Metraipolis › archive › dc_8f2821ff397e
Vision-Language Grounding as Bidirectional Concept Correspondence — arXiv:2608.07886
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.07886
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:50:40.751Z
- SHA-256 of the archived text
95af222877748bfaedb848b5fcaf4ecef71e02dbfb531f4a4c790d1e1b541b37- Stable URL of this page
https://metraipolis.com/documento/dc_8f2821ff397e
How to cite
Vision-Language Grounding as Bidirectional Concept Correspondence — arXiv:2608.07886 — arXiv (en), https://arxiv.org/abs/2608.07886 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8f2821ff397e (Metraipolis archive dc_8f2821ff397e, sha256 95af222877748bfaedb848b5fcaf4ecef71e02dbfb531f4a4c790d1e1b541b37)
BibTeX
@misc{dc8f2821ff397e,
title = {Vision-Language Grounding as Bidirectional Concept Correspondence — arXiv:2608.07886},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.07886},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8f2821ff397e; sha256 95af222877748bfaedb848b5fcaf4ecef71e02dbfb531f4a4c790d1e1b541b37},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07886. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-language grounding connects language to visual content, yet most existing formulations reduce grounding to a unidirectional localization problem: given a prespecified text phrase or category name, identify the corresponding image region. This setup assumes that the relevant linguistic unit is already known, overlooking a more basic challenge in grounded communication: determining which parts of the text are visually referential and how they correspond to entities in the image. We formulate grounding as $\textit{bidirectional concept correspondence}$ over an image-text pair. Given an image and its paired text, the goal is to recover all correspondences between visually referential text spans and instance-level image segments, without assuming that the relevant text spans are provided. This formulation unifies common grounding tasks, including phrase grounding, referring expression grounding, and open-vocabulary detection, by treating text segmentation, image segmentation, and cross-modal alignment as a single correspondence prediction problem. To address this task, we introduce $\textbf{ConCor-1}$, a grounding model built on top of a pretrained vision-language model. It uses learnable $\textit{bridge tokens}$ to represent candidate image-text correspondences and predicts, for each token, a text mask, an image mask, and a correspondence presence score. To train and evaluate this task, we convert diverse grounding and segmentation datasets into a unified correspondence format. Experiments show that $\textbf{ConCor-1}$ consistently outperforms baselines, improving correspondence F1 by 48% on the long-caption dataset and by 29% on zero-shot LVIS, where the large category list serves as the text input.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.CL).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.07886 — 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 2026-10-19T08:49:41.967Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).