Metraipolis › archive › dc_db0cec60bd2c

UNMATCH: Selective Unbalanced Token-Patch Matching for Forensic Image-Claim Verification — arXiv:2609.31766

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31766
License (as archived)
CC0-1.0
Archived
2026-10-07T23:50:38.569Z
SHA-256 of the archived text
1f79ff2f091d7baac176bed74ec429a00d8e819278fb8463be96a6f8630cb77d
Stable URL of this page
https://metraipolis.com/documento/dc_db0cec60bd2c

How to cite

UNMATCH: Selective Unbalanced Token-Patch Matching for Forensic Image-Claim Verification — arXiv:2609.31766 — arXiv (en), https://arxiv.org/abs/2609.31766 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db0cec60bd2c (Metraipolis archive dc_db0cec60bd2c, sha256 1f79ff2f091d7baac176bed74ec429a00d8e819278fb8463be96a6f8630cb77d)
BibTeX
@misc{dcdb0cec60bd2c,
  title = {UNMATCH: Selective Unbalanced Token-Patch Matching for Forensic Image-Claim Verification — arXiv:2609.31766},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31766},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db0cec60bd2c; sha256 1f79ff2f091d7baac176bed74ec429a00d8e819278fb8463be96a6f8630cb77d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31766. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Contextual image misuse pairs an image with a misleading claim. We study image-claim correspondence in fact-checked pairs containing out-of-context reuse, visual manipulation, or both. Existing pair-based detectors often compress the two modalities into a global compatibility score or learn a highly flexible interaction module, which can obscure a decisive local mismatch. We introduce directional multiscale coverage, a compact representation that summarizes local image-claim affinity in both directions and at three spatial scales. At each scale, each direction is summarized by its mean, lower quartile, and two thresholded support ratios; the signed difference between directional means completes a nine-dimensional scale descriptor. Concatenating the three scales yields a compact local representation for a lightweight global-local classifier. Under leakage-aware three-fold, three-seed evaluation on the Snopes subset of the Fauxtography benchmark, UNMATCH achieves 69.82 Macro-F1 and 71.05 balanced accuracy, exceeding the MCOT adaptation by 2.60 and 2.16 points. A matched-reassigned intervention shows that breaking the observed pairing lowers coverage and increases both discrepancy and false-pair probability.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.31766 — 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 2026-10-07T23:29:26.938Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).