ForensicsTok turns image manipulation localization into autoregressive token generation with a smoothing decoder and multi-scale forensic feature fusion, showing gains over MLLM baselines and slight gains over expert models on six benchmarks.
Can we get rid of handcrafted feature extractors? sparsevit: Nonsemantics-centered, parameter-efficient image manipulation localization through spare-coding transformer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ForensicsTok: Forensics-Guided Tokenized Modeling for Image Tampering Localization
ForensicsTok turns image manipulation localization into autoregressive token generation with a smoothing decoder and multi-scale forensic feature fusion, showing gains over MLLM baselines and slight gains over expert models on six benchmarks.