Vision-Language Grounding as Bidirectional Concept Correspondence
Summary
This paper introduces ConCor-1, a grounding model that treats vision-language grounding as bidirectional concept correspondence, jointly recovering text spans, image segments, and cross-modal matches without prespecified phrases. It unifies phrase grounding, referring expression grounding, and open-vocabulary detection, achieving significant F1 improvements on long-caption and zero-shot LVIS benchmarks.
View Cached Full Text
Cached at: 08/11/26, 10:20 AM
Paper page - Vision-Language Grounding as Bidirectional Concept Correspondence
Source: https://huggingface.co/papers/2608.07886
Abstract
ConCor-1 treats vision-language grounding as bidirectional concept correspondence, jointly predicting text spans, image segments, and cross-modal matches without prespecified phrases.
Vision-language groundingconnects 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 asbidirectional concept correspondenceover 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, includingphrase grounding,referring expression grounding, andopen-vocabulary detection, by treating text segmentation, image segmentation, andcross-modal alignmentas a single correspondence prediction problem. To address this task, we introduceConCor-1, a grounding model built on top of a pretrained vision-language model. It uses learnablebridge tokensto 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 thatConCor-1consistently 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.
View arXiv pageView PDFProject pageGitHub2Add to collection
Get this paper in your agent:
hf papers read 2608\.07886
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper1
#### UWGZQ/ConCor-1 Image Segmentation• 0.9B• Updatedabout 3 hours ago • 131
Datasets citing this paper1
#### UWGZQ/ConCor-1-Data Viewer• Updatedabout 3 hours ago • 1.28M • 110 • 1
Spaces citing this paper1
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Thinking with Visual Grounding
This paper introduces visually grounded thinking, a method for vision-language models to interleave natural-language reasoning with explicit visual evidence grounding using points or boxes. A scalable synthesis pipeline and grounding-aware reinforcement learning improve reasoning accuracy, enabling a 4B model to match or surpass a 27B model on spatial and counting benchmarks.
When Seeing Is Not Enough: Benchmarking Interactive Visual Grounding in LVLMs
This paper introduces a controlled evaluation framework for interactive visual grounding in large vision-language models (LVLMs), showing that current LVLMs perform below human baselines and struggle with proactive question-driven grounding.
Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models
This paper presents a function-centric framework using Transcoders to trace computational pathways in vision-language models, demonstrating stronger attribution of visual grounding and the ability to predict hallucinations via graph-based features.
RefCaptioner: Multi-Reference Image-Grounded Video Captioning
Introduces multi-reference image-grounded video captioning and proposes RefCaptioner, a two-stage post-training framework with mixed-data SFT and hierarchical coverage-discounted GRPO. The paper also presents MRVBench, a benchmark for evaluating caption factuality and multi-reference grounding.
SpatialCORE: Confidence-Aware Grounded Spatial Reasoning in Large Vision--Language Models
SpatialCORE is a post-training framework that uses a model's confidence in its generated bounding-box grounding as a learning signal for spatial reasoning in large vision-language models, achieving state-of-the-art results among open-source models on spatial reasoning benchmarks.