Xuan Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xuan Zhu has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
Jinye Peng
School of Information Science and Technology, Northwest University, Xi’an, China
3 shared publications- Lin Wang
Northwest University, School of Information Science and Technology, Xi’an, China
3 shared publications - Dongfeng Mei
Northwest University,School of Information Science and Technology,Xi’an,China
2 shared publications Peiling Song
School of Information science and Technology, Northwest University, Xian, Shaanxi, China
2 shared publications- Bin Li
Bioinspired Engineering and Biomechanics Center, Xian Jiaotong University, Xian, China
1 shared publication - Bo Jiang
School of Information science and Technology, Northwest University, Xian, Shaanxi, China
1 shared publication
Latest Publications
- 22 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (19) , 36479-36488
2-D-to-3-D Lifting Human Pose Estimation Based on Simple Graph Convolution Regression
In 2D-to-3D human pose estimation (HPE), the torso connection relationship between joints, which can be seen as important constraint information, is critical to improving the accuracy of 3D human pose estimation. Previous 3D HPE methods based on CNN and Transformer do not utilize the constraint information of nodes. GCN-based 3D HPE methods consider joints as nodes and torsos as edges. When learning node features, the weight values of edges determine the strength of information interaction between nodes. We propose a Simple Graph Convolution layer for Regression (SGCR) for solving the node regression task. Compared with the GCN layer, the SGCR layer has a larger receptive field, which can make full use of the weight relationship of edges. By stacking SGCR layers, we construct SGCRPose for monocular single-frame 2D-to-3D HPE. SGCRPose consists of an up-sampling stage, a residual SGCR stage, and a down-sampling stage. Each stage is only composed of SGCR layers. SGCRPose has a simple structure, a large receptive field, and a strong ability to fit complex functional relationships. On the Human3.6M dataset, this pure graph convolution method demonstrates superior 2D-to-3D HPE accuracy compared to state-of-the-art single-frame graph convolution approaches, while showing comparable performance to the previous best graph convolution method. Experimental results on COCO confirm that SGCRPose exhibits good robustness.
- 22 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (19) , 36479-36488
2-D-to-3-D Lifting Human Pose Estimation Based on Simple Graph Convolution Regression
In 2D-to-3D human pose estimation (HPE), the torso connection relationship between joints, which can be seen as important constraint information, is critical to improving the accuracy of 3D human pose estimation. Previous 3D HPE methods based on CNN and Transformer do not utilize the constraint information of nodes. GCN-based 3D HPE methods consider joints as nodes and torsos as edges. When learning node features, the weight values of edges determine the strength of information interaction between nodes. We propose a Simple Graph Convolution layer for Regression (SGCR) for solving the node regression task. Compared with the GCN layer, the SGCR layer has a larger receptive field, which can make full use of the weight relationship of edges. By stacking SGCR layers, we construct SGCRPose for monocular single-frame 2D-to-3D HPE. SGCRPose consists of an up-sampling stage, a residual SGCR stage, and a down-sampling stage. Each stage is only composed of SGCR layers. SGCRPose has a simple structure, a large receptive field, and a strong ability to fit complex functional relationships. On the Human3.6M dataset, this pure graph convolution method demonstrates superior 2D-to-3D HPE accuracy compared to state-of-the-art single-frame graph convolution approaches, while showing comparable performance to the previous best graph convolution method. Experimental results on COCO confirm that SGCRPose exhibits good robustness.
