# Visual Grounding

> Finding the spot in a picture that some words point to. A box marks it.

**Field:** Artificial Intelligence  
**Category:** Multimodal  
**Also known as:** Phrase Grounding, Referring Expression Grounding, Grounded Image Understanding

## Think of it like

It is like asking a friend where the red cup is. She puts her finger on it.

## Definition

Visual grounding is finding the exact part of a picture that some words describe. You give the model an image and a phrase, like 'the red cup on the left'. It answers with a box or an outline around that thing. This is harder than spotting cups in general, because the words pick out one of them. It lets a robot, an app or an AI agent point at things it was told about in plain words.

## Example

Jack's app is told to find the blue coat by the door. In a photo of a busy hall, it draws a box around that one coat.

## Why it matters

Many tasks need more than knowing what is in a picture. They need to know where the named thing is, so they can act on it.

## Common mistake

Mixing it up with finding objects. That finds every cup. Grounding finds the one cup the words point to.

## Three principles

- **Words to a place.** A phrase becomes a box.
- **One, not all.** The words pick out a single thing.
- **Lets AI point.** Useful for robots and agents.

## Related terms

- [Object Detection](https://learn.benibix.com/term/ai/object-detection)
- [Vision Language Model (VLM)](https://learn.benibix.com/term/ai/vision-language-model)
- [Image Segmentation](https://learn.benibix.com/term/ai/image-segmentation)
- [Visual Question Answering](https://learn.benibix.com/term/ai/visual-question-answering)
- [Computer Use](https://learn.benibix.com/term/ai/computer-use)

## Told apart from

- [Visual Grounding vs Object Detection](https://learn.benibix.com/compare/visual-grounding-vs-object-detection): People think visual grounding is the same as object detection. Both draw boxes on a picture, but they answer different asks. Object detection finds every thing of a known kind, like every cup on the table. Visual grounding reads a phrase, such as the red cup on the left, and finds the one thing it points to.

![Three panels. Left: a strip of video frames with a question and a time stamp as the answer. Middle: a photo with the words 'the red cup' and a box drawn around the cup. Right: a dog photo and the words 'a dog' landing on the same spot on a map of points.](https://learn.benibix.com/diagrams/ai5-vision-language.svg)

---

Source: https://learn.benibix.com/term/ai/visual-grounding
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-17
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
