473 citations · 764 across the 20 of their papers we have counts for
20 papers
Denoising Diffusion Autoencoders are Unified Self-supervised Learners
Weilai Xiang, Hongyu Yang, Di Huang +1
Inspired by recent advances in diffusion models, which are reminiscent of denoising autoencoders, we investigate whether they can acquire discriminative representations for classif…
ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representations
Mingwu Zheng, Hongyu Yang, Di Huang +1
Precise representations of 3D faces are beneficial to various computer vision and graphics applications. Due to the data discretization and model linearity, however, it remains cha…
Segmentation-Reconstruction-Guided Facial Image De-occlusion
Xiangnan Yin, Di Huang, Zehua Fu +2
Occlusions are very common in face images in the wild, leading to the degraded performance of face-related tasks. Although much effort has been devoted to removing occlusions from…
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…
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…
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…
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…
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…
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…
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
Jiaxi Wu, Songtao Liu, Di Huang +1
Few-shot object detection (FSOD) helps detectors adapt to unseen classes with few training instances, and is useful when manual annotation is time-consuming or data acquisition is…
Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation
Yangtao Zheng, Di Huang, Songtao Liu +1
Recent years have witnessed great progress in deep learning based object detection. However, due to the domain shift problem, applying off-the-shelf detectors to an unseen domain l…
A Feasible Framework for Arbitrary-Shaped Scene Text Recognition
Jinjin Zhang, Wei Wang, Di Huang +2
Deep learning based methods have achieved surprising progress in Scene Text Recognition (STR), one of classic problems in computer vision. In this paper, we propose a feasible fram…
Distraction-Aware Feature Learning for Human Attribute Recognition via Coarse-to-Fine Attention Mechanism
Mingda Wu, Di Huang, Yuanfang Guo +1
Recently, Human Attribute Recognition (HAR) has become a hot topic due to its scientific challenges and application potentials, where localizing attributes is a crucial stage but n…
Learning Spatial Fusion for Single-Shot Object Detection
Songtao Liu, Di Huang, Yunhong Wang
Pyramidal feature representation is the common practice to address the challenge of scale variation in object detection. However, the inconsistency across different feature scales…
Adaptive NMS: Refining Pedestrian Detection in a Crowd
Songtao Liu, Di Huang, Yunhong Wang
Pedestrian detection in a crowd is a very challenging issue. This paper addresses this problem by a novel Non-Maximum Suppression (NMS) algorithm to better refine the bounding boxe…
Learning Continuous Face Age Progression: A Pyramid of GANs
Hongyu Yang, Di Huang, Yunhong Wang +1
The two underlying requirements of face age progression, i.e. aging accuracy and identity permanence, are not well studied in the literature. This paper presents a novel generative…
Feature Map Pooling for Cross-View Gait Recognition Based on Silhouette Sequence Images
Qiang Chen, Yunhong Wang, Zheng Liu +2
In this paper, we develop a novel convolutional neural network based approach to extract and aggregate useful information from gait silhouette sequence images instead of simply rep…
Learning Face Age Progression: A Pyramid Architecture of GANs
Hongyu Yang, Di Huang, Yunhong Wang +1
The two underlying requirements of face age progression, i.e. aging accuracy and identity permanence, are not well studied in the literature. In this paper, we present a novel gene…
Receptive Field Block Net for Accurate and Fast Object Detection
Songtao Liu, Di Huang, Yunhong Wang
Current top-performing object detectors depend on deep CNN backbones, such as ResNet-101 and Inception, benefiting from their powerful feature representations but suffering from hi…
Face Aging Effect Simulation using Hidden Factor Analysis Joint Sparse Representation
Hongyu Yang, Di Huang, Yunhong Wang +2
Face aging simulation has received rising investigations nowadays, whereas it still remains a challenge to generate convincing and natural age-progressed face images. In this paper…