Uniformer_video_demo by Sense-X

Uniformer_video_demo by Sense-X

A Gradio demo that runs the Sense-X UniFormer video model on a clip and reports its class, with three example videos included. Suits students and developers who want to try video classification in a browser.

Made by Sense-X on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: Uniformer_video_demo is a Gradio app from Sense-X that shows its UniFormer video model at work. The repository holds a Kinetics class list, the model code and three example clips of baseball, hoverboarding and yoga. It looks like you give it a clip and it names the action it sees.

Who it suits: Students and developers who want to see a model recognise actions in video, or who want a compact example of a video model wrapped in a Gradio page.

Industry | Who uses it | How they use it | Example
Education | Computer vision students | Try the demo, then read uniformer.py and transforms.py for the model code | Run the bundled yoga clip
Software | Developers | Use the project as a pattern for a Gradio video demo | Replace the example clips with their own
Research | Vision researchers | Check the Sense-X video model on a few clips | Compare its answers on the baseball and hoverboarding clips

Skip it if you need a tool for long videos or large batches, because it is a single page demo.

Where to use it:

• A web browser, on the Space's page on Hugging Face
• Windows, macOS or Linux with Python, from a downloaded copy

Use case | Who | What they get back
Try action recognition online | Anyone curious | The class the model picks for a clip
Read a video model demo's code | Students | A short Python project built around one model

How to set it up:

• Nothing to install for the online version
• Python on your computer for a local copy
• The packages listed in requirements.txt

1. Install the Hugging Face hub package.
2. Download the Space's files to a folder.
3. Move into that folder.
4. Install gradio, then the packages from requirements.txt.
5. Start the app with app.py.

pip install -U huggingface_hub
hf download Sense-X/uniformer_video_demo --repo-type space --local-dir uniformer_video_demo
cd uniformer_video_demo
pip install gradio
pip install -r requirements.txt
python app.py

How to use it: Open the Space page in a browser and give it a clip, or pick one of the bundled examples. For a local copy, run the app and open the page Gradio opens for you.

python app.py

Tool | What it does
python app.py | Starts the Gradio app on your computer
hf download | Copies the Space's files into a local folder

Example: Open the Space and choose the bundled yoga clip. The app should return the class the UniFormer model picks for it. The page does not describe the output format, so check what the page shows.

For newcomers and experts: If you are new to this, start with one of the three bundled clips and watch what the page returns. Then try a short clip of your own.

If you know the field, the app names one model, Sense-X/uniformer_video, and ships a Kinetics class index with a transforms file next to the model code. The page does not state the model size or accuracy.

A clip goes in
Frames are prepared by transforms
The UniFormer model scores the clip
The class index maps scores to names

Good to know:

• The page gives no benchmark figures, so judge quality by trying your own clips.
• The online version needs nothing installed, and a local copy needs Python.
• License: mit.
• Cost to run: none named, only the packages in requirements.txt.
• Data it reaches: the clip you give it. On the hosted Space, that clip is handled on Hugging Face.
• Not for: the source names none.

On Hugging Face, 13 November 2026

• Likes: 2
• Built with: gradio
• License: mit

Links

• Space: https://huggingface.co/spaces/Sense-X/uniformer_video_demo
• Files: https://huggingface.co/spaces/Sense-X/uniformer_video_demo/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.