Robustness Evaluation of OCR-based Visual Document Understanding under Multi-Modal Adversarial Attacks

Documenti analoghi

• Adversarial Training with OCR Modality Perturbation for Scene-Text Visual Question Answering
  di: Shen, Zhixuan, et al.
  Pubblicazione: (2024)
• ThyroidEffi 1.0: A Cost-Effective System for High-Performance Multi-Class Thyroid Carcinoma Classification
  di: Pham-Ngoc, Hai, et al.
  Pubblicazione: (2025)
• TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document
  di: Liu, Yuliang, et al.
  Pubblicazione: (2024)
• Adversarial Attack for RGB-Event based Visual Object Tracking
  di: Chen, Qiang, et al.
  Pubblicazione: (2025)
• Lost in OCR Translation? Vision-Based Approaches to Robust Document Retrieval
  di: Most, Alexander, et al.
  Pubblicazione: (2025)