DiffNet achieves state-of-the-art cross-domain performance on human-made document tampering localization by combining RGB-DCT early fusion with multi-level discrepancy transformations and a frequency-index-aware DCT-quantization embedding, outperforming priors by ~30% at up to 7x throughput.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
SEED integrates similarity-guided data augmentation, a DINOv3-based ViT with LoRA for joint detection and localization, and an evolving MLLM harness to generate explainable forensic reports, placing 3rd in the GenText-Forensics Challenge.
citing papers explorer
-
Efficient Document Tampering Localization with Multi-Level Discrepancy Features and Unified DCT-Quantization Embedding
DiffNet achieves state-of-the-art cross-domain performance on human-made document tampering localization by combining RGB-DCT early fusion with multi-level discrepancy transformations and a frequency-index-aware DCT-quantization embedding, outperforming priors by ~30% at up to 7x throughput.
-
SEED: Simple ViT and Evolving Harness for Explainable Text Forgery Detection
SEED integrates similarity-guided data augmentation, a DINOv3-based ViT with LoRA for joint detection and localization, and an evolving MLLM harness to generate explainable forensic reports, placing 3rd in the GenText-Forensics Challenge.