activity
20162023
most citedVisual Relationship Detection with Language Priors

111 citations · 157 across the 12 of their papers we have counts for

collaborators
Showing cs.CVShow all

12 papers · 1 filter

cs.CV20232 cited

POEM: Reconstructing Hand in a Point Embedded Multi-view Stereo

Lixin Yang, Jian Xu, Licheng Zhong +4

Enable neural networks to capture 3D geometrical-aware features is essential in multi-view based vision tasks. Previous methods usually encode the 3D information of multi-view ster…

cs.CV20234 cited

NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation

Jiefeng Li, Siyuan Bian, Qi Liu +3

With the progress of 3D human pose and shape estimation, state-of-the-art methods can either be robust to occlusions or obtain pixel-aligned accuracy in non-occlusion cases. Howeve…

cs.CV202315 cited

HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery

Jiefeng Li, Siyuan Bian, Chao Xu +3

Recovering whole-body mesh by inferring the abstract pose and shape parameters from visual content can obtain 3D bodies with realistic structures. However, the inferring process is…

cs.CV2023

CRIN: Rotation-Invariant Point Cloud Analysis and Rotation Estimation via Centrifugal Reference Frame

Yujing Lou, Zelin Ye, Yang You +5

Various recent methods attempt to implement rotation-invariant 3D deep learning by replacing the input coordinates of points with relative distances and angles. Due to the incomple…

cs.CV20221 cited

Constructing Balance from Imbalance for Long-tailed Image Recognition

Yue Xu, Yong-Lu Li, Jiefeng Li +1

Long-tailed image recognition presents massive challenges to deep learning systems since the imbalance between majority (head) classes and minority (tail) classes severely skews th…

cs.CV20222 cited

Unsupervised Visual Representation Learning by Synchronous Momentum Grouping

Bo Pang, Yifan Zhang, Yaoyi Li +2

In this paper, we propose a genuine group-level contrastive visual representation learning method whose linear evaluation performance on ImageNet surpasses the vanilla supervised l…