Hugging Face's logo

SitongGong
/
VRS-HQ

Image Segmentation
PyTorch
ChatUniVi
Model card Files
xet
Community
1

The Devil is in Temporal Token: High Quality Video Reasoning Segmentation

Sitong Gong 1  Yunzhi Zhuge 1  Lu Zhang 1  Zongxin Yang 2  Pingping Zhang 1  Huchuan Lu 1 

CVPR 2025

1 Dalian University of Technology   2 Havard University 

arXiv

You can find the code at: https://github.com/SitongGong/VRS-HQ

Downloads last month
8
Inference Providers NEW
Image Segmentation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for SitongGong/VRS-HQ

Base model

Chat-UniVi/Chat-UniVi
Finetuned
(1)
this model

Paper for SitongGong/VRS-HQ