Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding
| Date | Stars |
|---|---|
| 2026-07-24 | 1400 |
| 2026-07-25 | 1400 |
| 2026-07-28 | 1400 |
| 2026-07-30 | 1400 |
| 2026-08-06 | 1400 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<h1 align="center">DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding</h1> <div align=center> **The World's Top-Performing Vision Model for Open-World Object Detection** The project provides **examples** for using **DINO-X**, which is hosted on [DeepDataSpace](https://deepdataspace.com/home). **[IDEA Research](https://github.com/IDEA-Research)** </div> <div align=center> [](https://arxiv.org/abs/2411.14347) [](https://deepdataspace.com/home) </div> [](https://github.com/user-attachments/assets/7209d885-7401-4f9e-9ed1-899eb4bd12b1) ## Highlights Beyond [Grounding DINO 1.5](https://github.com/IDEA-Research/Grounding-DINO-1.5-API), DINO-X has several improvements, taking a step forward towards becoming a more general object-centric vision model. The highlights of the DINO-X are as follows: ✨ **The Strongest Open-Set Detection Performance**: DINO-X Pro set new SOTA results on zero-shot transfer detection benchmarks: **56.0 AP** on COCO, **59.8 AP** on LVIS-minival and **52.4 AP** on LVIS-val. Notably, it scores **63.3 AP** and **56.5 AP** on the rare classes of LVIS-minival and LVIS-val benchmarks, improving the previous SOTA performance by 5.8 box AP and 5.0 box AP. Such a result underscores its significantly enhanced capacity for recognizing long-tailed objects. 🔥 **Diverse Input Prompt and Multi-level Output Semantic Representations**: DINO-X can accept text prompts, visual prompts, and customized prompts as input, and it outputs representations at various semantic levels, including bounding boxes, segmentation masks, pose keypoints, and object captions, with multiple perception heads. 🍉 **Rich and Practical Capabilities**: DINO-X can simultaneously support lots of highly practical tasks, including Open-Set Object Detection and Segmentation, Phrase Grounding, Visual-Prompt Counting, Pose Estimation, and Region Captioning. We further develop a universal object prompt to achieve *Prompt-Free* Anything Detection and Recognition. 🔌 **Seamless AI Tool Integration**: With [DINO-X MCP Server](https://github.com/IDEA-Research/DINO-X-MCP), developers can integrate DINO-X's capabilities directly into Cursor, Claude, and other MCP-compatible AI tools, enabling object detection in conversational AI workflows. ## Latest News - **2025.07.23**: We've updated `dds-cloudapi-sdk` to version `0.5.3`, which significantly improves mask encoding by removing the previous non-standard method and adopting the `pycocotools-aligned rle mask format`. This change makes it much easier to decode masks directly with pycocotools, and we've added a new `mask_format = coco_rle` parameter to the API; you can find detailed usage examples here: [dds visualization utils](https://github.com/deepdataspace/dds-cloudapi-sdk/blob/8b49bc882dc8f112ffe785afbf20c610ce5112d2/dds_cloudapi_sdk/visualization_util.py) - **2025.06.18**: 🚀 **DINO-X MCP Server** is now available! Integrate DINO-X into Cursor and other MCP-compatible tools. Check [dinox-mcp](https://github.com/IDEA-Research/DINO-X-MCP) for details. - **2025.05.21**: For more demo usages, including `DINO-X`, `T-Rex`, `DINO-X-SeeK`, please check [dds-cloud-api examples](https://github.com/deepdataspace/dds-cloudapi-sdk/blob/main/examples.py) for more details. - **2025.04.21**: Update to `dds-cloudapi-sdk` API V2 version. The V1 version in the original API for `DINO-X` has been deprecated, please update to the latest `dds-cloudapi-sdk` by `pip install dds-cloudapi-sdk -U` to use `DINO-X` model. Please refer to [dds-cloudapi-sdk](https://github.com/deepdataspace/dds-cloudapi-sdk) and our [API docs](https://cloud.deepdataspace.com/docs) to view more details about the update. - **2025.03.11**: We have released [DINO-XSeeK](https://deepdataspace.com/blog/dino-xseek) model towards dete
Excerpt of 18,211 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:42834e8b07b7b7fd, topic:pose-estimation, desc:object detection, readme:object detection
