8000 GitHub - yuggiehk/CaRe-Ego: The official implement of ORMNet: Object-centric Relationship Modeling for Egocentric Hand-object Segmentation
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

The official implement of ORMNet: Object-centric Relationship Modeling for Egocentric Hand-object Segmentation

Notifications You must be signed in to change notification settings

yuggiehk/CaRe-Ego

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

46 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CaRe-Ego

CaRe-Ego: Contact-aware Relationship Modeling for Egocentric Interactive Hand-object Segmentation

Yuejiao Su, Yi Wang, and Lap-Pui Chau

Qualitative Results

Comparison results on the EgoHOS in-domain test set.

My Image

Comparison results on the EgoHOS out-of-domain test set.

My Image

Comparison results on the out-of-distribution mini-HOI4D dataset. The dataset of mini-HOI4D will be released soon.

My Image

Quantitative Results

Comparison results on the EgoHOS in-domain test set measured by IoU/Acc and mIoU/mAcc. 1

Comparison results on the EgoHOS out-of-domain test set measured by IoU/Acc and mIoU/mAcc. 图片_20240718105915

Comparison results on the mini-HOI4D test set measured by IoU/Acc and mIoU/mAcc. 图片_20240718105954

Video Demonstrations

Although the CaRe-Ego is performed on Egocentric images, we can validate it on out-of-distribution videos frame-by-frame.

My Image
My Image
My Image
My Image

Acknowledgements

The research work was conducted in the JC STEM Lab of Machine Learning and Computer Vision funded by The Hong Kong Jockey Club Charities Trust.

The code of the CaRe-Ego is built upon the MMsegmentation codebase, thanks for their work.

About

The official implement of ORMNet: Object-centric Relationship Modeling for Egocentric Hand-object Segmentation

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

0