- 1 May 2025
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 34 (03) , 033021-15
Attention-based feature enhancement for direct multiview 3D human pose estimation
The task of 3D human pose estimation (3D HPE) is to estimate the coordinates of human joints from images or videos and connect adjacent joints to form a human skeleton. 3D HPE technology is widely used in the fields of behavior recognition, human–computer interaction, and virtual reality. The method of 3D HPE is divided into single-view method and the multiview method. The single-view method has great limitations in solving the problem of multiperson pose estimation and occlusion. The multiview 3D HPE can be classified into single-stage and mainstream two-stage methods. Compared with single-stage methods, the two-stage methods first estimate the coordinates of 2D joints in each view and then use the association between 2D joints lifting the 2D pose to the 3D pose, with an accuracy affected by the 2D estimation results. Moreover, the existing single-stage methods cannot consider the regression and attribution features of joints from a global perspective at the same time, with a performance that needs to be further improved. To address these problems, we propose an end-to-end multiview multiperson 3D human pose estimation network, named AFEMVPose. It uses attention mechanisms to adaptively focus on and enhance regression and affiliation features of joints, capturing complex interactions between joints. AFEMVPose consists of a feature extraction module (FE), attention-based feature enhancement module (AFE), and pose decoding module (DCPose). FE is used to extract the initial features of multiple views. AFE strengthens the regression features of joints to raise the localization precision of joints. The purpose of the specially designed DCPose is to enhance and integrate joint affiliation and regression features, achieving the correct connections of joints. Compared with the state-of-the-art methods, the 3D HPE accuracy of our method is competitive on the CMU Panoptic, Shelf, and Campus datasets and demonstrates good robustness.
- 1 May 2025
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 34 (03) , 033021-15
Attention-based feature enhancement for direct multiview 3D human pose estimation
The task of 3D human pose estimation (3D HPE) is to estimate the coordinates of human joints from images or videos and connect adjacent joints to form a human skeleton. 3D HPE technology is widely used in the fields of behavior recognition, human–computer interaction, and virtual reality. The method of 3D HPE is divided into single-view method and the multiview method. The single-view method has great limitations in solving the problem of multiperson pose estimation and occlusion. The multiview 3D HPE can be classified into single-stage and mainstream two-stage methods. Compared with single-stage methods, the two-stage methods first estimate the coordinates of 2D joints in each view and then use the association between 2D joints lifting the 2D pose to the 3D pose, with an accuracy affected by the 2D estimation results. Moreover, the existing single-stage methods cannot consider the regression and attribution features of joints from a global perspective at the same time, with a performance that needs to be further improved. To address these problems, we propose an end-to-end multiview multiperson 3D human pose estimation network, named AFEMVPose. It uses attention mechanisms to adaptively focus on and enhance regression and affiliation features of joints, capturing complex interactions between joints. AFEMVPose consists of a feature extraction module (FE), attention-based feature enhancement module (AFE), and pose decoding module (DCPose). FE is used to extract the initial features of multiple views. AFE strengthens the regression features of joints to raise the localization precision of joints. The purpose of the specially designed DCPose is to enhance and integrate joint affiliation and regression features, achieving the correct connections of joints. Compared with the state-of-the-art methods, the 3D HPE accuracy of our method is competitive on the CMU Panoptic, Shelf, and Campus datasets and demonstrates good robustness.
- 29 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-14
EP-Net: Improving Point Cloud Learning Efficiency Through Feature Decoupling
Point cloud analysis has been significantly influenced by the PointNet family which has achieved remarkable accuracy across various benchmarks. However, enhancing the efficiency of these models without compromising performance remains a challenging task. In this paper, we investigate the efficiency of the state-of-the-art point-based method PointNeXt without degrading its performance and propose a more efficient and powerful network named Efficient PointNet (EP-Net). In particular, we propose a decoupled feature aggregation (DFA) module that decouples the learning of geometric and semantic features to capture more discriminative information, rather than the vanilla set abstraction (SA) module aggregating them for coarse joint processing. Besides, we develop a more effective sampling strategy for EP-Net, compressing processing complexity from O ( n log( n )) to linear. It selects points nearest to the center of each non-empty grid cell as the new sampling points. Impressively, we achieve a dual increase in both speed and accuracy, attributed to the more refined feature aggregation and more efficient sampling. Furthermore, we demonstrate the extensibility of our proposal towards other point cloud networks, from the perspective either of boost efficiency or performance prompt. Conditioned on extensive experiments on point cloud classification and segmentation tasks, EP-Net reports a state-of-the-art performance with 73.3% mean IoU on S3DIS Area5, boosting their baseline PointNeXt by 2.5%, with only 10.6% FLOPs and 37% parameters. On extensibility experiments, our strategy boosts PointMLP with an improvement of 0.9% mAcc on the ScanObjectNN dataset.
