Metraipolis › archive › dc_cf4edd0f1108

ReVEAL: Eliciting Role-Aware Latent Visual Evidence from MLLMs for Reasoning Video Object Segmentation — arXiv:2610.41257

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41257
License (as archived)
CC0-1.0
Archived
2026-11-03T08:21:45.727Z
SHA-256 of the archived text
e81a6f8686e747505c12eed4f0a000338595ca22927273dd337e70bd91be825c
Stable URL of this page
https://metraipolis.com/documento/dc_cf4edd0f1108

How to cite

ReVEAL: Eliciting Role-Aware Latent Visual Evidence from MLLMs for Reasoning Video Object Segmentation — arXiv:2610.41257 — arXiv (en), https://arxiv.org/abs/2610.41257 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf4edd0f1108 (Metraipolis archive dc_cf4edd0f1108, sha256 e81a6f8686e747505c12eed4f0a000338595ca22927273dd337e70bd91be825c)
BibTeX
@misc{dccf4edd0f1108,
  title = {ReVEAL: Eliciting Role-Aware Latent Visual Evidence from MLLMs for Reasoning Video Object Segmentation — arXiv:2610.41257},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41257},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf4edd0f1108; sha256 e81a6f8686e747505c12eed4f0a000338595ca22927273dd337e70bd91be825c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41257. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reasoning video object segmentation (ReVOS) requires segmenting the target specified by an implicit query throughout a video. Existing MLLM-based methods typically require costly cross-model alignment, tying MLLM training to a downstream segmentation model. We present ReVEAL, a decoupled thinking-with-video framework for ReVOS that elicits role-aware latent visual evidence from MLLM reasoning to directly guide segmentation. ReVEAL introduces Visual Evidence Tokens (VETs) into video reasoning to associate necessary visual regions or entities with target, background, or distractor roles, while a Dynamic Attention Layer Router adaptively aggregates VET-to-video attention across layers into role-specific grounding evidence. We train the MLLM to perform VET-augmented reasoning on our constructed ReVEAL-47K dataset, with a Contrastive Attention Grounding Loss as auxiliary supervision to apply role-specific constraints to VET attention and optimize layer routing for reliable latent grounding. At inference, ReVEAL identifies the target through this thinking-with-video process and fuses the resulting role-specific evidence to guide a frozen SAM2 in predicting target masks. Experiments on five benchmarks show that ReVEAL outperforms alignment-free baselines and remains competitive with alignment-based methods.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.41257 — 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 2026-11-03T08:06:38.824Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).