OV-DINO

Closed weights Guangzhou AI Public Computing Center,Sun Yat-sen University,Meituan Inc,Pengcheng Lab July 2024

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Guangzhou AI Public Computing Center,Sun Yat-sen University,Meituan Inc,Pengcheng Lab
Organisation type
Government,Industry,Academia,Industry,Academia
Country
China
Published
22 July 2024
Authors
Hao Wang, Pengzhen Ren, Zequn Jie, Xiao Dong, Chengjian Feng, Yinlong Qian, Lin Ma, Dongmei Jiang, Yaowei Wang, Xiangyuan Lan, Xiaodan Liang

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Vision
Task
Object detection

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Training data
tokens

batch size: 128 epochs: 24 resolution: [800, 1333]

Epochs
24

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased
Training code
Open source

Apache 2.0 https://github.com/wanghao9610/OV-DINO weights are supposed to be here but the repo is empty [August 2025] https://huggingface.co/hao9610/OV-DINO

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Unknown

Sources

Where this record came from and when it was last checked.

Reference
OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion
Last updated
28 November 2025

What the numbers mean

Where it came from

OV-DINO was published by Guangzhou AI Public Computing Center,Sun Yat-sen University,Meituan Inc,Pengcheng Lab, in China, in July 2024. It comes out of government,Industry,Academia,Industry,Academia.

It works in Vision, and is recorded as doing object detection.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

Answers

OV-DINO — common questions

01

Who created OV-DINO?

OV-DINO was published by Guangzhou AI Public Computing Center,Sun Yat-sen University,Meituan Inc,Pengcheng Lab, based in China, categorised as government,Industry,Academia,Industry,Academia.

02

When was OV-DINO released?

OV-DINO was published in July 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

03

What is OV-DINO used for?

OV-DINO works in Vision, and is recorded as handling object detection. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

04

What GPU do I need to run OV-DINO?

None. OV-DINO is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

05

Is OV-DINO open source?

No. OV-DINO has not had its weights published, so it exists only as a service controlled by its owner.

06

How many parameters does OV-DINO have?

No parameter count has been published for OV-DINO, which is why no memory or speed figure appears on this page.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.