Ke Xu

Dr. Ke Xu

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
1 August 2020 in IEEE Journal of Selected Topics in Signal Processing
Verified
Journal Article
Closed access
ZMZhongjie Mi
Zhongjie Mi
XJXinghao Jiang
Xinghao Jiang
TSTanfeng Sun
Tanfeng Sun
KXKe Xu
Ke Xu
With Generative Adversarial Networks (GAN) achieving realistic image generation, fake image detection research has become an imminent need. In this paper, a novel detection algorithm is designed to exploit the structural defect in GAN, taking advantage of the most vulnerable link in GAN generators — the Up-sampling process conducted by the Transposed Convolution operation. The Transposed Convolution in the process will cause the lack of global information in the generated images. Therefore, the Self-Attention mechanism is adopted correspondingly, equipping the algorithm with a much better comprehension of the global information than the other current work adopting pure CNN network, which is reflected in the significant increase in the detection accuracy. With the thorough comparison to the current work and corresponding careful analysis, it is verified that our proposed algorithm outperforms other current works in the field. Also, with experiments conducted on other image-generation categories and images undergone usual real-life post-processing methods, our proposed algorithm shows decent robustness for various categories of images under different reality circumstances, rather than restricted by image types and pure laboratory situation.

30 April 2019 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
XJXinghao Jiang
Xinghao Jiang
KXKe Xu
Ke Xu
TSTanfeng Sun
Tanfeng Sun
Skeleton-based human action recognition has been a popular research field during the past few years. With the help of cameras equipping deep sensors, such as the Kinect, a human action can be represented by a sequence of human skeleton data. Inspired by the skeleton descriptors based on Lie group, a Spatial Temporal Skeleton Transformation Descriptor (ST-STD) is proposed in this paper. The ST-STD describes the relative transformations of skeletons, including the rotation and translation during movement. It gives a comprehensive view of the skeleton in both spatial and temporal domain for each frame. To capture the temporal connections in the skeleton sequence, a Denoising Sparse Long Short Term Memory (DS-LSTM) network is proposed in this paper. The DS-LSTM is designed to deal with two problems in action recognition. Firstly, to decrease the intra-class diversity, the Spatial Temporal Auto-Encoder (STAE) is proposed in this paper to generate representations with higher abstractness. The denoising constraint and the sparsity constraint are applied on both spatial and temporal domain to enhance robustness and to reduce action misalignment. Secondly, to model the action sequence, a three-layer LSTM structure is trained with STAE representations for temporal modelling and classification. The experiments are carried out on four popular datasets. The results show that our approach performs better than several existing skeleton-based action recognition methods, which prove the effectiveness of our method.

22 July 2019 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
KXKe Xu
Ke Xu
TSTanfeng Sun
Tanfeng Sun
XJXinghao Jiang
Xinghao Jiang
Anomaly detection and localization in videos is still a challenging task in computer vision field. Previous methods took this task as a one-class deviation problem, which computed the deviation between test samples and normal patterns. In this paper, an Adaptive Intra-frame Classification Network (AICN) is proposed to transform this task to a multi-class classification problem. The contributions of our method are: 1) AICN is a more effective anomaly evaluation network. It evaluates abnormality based on intra-frame classification results, which reserves more connection information of sub-regions and makes the model outperform previous one-class classifiers. 2) AICN reduces the computational cost. Motion Convolutional Layers (MCLs) and Shape Convolutional Layers (SCLs) are proposed to extract feature maps, which utilize the simplicity of convolution to reduce computational cost. Adaptive Region Pooling Layer (ARPL) is also proposed to reduce the calculation cost of overlapped sub-regions. 3) AICN enhances the adaptiveness of model. Only one multi-class classifier is used rather than multiple one-class classifiers. It makes the network easier to be applied on other scenes and makes the model adaptive to samples with different resolutions. The proposed method is examined on four public datasets with different background complexities and resolutions: UCSD Ped1 dataset, UCSD Ped2 dataset, Avenue dataset and Subway dataset. The results are further compared with previous approaches to confirm the effectiveness and the advantage of our method.

