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.
Learning jpeg compression artifacts for image manipulation detection and localization.International Journal of Computer Vision, 130(8):1875–1895, August 2022
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
COinCO is a new dataset of inpainted COCO images with in- and out-of-context objects, enabling context reasoning, object prediction from scenes, and improved fake image detection.
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.
-
Common Inpainted Objects In-N-Out of Context
COinCO is a new dataset of inpainted COCO images with in- and out-of-context objects, enabling context reasoning, object prediction from scenes, and improved fake image detection.