- 29 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-14
EP-Net: Improving Point Cloud Learning Efficiency Through Feature Decoupling
Point cloud analysis has been significantly influenced by the PointNet family which has achieved remarkable accuracy across various benchmarks. However, enhancing the efficiency of these models without compromising performance remains a challenging task. In this paper, we investigate the efficiency of the state-of-the-art point-based method PointNeXt without degrading its performance and propose a more efficient and powerful network named Efficient PointNet (EP-Net). In particular, we propose a decoupled feature aggregation (DFA) module that decouples the learning of geometric and semantic features to capture more discriminative information, rather than the vanilla set abstraction (SA) module aggregating them for coarse joint processing. Besides, we develop a more effective sampling strategy for EP-Net, compressing processing complexity from O ( n log( n )) to linear. It selects points nearest to the center of each non-empty grid cell as the new sampling points. Impressively, we achieve a dual increase in both speed and accuracy, attributed to the more refined feature aggregation and more efficient sampling. Furthermore, we demonstrate the extensibility of our proposal towards other point cloud networks, from the perspective either of boost efficiency or performance prompt. Conditioned on extensive experiments on point cloud classification and segmentation tasks, EP-Net reports a state-of-the-art performance with 73.3% mean IoU on S3DIS Area5, boosting their baseline PointNeXt by 2.5%, with only 10.6% FLOPs and 37% parameters. On extensibility experiments, our strategy boosts PointMLP with an improvement of 0.9% mAcc on the ScanObjectNN dataset.
- 15 September 2021
- Published by Taylor & Francis
- p. 249-261
Backpacker tourist experiences
Backpacker tourism has a long history associated with hitchhiking in North America, but it became especially notorious during the hippie movement of the 1960s. During that time, young, carefree backpackers began travelling in large numbers to well-established tourist destinations. Through this process, certain routes and backpacker enclaves developed in Europe and Asia, and later in other parts of the world. Today, backpacker tourism is one of the most pervasive forms of independent travel and touches nearly every corner of the globe. This chapter describes the backpacker tourism phenomenon and its motivations in broad terms and examines the backpacker experience from the perspectives of time (temporalities), geography (spatialities) and cultural norms (culturalities). This conceptual framework is used to interpret the experiences of backpackers in the contexts of gap year travel, the Chinese concept of qiongyou, European Interrailing, backpacker enclaves and tourism trails/routes. Thresholds of adulthood and the frequent sense of timelessness are examples of strong manifestations of temporalities. The mobilities and moorings associated with transit spaces and backpacker enclaves illustrate the socialization processes, in-betweenness and connections to the comforts of home that many young travellers crave. Finally, the interactions with other backpackers and local inhabitants, as well as changing markets for traditional backpacker tourism illustrate some of the culturalities frequently manifested in this global travel phenomenon.