7 February 2017 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
KXKe Xu
Ke Xu
XJXinghao Jiang
Xinghao Jiang
TSTanfeng Sun
Tanfeng Sun
In this paper, a novel method based on the two-stream dictionary learning architecture for human action recognition is proposed. The architecture consists of interest patch (IP) detector and descriptor, two-stream dictionary models, and support vector machine (SVM) for classification. The novel IP detector combines a human detector and a contour detector to extract patches of interest on human contours. Then the IP descriptors are calculated in spatial stream and temporal stream separately. In each stream, a dictionary is trained for each action with the IP descriptors as an action model. In this way, measuring the similarity between an action sequence and an action model is transformed to reconstructing the IPs in this sequence with the model and computing the reconstruction error. For each action, an IP distribution histogram is constructed and the histogram is further used to train an SVM classifier in each stream. A score fusion method is applied to fuse the spatial and temporal SVM classification results to make a final decision. The proposed architecture is examined on four public data sets with different background complexities and camera motion conditions: Weizmann data set, KTH data set, Olympic sports data set, and HMDB51 data set. The results are further compared with state-of-the-art approaches in the experiment section to confirm the effectiveness of this architecture.

23 March 2018 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
KXKe Xu
Ke Xu
XJXinghao Jiang
Xinghao Jiang
TSTanfeng Sun
Tanfeng Sun
Anomaly detection in videos is still a challenging task among the computer vision community. In this paper, an efficient anomaly detection method based on stacked sparse coding (SSC) with intraframe classification strategy is proposed. Each video is divided into blocks and the Foreground Interest Point (FIP) descriptor is proposed to describe the appearance and motion features for each block. The spatial-temporal features are then encoded with SSC. Specifically, the first stage of SSC encodes the spatial connections among blocks and the second stage of SSC encodes the temporal connections of all frame patches in each block. Finally, an intraframe classification strategy which uses the probabilistic outputs of SVM is proposed to evaluate the abnormality of each block. Contributions of this paper are listed as follows: 1) The FIP descriptor is proposed to describe the features of blocks, which reserves more spatial-temporal information. 2) The SSC encoding method encodes both the spatial and temporal connections of blocks, which makes the features more representative. 3) The intraframe classification strategy keeps the evaluation consistency among blocks and it helps to improve detection performance. The proposed method is examined on four public datasets with different background complexities and resolutions: UCSD Ped1 dataset, UCSD Ped2 dataset, Avenue dataset, and Subway dataset. The results are further compared with previous approaches to confirm the effectiveness and advantages of this method.

30 August 2023 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
HMHaotian Ma
Haotian Ma
KXKe Xu
Ke Xu
XJXinghao Jiang
Xinghao Jiang
ZZZeyu Zhao
Zeyu Zhao
TSTanfeng Sun
Tanfeng Sun
Deep Neural Networks (DNNs) are vulnerable to adversarial patch attacks, which raises security concerns for face recognition systems using DNNs. Previous attack methods focus on the perturbation texture and generate adversarial patches with fixed shapes at random or pre-designed locations, which causes poor adversarial transferability. This paper proposes a Spatial Mutable Adversarial Patch (SMAP) method to generate a dynamic mutable patch to be injected into the face. In the proposed SMAP, the texture, position and shape of the patch are optimized simultaneously and the patch generation pipeline is end-to-end differentiable. Specifically, a Patch Location Selection Scheme is designed to find the critical patch position with the most significant influence on the target identity by the step-based gradient search. By innovatively bridging the pre-defined mask and the dynamic update of the patch, the patch position and shape are changed based on the affine transformation and sampling mechanism in each iteration, which maintains the importance of the injected patch to the adversarial objective. To evaluate the vulnerability of face recognition models, we explore more threatening impersonation attacks under the black-box setting and design a strict evaluation metric that aligns with the real-world scenario. Extensive experiments show that the proposed SMAP improves attack performance across various face recognition models and datasets. Moreover, SMAP achieves better transferability on commercial face recognition systems than existing methods.