# Communities for computer vision?

**URL:** <https://discuss.huggingface.co/t/communities-for-computer-vision/24393>\
**Category:** Beginners\
**Created:** [October 13, 2022, 3:20pm UTC](https://discuss.huggingface.co/t/communities-for-computer-vision/24393 "2022-10-13T15:20:06Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![mineshj1291](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/mineshj1291/32/37149_2.png) [@mineshj1291](https://discuss.huggingface.co/u/mineshj1291)\
**Post date:** [October 13, 2022, 3:20pm UTC](https://discuss.huggingface.co/t/communities-for-computer-vision/24393/1 "2022-10-13T15:20:06Z")

</div>

Can you suggest a community similar to this for computer vision please?

---

<div class="post-metadata">

**Author:** ![nielsr](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/nielsr/32/39617_2.png) [@nielsr](https://discuss.huggingface.co/u/nielsr)\
**Post date:** [October 14, 2022, 9:18am UTC](https://discuss.huggingface.co/t/communities-for-computer-vision/24393/2 "2022-10-14T09:18:57Z")

</div>

Hi,

HuggingFace is quite active in other domains besides NLP as well.

We currently support 20+ vision models, including [ConvNeXt](https://huggingface.co/docs/transformers/model_doc/convnext), [Swin Transformer](https://huggingface.co/docs/transformers/model_doc/swin), [Vision Transformer](https://huggingface.co/docs/transformers/model_doc/vit), [Swin Transformer v2](https://huggingface.co/docs/transformers/model_doc/swinv2), etc.

For an overview of all vision backbones, see here: [Auto Classes](https://huggingface.co/docs/transformers/model_doc/auto#transformers.AutoModelForImageClassification).

Besides that, we also support object detection models, such as DETR, Deformable DETR, Conditional DETR and YOLOS: [Auto Classes](https://huggingface.co/docs/transformers/model_doc/auto#transformers.AutoModelForObjectDetection).

We also support image segmentation models, such as [SegFormer](https://huggingface.co/docs/transformers/model_doc/segformer) and [MobileViT](https://huggingface.co/docs/transformers/model_doc/mobilevit).

We have a computer vision channel on Discord: [http://hf.co/join/discord](https://t.co/1n75wi976V?amp=1)

---

<div class="post-metadata">

**Author:** ![mineshj1291](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/mineshj1291/32/37149_2.png) [@mineshj1291](https://discuss.huggingface.co/u/mineshj1291)\
**Post date:** [October 14, 2022, 11:21am UTC](https://discuss.huggingface.co/t/communities-for-computer-vision/24393/3 "2022-10-14T11:21:41Z")

</div>

thanks for sharing these resources. Is there any model for object tracking as well?

---

<div class="post-metadata">

**Author:** ![nielsr](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/nielsr/32/39617_2.png) [@nielsr](https://discuss.huggingface.co/u/nielsr)\
**Post date:** [October 14, 2022, 2:41pm UTC](https://discuss.huggingface.co/t/communities-for-computer-vision/24393/4 "2022-10-14T14:41:14Z")

</div>

There’s no object tracking yet. But we’re adding several domains, like monocular depth estimation recently with models like DPT and [GLPN](https://huggingface.co/docs/transformers/main/en/model_doc/glpn#transformers.GLPNForDepthEstimation).

If you have suggestions for models to add (with pre-trained weights), feel free to open an issue on Github.

---

<div class="post-metadata">

**Author:** ![Indramal](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/indramal/32/61744_2.png) [@Indramal](https://discuss.huggingface.co/u/Indramal)\
**Post date:** [October 15, 2022, 1:30am UTC](https://discuss.huggingface.co/t/communities-for-computer-vision/24393/5 "2022-10-15T01:30:42Z")

</div>

> [@mineshj1291](#):
>
> object tracking

Use object detection + OpenCV for object tracking