# Advanced Inference Usage
`apply_model()` isn’t limited to the task types covered above. It stores
whatever [`Label`](../../api/fiftyone.core.labels.md#fiftyone.core.labels.Label) your model returns, including [`Regression`](../../api/fiftyone.core.labels.md#fiftyone.core.labels.Regression) values,
[`Polylines`](../../api/fiftyone.core.labels.md#fiftyone.core.labels.Polylines), [`TemporalDetections`](../../api/fiftyone.core.labels.md#fiftyone.core.labels.TemporalDetections) for video-level events, and [`GeoLocation`](../../api/fiftyone.core.labels.md#fiftyone.core.labels.GeoLocation)
data. These have fewer end-to-end guides today, so search the
[Model Zoo catalog](../../model_zoo/index.md#model-zoo) (for example, by the `video` or `3d`
tags) to find a model for one of these tasks, or implement a custom
[`Model`](../../api/fiftyone.core.models.md#fiftyone.core.models.Model) that returns the label type you
need.
## Sharing a custom model
Once you have a custom model working, you can
[register it as a remotely-sourced zoo model](../../model_zoo/remote.md#model-zoo-remote) so that
it can be loaded and applied just like a built-in model:
```python
model = foz.load_zoo_model("your-custom-model")
dataset.apply_model(model, label_field="predictions")
```
#### NOTE
Framework-specific examples are also available for
[Hugging Face](../../integrations/huggingface.md#huggingface-integration),
[Ultralytics](../../integrations/ultralytics.md#ultralytics-integration), and
[PyTorch Hub](../../integrations/pytorch_hub.md#pytorch-hub-integration) models.