videomt-dinov2-large-ovis – AI Model by tue-mps | AlphaNeural AI

You can deploy this model and start earning money today!

tue-mps/
videomt-dinov2-large-ovis

like

0

video-segmentation

video-instance-segmentation

image-segmentation

endpoints_compatible

Views

No views yet

VidEoMT-L on OVIS

This repository contains the Hugging Face Transformers conversion of the official VidEoMT checkpoint ovis_vit_large_52.5.pth from tue-mps/VidEoMT.

Model details

Reported metrics

Metric	Value
AP	52.5
AR@10	57.5
FPS	115

The metrics above are the numbers reported by the authors in the official model zoo.

Usage

python

from transformers import AutoModelForUniversalSegmentation, AutoVideoProcessor

model_id = "tue-mps/videomt-dinov2-large-ovis"
processor = AutoVideoProcessor.from_pretrained(model_id)
model = AutoModelForUniversalSegmentation.from_pretrained(model_id)

Use processor.post_process_instance_segmentation, processor.post_process_panoptic_segmentation, or processor.post_process_semantic_segmentation depending on the target task.