arXiv cs.CV: handwriting/OCR
Beyond OCR Accuracy: Text-Centric VQA Under Image Degradation with Modular and End-to-End
OCR 정확도를 넘어서: 모듈러 및 엔드투엔드 방식을 활용한 이미지 품질 저하 시 텍스트 중심 VQA
No write-up yet — this entry is still just the auto-fetched hook. Aaron's own summary (200–500 words) will replace this note once he's written it.