activity
20172022
most citedLearning Spatial Fusion for Single-Shot Object Detection

473 citations · 533 across the 12 of their papers we have counts for

collaborators

14 papers

cs.CV20211 cited

iDARTS: Improving DARTS by Node Normalization and Decorrelation Discretization

Huiqun Wang, Ruijie Yang, Di Huang +1

Differentiable ARchiTecture Search (DARTS) uses a continuous relaxation of network representation and dramatically accelerates Neural Architecture Search (NAS) by almost thousands…

cs.CV20212 cited

Weakly-Supervised Photo-realistic Texture Generation for 3D Face Reconstruction

Xiangnan Yin, Di Huang, Zehua Fu +2

Although much progress has been made recently in 3D face reconstruction, most previous work has been devoted to predicting accurate and fine-grained 3D shapes. In contrast, relativ…

cs.CV20211 cited

Pixel Sampling for Style Preserving Face Pose Editing

Xiangnan Yin, Di Huang, Hongyu Yang +3

The existing auto-encoder based face pose editing methods primarily focus on modeling the identity preserving ability during pose synthesis, but are less able to preserve the image…

cs.CV2021

Magnifying Subtle Facial Motions for Effective 4D Expression Recognition

Qingkai Zhen, Di Huang, Yunhong Wang +3

In this paper, an effective pipeline to automatic 4D Facial Expression Recognition (4D FER) is proposed. It combines two growing but disparate ideas in Computer Vision -- computing…

cs.CV20202 cited

PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection

Yanan Zhang, Di Huang, Yunhong Wang

LiDAR-based 3D object detection is an important task for autonomous driving and current approaches suffer from sparse and partial point clouds of distant and occluded objects. In t…

cs.CV2020

MRDet: A Multi-Head Network for Accurate Oriented Object Detection in Aerial Images

Ran Qin, Qingjie Liu, Guangshuai Gao +2

Objects in aerial images usually have arbitrary orientations and are densely located over the ground, making them extremely challenge to be detected. Many recently developed method…