Xiaogang Wang

is this you? claim profile

∙ 0 followers
SenseTime Corporation ∙ National University of Singapore ∙ Beihang University ∙ The Chinese University of Hong Kong

Associate Professor of Electronic Engineering at The Chinese University of Hongkong

Semantic Scene Completion via Integrating Instances and Scene in-the-Loop

Semantic Scene Completion aims at reconstructing a complete 3D scene wit...
04/08/2021 ∙ by Yingjie Cai, et al. ∙ 0 ∙ share

read it
Fixing the Teacher-Student Knowledge Discrepancy in Distillation

Training a small student network with the guidance of a larger teacher n...
03/31/2021 ∙ by Jiangfan Han, et al. ∙ 0 ∙ share

read it
Learning Fine-Grained Segmentation of 3D Shapes without Part Labels

Learning-based 3D shape segmentation is usually formulated as a semantic...
03/24/2021 ∙ by Xiaogang Wang, et al. ∙ 0 ∙ share

read it
DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network

Conditional generative adversarial networks (cGANs) target at synthesizi...
03/14/2021 ∙ by Rui Liu, et al. ∙ 4 ∙ share

read it
PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection

3D object detection is receiving increasing attention from both industry...
01/31/2021 ∙ by Shaoshuai Shi, et al. ∙ 5 ∙ share

read it
Fast Convergence of DETR with Spatially Modulated Co-Attention

The recently proposed Detection Transformer (DETR) model successfully ap...
01/19/2021 ∙ by Peng Gao, et al. ∙ 8 ∙ share

read it
Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Prediction

Multi-scale representations deeply learned via convolutional neural netw...
01/08/2021 ∙ by Dan Xu, et al. ∙ 17 ∙ share

read it
A Holistically-Guided Decoder for Deep Representation Learning with Applications to Semantic Segmentation and Object Detection

Both high-level and high-resolution feature representations are of great...
12/18/2020 ∙ by Jianbo Liu, et al. ∙ 0 ∙ share

read it
End-to-End Object Detection with Adaptive Clustering Transformer

End-to-end Object Detection with Transformer (DETR)proposes to perform o...
11/18/2020 ∙ by Minghang Zheng, et al. ∙ 0 ∙ share

read it
A Self-supervised Cascaded Refinement Network for Point Cloud Completion

Point clouds are often sparse and incomplete, which imposes difficulties...
10/17/2020 ∙ by Xiaogang Wang, et al. ∙ 0 ∙ share

read it
Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation

We propose a general framework for searching surrogate losses for mainst...
10/15/2020 ∙ by Hao Li, et al. ∙ 10 ∙ share

read it
Deformable DETR: Deformable Transformers for End-to-End Object Detection

DETR has been recently proposed to eliminate the need for many hand-desi...
10/08/2020 ∙ by Xizhou Zhu, et al. ∙ 10 ∙ share

read it
Open-Edit: Open-Domain Image Manipulation with Open-Vocabulary Instructions

We propose a novel algorithm, named Open-Edit, which is the first attemp...
08/04/2020 ∙ by Xihui Liu, et al. ∙ 13 ∙ share

read it
Point Cloud Completion by Learning Shape Priors

In view of the difficulty in reconstructing object details in point clou...
08/02/2020 ∙ by Xiaogang Wang, et al. ∙ 0 ∙ share

read it
Gradient Regularized Contrastive Learning for Continual Domain Adaptation

Human beings can quickly adapt to environmental changes by leveraging le...
07/25/2020 ∙ by Peng Su, et al. ∙ 0 ∙ share

read it
Sep-Stereo: Visually Guided Stereophonic Audio Generation by Associating Source Separation

Stereophonic audio is an indispensable ingredient to enhance human audit...
07/20/2020 ∙ by Hang Zhou, et al. ∙ 7 ∙ share

read it
3D Human Mesh Regression with Dense Correspondence

Estimating 3D mesh of the human body from a single 2D image is an import...
06/10/2020 ∙ by Wang Zeng, et al. ∙ 0 ∙ share

read it
StereoGAN: Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain Translation and Stereo Matching

Large-scale synthetic datasets are beneficial to stereo matching but usu...
05/05/2020 ∙ by Rui Liu, et al. ∙ 7 ∙ share

read it
Cascaded Refinement Network for Point Cloud Completion

Point clouds are often sparse and incomplete. Existing shape completion ...
04/07/2020 ∙ by Xiaogang Wang, et al. ∙ 0 ∙ share

read it
1st Place Solutions for OpenImage2019 – Object Detection and Instance Segmentation

This article introduces the solutions of the two champion teams, `MMfrui...
03/17/2020 ∙ by Yu Liu, et al. ∙ 7 ∙ share

read it
KPNet: Towards Minimal Face Detector

The small receptive field and capacity of minimal neural networks limit ...
03/17/2020 ∙ by Guanglu Song, et al. ∙ 7 ∙ share

read it
Revisiting the Sibling Head in Object Detector

The “shared head for classification and localization” (sibling head), fi...
03/17/2020 ∙ by Guanglu Song, et al. ∙ 0 ∙ share

read it
Adapting Object Detectors with Conditional Domain Normalization

Real-world object detectors are often challenged by the domain gaps betw...
03/16/2020 ∙ by Peng Su, et al. ∙ 5 ∙ share

read it
Channel Equilibrium Networks for Learning Deep Representation

Convolutional Neural Networks (CNNs) are typically constructed by stacki...
02/29/2020 ∙ by Wenqi Shao, et al. ∙ 0 ∙ share

