Xinggang Wang

verfied profile

∙ 0 followers
Huazhong University of Science u0026 Technology

Xinggang Wang is an Associate Professor in the School of Electronic Information and Communications in Huazhong University of Science and Technology

. His research interests are computer vision and machine learning, especially,

data/label- and computation-efficient deep learning for visual recognition
.

Featured Co-authors

Qi Tian
144 publications
Alan Yuille
130 publications
Philip H. S. Torr
130 publications
Xiang Bai
80 publications
Qian Zhang
78 publications
Lingxi Xie
78 publications
Yunchao Wei
64 publications
Serge Belongie
64 publications
Wenjun Zeng
64 publications
Jingdong Wang
63 publications
Bo Wang
61 publications

Tracking Instances as Queries

Recently, query based deep networks catch lots of attention owing to the...
06/22/2021 ∙ by Shusheng Yang, et al. ∙ 0 ∙ share

read it
You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection

Can Transformer perform 2D object-level recognition from a pure sequence...
06/01/2021 ∙ by Yuxin Fang, et al. ∙ 0 ∙ share

read it
MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens

Transformers have offered a new methodology of designing neural networks...
05/31/2021 ∙ by Jiemin Fang, et al. ∙ 0 ∙ share

read it
QueryInst: Parallelly Supervised Mask Query for Instance Segmentation

Recently, query based object detection frameworks achieve comparable per...
05/05/2021 ∙ by Yuxin Fang, et al. ∙ 6 ∙ share

read it
Crossover Learning for Fast Online Video Instance Segmentation

Modeling temporal visual context across frames is critical for video ins...
04/13/2021 ∙ by Shusheng Yang, et al. ∙ 0 ∙ share

read it
Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images

Humans have a strong class-agnostic object segmentation ability and can ...
04/04/2021 ∙ by Xinggang Wang, et al. ∙ 0 ∙ share

read it
Half-Real Half-Fake Distillation for Class-Incremental Semantic Segmentation

Despite their success for semantic segmentation, convolutional neural ne...
04/02/2021 ∙ by Zilong Huang, et al. ∙ 0 ∙ share

read it
Real-Time and Accurate Object Detection in Compressed Video by Long Short-term Feature Aggregation

Video object detection is a fundamental problem in computer vision and h...
03/25/2021 ∙ by Xinggang Wang, et al. ∙ 0 ∙ share

read it
Human De-occlusion: Invisible Perception and Recovery for Humans

In this paper, we tackle the problem of human de-occlusion which reasons...
03/22/2021 ∙ by Qiang Zhou, et al. ∙ 0 ∙ share

read it
Noise Modulation: Let Your Model Interpret Itself

Given the great success of Deep Neural Networks(DNNs) and the black-box ...
03/19/2021 ∙ by Haoyang Li, et al. ∙ 0 ∙ share

read it
Deep Online Correction for Monocular Visual Odometry

In this work, we propose a novel deep online correction (DOC) framework ...
03/18/2021 ∙ by Jiaxin Zhang, et al. ∙ 3 ∙ share

read it
Occluded Video Instance Segmentation

Can our video understanding systems perceive objects when a heavy occlus...
02/02/2021 ∙ by Jiyang Qi, et al. ∙ 12 ∙ share

read it
Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition

Deep networks can learn to accurately recognize objects of a category by...
01/13/2021 ∙ by Mengting Chen, et al. ∙ 0 ∙ share

read it
ResizeMix: Mixing Data with Preserved Object Information and True Labels

Data augmentation is a powerful technique to increase the diversity of d...
12/21/2020 ∙ by Jie Qin, et al. ∙ 12 ∙ share

read it
EfficientPose: Efficient Human Pose Estimation with Neural Architecture Search

Human pose estimation from image and video is a vital task in many multi...
12/13/2020 ∙ by Wenqiang Zhang, et al. ∙ 0 ∙ share

read it
Deep multi-metric learning for text-independent speaker verification

Text-independent speaker verification is an important artificial intelli...
07/17/2020 ∙ by Jiwei Xu, et al. ∙ 32 ∙ share

read it
Boundary-preserving Mask R-CNN

Tremendous efforts have been made to improve mask localization accuracy ...
07/17/2020 ∙ by Tianheng Cheng, et al. ∙ 23 ∙ share

read it
FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search

Deep neural networks achieve remarkable performance in many computer vis...
06/21/2020 ∙ by Jiemin Fang, et al. ∙ 2 ∙ share

read it
A Simple Baseline for Multi-Object Tracking

There has been remarkable progress on object detection and re-identifica...
04/04/2020 ∙ by Yifu Zhan, et al. ∙ 11 ∙ share

read it
Fast Neural Network Adaptation via Parameter Remapping and Architecture Search

Deep neural networks achieve remarkable performance in many computer vis...
01/08/2020 ∙ by Jiemin Fang, et al. ∙ 26 ∙ share

read it
Diversity Transfer Network for Few-Shot Learning

Few-shot learning is a challenging task that aims at training a classifi...
12/31/2019 ∙ by Mengting Chen, et al. ∙ 12 ∙ share

read it
IoU-aware Single-stage Object Detector for Accurate Localization

Due to the simpleness and high efficiency, single-stage object detectors...
12/12/2019 ∙ by Shengkai Wu, et al. ∙ 9 ∙ share

read it
Deep High-Resolution Representation Learning for Visual Recognition

High-resolution representations are essential for position-sensitive vis...
08/20/2019 ∙ by Jingdong Wang, et al. ∙ 0 ∙ share

read it
Object Detection in Video with Spatial-temporal Context Aggregation

Recent cutting-edge feature aggregation paradigms for video object detec...
07/11/2019 ∙ by Hao Luo, et al. ∙ 7 ∙ share

read it
Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation

Video object segmentation (VOS) aims at pixel-level object tracking give...
07/02/2019 ∙ by Qiang Zhou, et al. ∙ 4 ∙ share

read it
Densely Connected Search Space for More Flexible Neural Architecture Search

