Metraipolis › archive › dc_77353f38c461
Beyond Token Representations: Explicit Visual Object Grounding for Video Reasoning Segmentation — arXiv:2611.04472
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04472
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T12:56:27.755Z
- SHA-256 of the archived text
9fe57562644111e291a62ecf52b76c9ca5e7ac40257216a437cda6d6038c1468- Stable URL of this page
https://metraipolis.com/documento/dc_77353f38c461
How to cite
Beyond Token Representations: Explicit Visual Object Grounding for Video Reasoning Segmentation — arXiv:2611.04472 — arXiv (en), https://arxiv.org/abs/2611.04472 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_77353f38c461 (Metraipolis archive dc_77353f38c461, sha256 9fe57562644111e291a62ecf52b76c9ca5e7ac40257216a437cda6d6038c1468)
BibTeX
@misc{dc77353f38c461,
title = {Beyond Token Representations: Explicit Visual Object Grounding for Video Reasoning Segmentation — arXiv:2611.04472},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04472},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_77353f38c461; sha256 9fe57562644111e291a62ecf52b76c9ca5e7ac40257216a437cda6d6038c1468},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04472. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Video Reasoning Segmentation (VRS) aims to infer and segment target objects specified by reasoning queries in videos. Existing methods typically first infer the target and generate a few segmentation tokens for it, which are then fed into a mask decoder for mask prediction. However, such segmentation tokens tend to be both semantically monotonous and spatially ambiguous, making them largely insufficient to represent the target to guide mask prediction. In this paper, we propose an explicit visual object grounding framework for VRS. Specifically, we first propose a spatial-aware prompt generation and refinement scheme, in which we query a multimodal large language model to generate explicit spatial prompts (i.e., bounding box and point set) for the target and then refine them through multi-step dialogue. Furthermore, we introduce a query diversification and alignment module to generate auxiliary queries that describe the same target from different perspectives. We then enforce cross-query consistency between their predicted spatial prompts to alleviate the training bias caused by query limitations. Finally, we select several reliable frames using a prompt-based keyframe selection strategy to support mask decoding and propagation. Extensive experiments on eight datasets demonstrate that our method significantly outperforms state-of-the-art methods. The code is available at this https URL . 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/2611.04472 — 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 2026-11-04T12:33:47.153Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).