SymbolSight optimizes symbol-to-letter mappings via simulated prosthetic vision and bigram statistics, cutting predicted confusion by a median factor of 22 across Arabic, Bulgarian, and English.
mixup: Beyond empirical risk minimization
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
AaSP learns aliasing-stable audio representations by augmenting patch tokens with adaptive subband features from alias-prone bands and using teacher-student masked modeling plus multi-mask contrastive regularization, reaching SOTA on AS-20K, ESC-50, and NSynth under fine-tuning.
citing papers explorer
-
SymbolSight: Minimizing Inter-Symbol Interference for Reading with Prosthetic Vision
SymbolSight optimizes symbol-to-letter mappings via simulated prosthetic vision and bigram statistics, cutting predicted confusion by a median factor of 22 across Arabic, Bulgarian, and English.
-
AaSP: Aliasing-aware Self-Supervised Pre-Training for Audio Spectrogram Transformers
AaSP learns aliasing-stable audio representations by augmenting patch tokens with adaptive subband features from alias-prone bands and using teacher-student masked modeling plus multi-mask contrastive regularization, reaching SOTA on AS-20K, ESC-50, and NSynth under fine-tuning.