In recent years, neural architecture search (NAS) has dramatically advan...
06/23/2019 ∙ by Jiemin Fang, et al. ∙ 6 ∙ share

read it
High-Resolution Representations for Labeling Pixels and Regions

High-resolution representation learning plays an essential role in many ...
04/09/2019 ∙ by Ke Sun, et al. ∙ 6 ∙ share

read it
Reducing the dilution: An analysis of the information sensitiveness of capsule network with a practical solution

Capsule network has shown various advantages over convolutional neural n...
03/25/2019 ∙ by Zonglin Yang, et al. ∙ 2 ∙ share

read it
Reducing the Dilution: analysis of the information sensitiveness of capsule network and one practical solution

Capsule network has shown various advantages over convolutional neural n...
03/25/2019 ∙ by Zonglin Yang, et al. ∙ 2 ∙ share

read it
Direct Object Recognition Without Line-of-Sight Using Optical Coherence

Visual object recognition under situations in which the direct line-of-s...
03/18/2019 ∙ by Xin Lei, et al. ∙ 10 ∙ share

read it
Mask Scoring R-CNN

Letting a deep network be aware of the quality of its own predictions is...
03/01/2019 ∙ by Zhaojin Huang, et al. ∙ 12 ∙ share

read it
EAT-NAS: Elastic Architecture Transfer for Accelerating Large-scale Neural Architecture Search

Neural architecture search (NAS) methods have been proposed to release h...
01/17/2019 ∙ by Jiemin Fang, et al. ∙ 8 ∙ share

read it
CCNet: Criss-Cross Attention for Semantic Segmentation

Long-range dependencies can capture useful contextual information to ben...
11/28/2018 ∙ by Zilong Huang, et al. ∙ 6 ∙ share

read it
Detect or Track: Towards Cost-Effective Video Object Detection/Tracking

State-of-the-art object detectors and trackers are developing fast. Trac...
11/13/2018 ∙ by Hao Luo, et al. ∙ 6 ∙ share

read it
Reinforced Evolutionary Neural Architecture Search

Neural architecture search (NAS) is an important task in network design,...
08/01/2018 ∙ by Yukang Chen, et al. ∙ 0 ∙ share

read it
Unsupervised Domain Adaptive Re-Identification: Theory and Practice

We study the problem of unsupervised domain adaptive re-identification (...
07/30/2018 ∙ by Liangchen Song, et al. ∙ 4 ∙ share

read it
PCL: Proposal Cluster Learning for Weakly Supervised Object Detection

Weakly Supervised Object Detection (WSOD), using only image-level annota...
07/09/2018 ∙ by Peng Tang, et al. ∙ 0 ∙ share

read it
Object Detection in Videos by Short and Long Range Object Linking

We address the problem of detecting objects in videos with the interest ...
01/30/2018 ∙ by Peng Tang, et al. ∙ 0 ∙ share

read it
Point Linking Network for Object Detection

Object detection is a core problem in computer vision. With the developm...
06/12/2017 ∙ by Xinggang Wang, et al. ∙ 0 ∙ share

read it
Deep Patch Learning for Weakly Supervised Object Classification and Discovery

Patch-level image representation is very important for object classifica...
05/06/2017 ∙ by Peng Tang, et al. ∙ 0 ∙ share

read it
Multiple Instance Detection Network with Online Instance Classifier Refinement

Of late, weakly supervised object detection is with great importance in ...
04/01/2017 ∙ by Peng Tang, et al. ∙ 0 ∙ share

read it
TextBoxes: A Fast Text Detector with a Single Deep Neural Network

This paper presents an end-to-end trainable fast scene text detector, na...
11/21/2016 ∙ by Minghui Liao, et al. ∙ 0 ∙ share

read it
Revisiting Multiple Instance Neural Networks

Recently neural networks and multiple instance learning are both attract...
10/08/2016 ∙ by Xinggang Wang, et al. ∙ 0 ∙ share

read it
Deep FisherNet for Object Classification

Despite the great success of convolutional neural networks (CNN) for the...
07/31/2016 ∙ by Peng Tang, et al. ∙ 0 ∙ share

read it
Shape Recognition by Bag of Skeleton-associated Contour Parts

Contour and skeleton are two complementary representations for shape rec...
05/20/2016 ∙ by Wei Shen, et al. ∙ 0 ∙ share

read it
Robust Scene Text Recognition with Automatic Rectification

Recognizing text in natural images is a challenging task with many unsol...
03/12/2016 ∙ by Baoguang Shi, et al. ∙ 0 ∙ share

read it
Bag Reference Vector for Multi-instance Learning

Multi-instance learning (MIL) has a wide range of applications due to it...
12/03/2015 ∙ by Hanqiang Song, et al. ∙ 0 ∙ share

read it
Relaxed Multiple-Instance SVM with Application to Object Discovery

Multiple-instance learning (MIL) has served as an important tool for a w...
10/05/2015 ∙ by Xinggang Wang, et al. ∙ 0 ∙ share

read it
Deep Learning Representation using Autoencoder for 3D Shape Retrieval

We study the problem of how to build a deep learning representation for ...
09/25/2014 ∙ by Zhuotun Zhu, et al. ∙ 0 ∙ share

read it