Metraipolis › archive › dc_f11d53fc3f00

FOMO: Forget the Concept, Don't Miss Out on the Scene in Selective Video Unlearning — arXiv:2609.39605

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.39605
License (as archived)
CC0-1.0
Archived
2026-10-07T14:46:16.214Z
SHA-256 of the archived text
3d92315ff6f30708711b45cb6158729ff773a517899127fe86bcb23228aa8973
Stable URL of this page
https://metraipolis.com/documento/dc_f11d53fc3f00

How to cite

FOMO: Forget the Concept, Don't Miss Out on the Scene in Selective Video Unlearning — arXiv:2609.39605 — arXiv (en), https://arxiv.org/abs/2609.39605 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f11d53fc3f00 (Metraipolis archive dc_f11d53fc3f00, sha256 3d92315ff6f30708711b45cb6158729ff773a517899127fe86bcb23228aa8973)
BibTeX
@misc{dcf11d53fc3f00,
  title = {FOMO: Forget the Concept, Don't Miss Out on the Scene in Selective Video Unlearning — arXiv:2609.39605},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39605},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f11d53fc3f00; sha256 3d92315ff6f30708711b45cb6158729ff773a517899127fe86bcb23228aa8973},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39605. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The rapid advancement of generative video models has enabled the synthesis of increasingly realistic and temporally coherent videos, while also raising concerns about the generation of harmful content. The reliance on large-scale web datasets during training inevitably exposes these models to undesirable material, making concept unlearning an essential mitigation. Existing methods mainly target static visual concepts, such as objects, identities, or unsafe appearance, largely overlooking motion unlearning. Furthermore, these approaches often pay little attention to preserving the surrounding scene. As a result, successful concept removal may unintentionally alter the background, composition, or overall video dynamics. We argue that effective unlearning should ideally change only what is targeted, while minimizing unnecessary changes to the remaining scene. In this work, we introduce FOMO, to the best of our knowledge the first training-based selective video unlearning method that directly treats preservation of the original scene as a priority. We formulate unlearning around two complementary objectives: what to change and what to preserve. Our method localizes concept-related representations and modifies them, while the preservation mechanism maintains non-target scene information without requiring auxiliary data. Beyond simply erasing unwanted concepts, FOMO explicitly redirects the generation toward a specified safe alternative. We further extend this formulation to motion unlearning, where the concept is defined by temporal behavior rather than a fixed spatial region. Our solution achieves effective unlearning across unsafe content, object, and motion concepts, while achieving the best trade-off between concept removal and scene preservation. Code: this https URL Project Page this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.39605 — 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 2026-10-07T14:19:00.774Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).