AI Radar
Support
LiveUpdated 2026-09-19 21:10 UTC

sid2697.github.io

sid2697.github.io is Project page for Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation, introducing EPIC-Contact and HOPformer.. It is ranked #620 on the AI Radar, in AI research, first seen 9 days ago and shared in 2 posts (13.7k views).

Visit sid2697.github.io

Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation EPIC-Contact + HOPformer Siddhant Bansal 1 , Zhifan Zhu 1 , Shashank Tripathi 2 , Jiahe Zhao 1 , Michael Black 2 , Dima Damen 1 1 University of Bristol 2 Max Planck Institute for Intelligent Systems ECCV 2026 TL;DR We tackle 3D hand–object pose estimation in unconstrained, cluttered, occluded egocentric video. We contribute EPIC-Contact , an in-the-wild dataset with dense 3D hand–object contact, and HOPformer , a transformer that conditions object pose on strong hand priors to predict both hands and the object in a…

What people said about sid2697.github.io on X

Today at ECCV: Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation, ExHall Poster: #70, PM CEST, Poster Session 2. * 3D hand–object pose estimation in unconstrained, cluttered, occluded egocentric video * EPIC-Contact, an in-the-wild dataset with dense 3D hand–object contact * HOPformer, a transformer that…

@Michael_J_Black, 9 days ago · 104 likes · see the post

One thing off my professional bucket-list, To co-author a paper with @Michael_J_Black 🥰 Thanks @Sid__Bansal @zhifan_zhu @sha2nk_t @terry_jhzhao00 for helping make this happen,

@dimadamen, 9 days ago · 33 likes · see the post

Alternatives to sid2697.github.io

sid2697.github.io in numbers

FAQ

What is sid2697.github.io?

Project page for Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation, introducing EPIC-Contact and HOPformer. It was first shared on X 9 days ago and is ranked #620 on the AI Radar.

Is sid2697.github.io free?

Yes, it is free to use.

Who shared sid2697.github.io?

2 accounts on X, including @Michael_J_Black, @dimadamen, in 2 posts totalling 13.7k views.

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 31.3k posts from 4.7k X accounts over the last 14 days, 1.3k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 21:10 UTC. Full method.