HAKARI-Bench reconstructs 35 benchmarks into 551 tasks across 43 languages, reproducing full MTEB, MMTEB, and BEIR rankings with Spearman correlation above 0.97 while supporting efficiency variant comparisons.
In: 2021 IEEE FourthInternationalConferenceonArtificialIntelligenceandKnowledgeEngineer- ing (AIKE)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Deep metric learning with L2-normalized embeddings and prototype-based matching achieves OSCR of 0.9945 and EER of 1.57% on large-scale vein datasets under strict open-set subject-disjoint protocols.
citing papers explorer
-
HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions
HAKARI-Bench reconstructs 35 benchmarks into 551 tasks across 43 languages, reproducing full MTEB, MMTEB, and BEIR rankings with Spearman correlation above 0.97 while supporting efficiency variant comparisons.
-
Open-Set Vein Biometric Recognition with Deep Metric Learning
Deep metric learning with L2-normalized embeddings and prototype-based matching achieves OSCR of 0.9945 and EER of 1.57% on large-scale vein datasets under strict open-set subject-disjoint protocols.