Dong Xu

Dong Xu

Auto-generated profile, based on publicly available information

Dong Xu

University of Hong Kong, Hong Kong, Hong Kong

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 October 2018 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
CZChangqing Zhang
Changqing Zhang
HFHuazhu Fu
Huazhu Fu
QHQinghua Hu
Qinghua Hu
XCXiaochun Cao
Xiaochun Cao
YXYuan Xie
Yuan Xie
DXDong Xu
Dong Xu
Subspace clustering is an effective method that has been successfully applied to many applications. Here we propose a novel subspace clustering model for multi-view data using a latent representation termed Latent Multi-View Subspace Clustering (LMSC). Unlike most existing single-view subspace clustering methods, which directly reconstruct data points using original features, our method explores underlying complementary information from multiple views and simultaneously seeks the underlying latent representation. Using the complementarity of multiple views, the latent representation depicts data more comprehensively than each individual view, accordingly making subspace representation more accurate and robust. We proposed two LMSC formulations: linear LMSC (lLMSC), based on linear correlations between latent representation and each view, and generalized LMSC (gLMSC), based on neural networks to handle general relationships. The proposed method can be efficiently optimized under the Augmented Lagrangian Multiplier with Alternating Direction Minimization (ALM-ADM) framework. Extensive experiments on diverse datasets demonstrate the effectiveness of the proposed method.

10 January 2018 in IEEE Signal Processing Magazine
Verified
Journal Article
Closed access
JHJunwei Han
Junwei Han
DZDingwen Zhang
Dingwen Zhang
GCGong Cheng
Gong Cheng
NLNian Liu
Nian Liu
DXDong Xu
Dong Xu
Object detection, including objectness detection (OD), salient object detection (SOD), and category-specific object detection (COD), is one of the most fundamental yet challenging problems in the computer vision community. Over the last several decades, great efforts have been made by researchers to tackle this problem, due to its broad range of applications for other computer vision tasks such as activity or event recognition, content-based image retrieval and scene understanding, etc. While numerous methods have been presented in recent years, a comprehensive review for the proposed high-quality object detection techniques, especially for those based on advanced deep-learning techniques, is still lacking. To this end, this article delves into the recent progress in this research field, including 1) definitions, motivations, and tasks of each subdirection; 2) modern techniques and essential research trends; 3) benchmark data sets and evaluation metrics; and 4) comparisons and analysis of the experimental results. More importantly, we will reveal the underlying relationship among OD, SOD, and COD and discuss in detail some open questions as well as point out several unsolved challenges and promising future works.

9 November 2017 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
JLJared Liu
Jared Liu
ASAmir Shahroudy
Amir Shahroudy
DXDong Xu
Dong Xu
AKAlex C. Kot
Alex C. Kot
GWGang Wang
Gang Wang
Skeleton-based human action recognition has attracted a lot of research attention during the past few years. Recent works attempted to utilize recurrent neural networks to model the temporal dependencies between the 3D positional configurations of human body joints for better analysis of human activities in the skeletal data. The proposed work extends this idea to spatial domain as well as temporal domain to better analyze the hidden sources of action-related information within the human skeleton sequences in both of these domains simultaneously. Based on the pictorial structure of Kinect's skeletal data, an effective tree-structure based traversal framework is also proposed. In order to deal with the noise in the skeletal data, a new gating mechanism within LSTM module is introduced, with which the network can learn the reliability of the sequential data and accordingly adjust the effect of the input data on the updating procedure of the long-term context representation stored in the unit's memory cell. Moreover, we introduce a novel multi-modal feature fusion strategy within the LSTM unit in this paper. The comprehensive experimental results on seven challenging benchmark datasets for human action recognition demonstrate the effectiveness of the proposed method.

24 August 2018 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
GCGong Cheng
Gong Cheng
JHJunwei Han
Junwei Han
PZPeicheng Zhou
Peicheng Zhou
DXDong Xu
Dong Xu
The performance of object detection has recently been significantly improved due to the powerful features learnt through convolutional neural networks (CNNs). Despite the remarkable success, there are still several major challenges in object detection, including object rotation, within-class diversity, and between-class similarity, which generally degenerate object detection performance. To address these issues, we build up the existing state-of-the-art object detection systems and propose a simple but effective method to train rotation-invariant and Fisher discriminative CNN models to further boost object detection performance. This is achieved by optimizing a new objective function that explicitly imposes a rotation-invariant regularizer and a Fisher discrimination regularizer on the CNN features. Specifically, the first regularizer enforces the CNN feature representations of the training samples before and after rotation to be mapped closely to each other in order to achieve rotation-invariance. The second regularizer constrains the CNN features to have small within-class scatter but large between-class separation. We implement our proposed method under four popular object detection frameworks, including region-CNN (R-CNN), Fast R- CNN, Faster R- CNN, and R- FCN. In the experiments, we comprehensively evaluate the proposed method on the PASCAL VOC 2007 and 2012 data sets and a publicly available aerial image data set. Our proposed methods outperform the existing baseline methods and achieve the state-of-the-art results.

20 April 2020 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
GLGuo Lu
Guo Lu
XZXiaoyun Zhang
Xiaoyun Zhang
WOWanli Ouyang
Wanli Ouyang
LCLi Chen
Li Chen
ZGZhiyong Gao
Zhiyong Gao
DXDong Xu
Dong Xu
Traditional video compression approaches build upon the hybrid coding framework with motion-compensated prediction and residual transform coding. In this paper, taking advantage of both the classical compression architecture and the powerful non-linear representation ability of neural networks, we propose the first end-to-end deep video compression framework. Our framework employs pixel-wise motion information, which is learned from an optical flow network and further compressed by an auto-encoder network to save bits. The other compression components are also implemented by well-designed networks for high efficiency. All the modules are jointly optimized by using the rate-distortion trade-off and collaborate with each other. More importantly, the proposed deep video compression framework is very flexible and can be easily extended by using lightweight or advanced networks for higher speed or better efficiency. Experimental results show that the proposed approach can outperform the widely used video coding standard H.264 and be even on par with the latest standard H.265.

15 October 2007 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
DXDong Xu
Dong Xu
SYShuicheng Yan
Shuicheng Yan
DTDacheng Tao
Dacheng Tao
SLStephen Lin
Stephen Lin
HZHong-Jiang Zhang
Hong-Jiang Zhang
Dimensionality reduction algorithms, which aim to select a small set of efficient and discriminant features, have attracted great attention for human gait recognition and content-based image retrieval (CBIR). In this paper, we present extensions of our recently proposed marginal Fisher analysis (MFA) to address these problems. For human gait recognition, we first present a direct application of MFA, then inspired by recent advances in matrix and tensor-based dimensionality reduction algorithms, we present matrix-based MFA for directly handling 2-D input in the form of gray-level averaged images. For CBIR, we deal with the relevance feedback problem by extending MFA to marginal biased analysis, in which within-class compactness is characterized only by the distances between each positive sample and its neighboring positive samples. In addition, we present a new technique to acquire a direct optimal solution for MFA without resorting to objective function modification as done in many previous algorithms. We conduct comprehensive experiments on the USF HumanID gait database and the Corel image retrieval database. Experimental results demonstrate that MFA and its extensions outperform related algorithms in both applications.