001730079,0.001567101,0.0003621948,0.0001905093,0.000179926,0.000228572,0.2733735,0.005073566,0.04003407,0.01817051,0.6604021],"study_design_scores_gemma":[0.00005318721,0.00005042887,0.0003933558,0.00002983982,0.00001911085,0.0001772469,0.00009226167,0.9249101,0.002366625,0.06402604,0.007850635,0.00003124134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0032917,0.0008230411,0.9929643,0.0001286522,0.00008412618,0.00008705188,0.0001757487,0.001460722,0.0009846146],"genre_scores_gemma":[0.06571697,0.0008029672,0.929535,0.0001327589,0.0001212749,0.0003481178,0.00120536,0.0002200117,0.001917513],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008225355,"threshold_uncertainty_score":0.01635498,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0376312748953848,"score_gpt":0.3119817468991594,"score_spread":0.2743504720037746,"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."}}