activity
20192022
most citedRethinking on Multi-Stage Networks for Human Pose Estimation

109 citations · 123 across the 6 of their papers we have counts for

collaborators

9 papers

cs.RO2022

Multi-Finger Grasping Like Humans

Yuming Du, Philippe Weinzaepfel, Vincent Lepetit +1

Robots with multi-fingered grippers could perform advanced manipulation tasks for us if we were able to properly specify to them what to do. In this study, we take a step in that d…

cs.CV2022

A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation

Georgy Ponimatkin, Nermin Samet, Yang Xiao +3

We propose a simple, yet powerful approach for unsupervised object segmentation in videos. We introduce an objective function whose minimum represents the mask of the main salient…

cs.CV20229 cited

PIZZA: A Powerful Image-only Zero-Shot Zero-CAD Approach to 6 DoF Tracking

Van Nguyen Nguyen, Yuming Du, Yang Xiao +2

Estimating the relative pose of a new object without prior knowledge is a hard problem, while it is an ability very much needed in robotics and Augmented Reality. We present a meth…

cs.CV2021

UVO Challenge on Video-based Open-World Segmentation 2021: 1st Place Solution

Yuming Du, Wen Guo, Yang Xiao +1

In this report, we introduce our (pretty straightforard) two-step "detect-then-match" video instance segmentation method. The first step performs instance segmentation for each fra…

cs.CV20215 cited

1st Place Solution for the UVO Challenge on Image-based Open-World Segmentation 2021

Yuming Du, Wen Guo, Yang Xiao +1

We describe our two-stage instance segmentation framework we use to compete in the challenge. The first stage of our framework consists of an object detector, which generates objec…

cs.CV2021

PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning

Yang Xiao, Yuming Du, Renaud Marlet

Motivated by the need for estimating the 3D pose of arbitrary objects, we consider the challenging problem of class-agnostic object viewpoint estimation from images only, without C…