Metraipolis › archive › dc_a050884f3acd
Evidence-Guided Detection, Localization and Explanation for Text-Centric Image Forensics — arXiv:2609.02097
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.02097
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T05:49:52.804Z
- SHA-256 of the archived text
13c6398679cafc8aa24f54e04c3851725640ff83a665009cfc1f6e1d7b93106d- Stable URL of this page
https://metraipolis.com/documento/dc_a050884f3acd
How to cite
Evidence-Guided Detection, Localization and Explanation for Text-Centric Image Forensics — arXiv:2609.02097 — arXiv (en), https://arxiv.org/abs/2609.02097 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a050884f3acd (Metraipolis archive dc_a050884f3acd, sha256 13c6398679cafc8aa24f54e04c3851725640ff83a665009cfc1f6e1d7b93106d)
BibTeX
@misc{dca050884f3acd,
title = {Evidence-Guided Detection, Localization and Explanation for Text-Centric Image Forensics — arXiv:2609.02097},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.02097},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a050884f3acd; sha256 13c6398679cafc8aa24f54e04c3851725640ff83a665009cfc1f6e1d7b93106d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02097. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The rapid progress of AIGC has made text-centric image manipulation increasingly accessible, creating new forensic challenges that require not only authenticity detection but also spatial grounding and evidence-based explanation. This paper presents our solution to the GenText-Forensics Challenge at ACM Multimedia 2026. We propose an evidence-guided detector-localizer-reasoner system, where an image-level detector provides a global authenticity prior, a dedicated localizer extracts tampered regions as spatial grounding evidence, and an MLLM-based reasoner generates structured forensic reports grounded in this expert forensic evidence. These modules are connected through a cascaded evidence flow: the detector gates the subsequent localization and prompting process, the localizer converts tamper responses into grounding boxes, and the reasoner is trained to synthesize the detector decision and localized evidence into the final report. As a key part of our method, we introduce iterative difficulty-aware mining to improve localization quality and apply report-mask consistency post-processing to align report grounding with predicted masks. On the official hidden test set, our system achieves a final score of 0.638 and ranks second in the challenge, validating the effectiveness of the proposed evidence-guided system. The code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.02097 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T05:25:58.067Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).