read it
Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimation

Monocular 3D object detection task aims to predict the 3D bounding boxes...
02/05/2020 ∙ by Yingjie Cai, et al. ∙ 23 ∙ share

read it
Single Image Dehazing Using Ranking Convolutional Neural Network

Single image dehazing, which aims to recover the clear image solely from...
01/15/2020 ∙ by Yafei Song, et al. ∙ 0 ∙ share

read it
PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

We present a novel and high-performance 3D object detection framework, n...
12/31/2019 ∙ by Shaoshuai Shi, et al. ∙ 0 ∙ share

read it
Search to Distill: Pearls are Everywhere but not the Eyes

Standard Knowledge Distillation (KD) approaches distill the knowledge of...
11/20/2019 ∙ by Yu Liu, et al. ∙ 0 ∙ share

read it
Fetal cardiovascular decompensation during labor predicted from the individual heart rate: a prospective study in fetal sheep near term and the impact of low sampling rate

We present a novel computerized fetal heart rate intrapartum algorithm f...
11/04/2019 ∙ by Nathan Gold, et al. ∙ 0 ∙ share

read it
Vision-Infused Deep Audio Inpainting

Multi-modality perception is essential to develop interactive intelligen...
10/24/2019 ∙ by Hang Zhou, et al. ∙ 17 ∙ share

read it
Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis

Semantic image synthesis aims at generating photorealistic images from s...
10/15/2019 ∙ by Xihui Liu, et al. ∙ 33 ∙ share

read it
CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval

Text-image cross-modal retrieval is a challenging task in the field of l...
09/12/2019 ∙ by Zihao Wang, et al. ∙ 0 ∙ share

read it
Differentiable Learning-to-Group Channels via Groupable Convolutional Neural Networks

Group convolution, which divides the channels of ConvNets into groups, h...
08/16/2019 ∙ by Zhaoyang Zhang, et al. ∙ 0 ∙ share

read it
Differentiable Learning-to-Group Channels viaGroupable Convolutional Neural Networks

Group convolution, which divides the channels of ConvNets into groups, h...
08/16/2019 ∙ by Zhaoyang Zhang, et al. ∙ 0 ∙ share

read it
Once a MAN: Towards Multi-Target Attack via Learning Multi-Target Adversarial Network Once

Modern deep neural networks are often vulnerable to adversarial samples....
08/14/2019 ∙ by Jiangfan Han, et al. ∙ 9 ∙ share

read it
Interpolated Convolutional Networks for 3D Point Cloud Understanding

Point cloud is an important type of 3D representation. However, directly...
08/13/2019 ∙ by Jiageng Mao, et al. ∙ 4 ∙ share

read it
Multi-modality Latent Interaction Network for Visual Question Answering

Exploiting relationships between visual regions and question words have ...
08/10/2019 ∙ by Peng Gao, et al. ∙ 14 ∙ share

read it
Deep Self-Learning From Noisy Labels

ConvNets achieve good results when training from clean data, but learnin...
08/06/2019 ∙ by Jiangfan Han, et al. ∙ 16 ∙ share

read it
Part-A^2 Net: 3D Part-Aware and Aggregation Neural Network for Object Detection from Point Cloud

In this paper, we propose the part-aware and aggregation neural network ...
07/08/2019 ∙ by Shaoshuai Shi, et al. ∙ 0 ∙ share

read it
Finding Task-Relevant Features for Few-Shot Learning by Category Traversal

Few-shot learning is an important area of research. Conceptually, humans...
05/27/2019 ∙ by Hongyang Li, et al. ∙ 0 ∙ share

read it
P2SGrad: Refined Gradients for Optimizing Deep Face Models

Cosine-based softmax losses significantly improve the performance of dee...
05/07/2019 ∙ by Xiao Zhang, et al. ∙ 14 ∙ share

read it
PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graph

Despite some exciting progress on high-quality image generation from str...
05/05/2019 ∙ by Yikang Li, et al. ∙ 0 ∙ share

read it
AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations

The cosine-based softmax losses and their variants achieve great success...
05/01/2019 ∙ by Xiao Zhang, et al. ∙ 0 ∙ share

read it
Disentangling Pose from Appearance in Monochrome Hand Images

Hand pose estimation from the monocular 2D image is challenging due to t...
04/16/2019 ∙ by Yikang Li, et al. ∙ 6 ∙ share

read it
Conditional Adversarial Generative Flow for Controllable Image Synthesis

Flow-based generative models show great potential in image synthesis due...
04/03/2019 ∙ by Rui Liu, et al. ∙ 0 ∙ share

read it
Semantics Disentangling for Text-to-Image Generation

Synthesizing photo-realistic images from text descriptions is a challeng...
04/02/2019 ∙ by Guojun Yin, et al. ∙ 0 ∙ share

read it
Context and Attribute Grounded Dense Captioning

Dense captioning aims at simultaneously localizing semantic regions and ...
04/02/2019 ∙ by Guojun Yin, et al. ∙ 0 ∙ share

read it
Feature Intertwiner for Object Detection

A well-trained model should classify objects with a unanimous score for ...
03/28/2019 ∙ by Hongyang Li, et al. ∙ 0 ∙ share

read it
GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving

We present an efficient 3D object detection framework based on a single ...
03/26/2019 ∙ by Buyu Li, et al. ∙ 0 ∙ share

read it
Video Generation from Single Semantic Label Map

This paper proposes the novel task of video generation conditioned on a ...
03/11/2019 ∙ by Junting Pan, et al. ∙ 16 ∙ share

read it

Xiaogang Wang

Featured Co-authors