- 15 September 2021
- Published by Taylor & Francis
- p. 249-261
Backpacker tourist experiences
Backpacker tourism has a long history associated with hitchhiking in North America, but it became especially notorious during the hippie movement of the 1960s. During that time, young, carefree backpackers began travelling in large numbers to well-established tourist destinations. Through this process, certain routes and backpacker enclaves developed in Europe and Asia, and later in other parts of the world. Today, backpacker tourism is one of the most pervasive forms of independent travel and touches nearly every corner of the globe. This chapter describes the backpacker tourism phenomenon and its motivations in broad terms and examines the backpacker experience from the perspectives of time (temporalities), geography (spatialities) and cultural norms (culturalities). This conceptual framework is used to interpret the experiences of backpackers in the contexts of gap year travel, the Chinese concept of qiongyou, European Interrailing, backpacker enclaves and tourism trails/routes. Thresholds of adulthood and the frequent sense of timelessness are examples of strong manifestations of temporalities. The mobilities and moorings associated with transit spaces and backpacker enclaves illustrate the socialization processes, in-betweenness and connections to the comforts of home that many young travellers crave. Finally, the interactions with other backpackers and local inhabitants, as well as changing markets for traditional backpacker tourism illustrate some of the culturalities frequently manifested in this global travel phenomenon.
- Open Access
- 12 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 205938-205947
Complex Human Pose Estimation via Keypoints Association Constraint Network
Human pose estimation has attracted enormous interest in the field of human action recognition. When the human pose is complex (such as pose distortion, pose reversal, etc.) or there is background interference (multi-target, shadow, etc.), the keypoints obtained by existing methods of human pose estimation often have incorrect positioning, category, and connection. This paper proposes a novel human pose estimation network KACNet via the keypoint association constraints. The Channel-1 of KACNet is constrained by the distance loss function to obtain the position of keypoints, and the Channel-2 of KACNet is constrained by the association loss function to obtain the relationship of keypoints. Then, the position and relationship of keypoints are fused by the weighted loss function to obtain the keypoints with accurate location, classification, and connection. Experiments on a large number of public datasets and Internet data show that our method can effectively suppress background interference to improve the accuracy of complex human pose estimation. Compared with state-of-the-art human pose estimation methods, the proposed methods can accurately locate, classify, and connect the human body keypoints robustly.
- 12 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 205938-205947
Open AccessComplex Human Pose Estimation via Keypoints Association Constraint Network
Human pose estimation has attracted enormous interest in the field of human action recognition. When the human pose is complex (such as pose distortion, pose reversal, etc.) or there is background interference (multi-target, shadow, etc.), the keypoints obtained by existing methods of human pose estimation often have incorrect positioning, category, and connection. This paper proposes a novel human pose estimation network KACNet via the keypoint association constraints. The Channel-1 of KACNet is constrained by the distance loss function to obtain the position of keypoints, and the Channel-2 of KACNet is constrained by the association loss function to obtain the relationship of keypoints. Then, the position and relationship of keypoints are fused by the weighted loss function to obtain the keypoints with accurate location, classification, and connection. Experiments on a large number of public datasets and Internet data show that our method can effectively suppress background interference to improve the accuracy of complex human pose estimation. Compared with state-of-the-art human pose estimation methods, the proposed methods can accurately locate, classify, and connect the human body keypoints robustly.
- 16 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 59 (6) , 4957-4971
PSMD-Net: A Novel Pan-Sharpening Method Based on a Multiscale Dense Network
Pan sharpening is used to fuse a low-resolution multispectral (MS) image and a high-resolution panchromatic (PAN) image to obtain a high-resolution MS image. This article proposes PSMD-Net, an end-to-end pan-sharpening method based on a multi-scale dense network. A shallow feature extraction layer (SFEL) extracts the shallow features from the original images, and these are used as an input to a global dense feature fusion (GDFF) network to learn the global features for image reconstruction. A multiscale dense block (MDB) is designed to fully extract the spatial and spectral information from the shallow features in the GDFF network. In the proposed network, multiple MDBs are stacked to extract rich, multi-scale dense hierarchical features, and a global dense connection (GDC) is designed to allow direct connections from the state of the current MDB to all subsequent MDBs to extract more advanced features. The extracted hierarchical features are sent to the global feature fusion layer (GFFL) to adaptively learn the global features for image reconstruction. Finally, global residual learning (GRL) is adopted to force the network to pay more attention to the changing part of the image. We perform experiments on simulated and real data from WorldView-2 and WorldView-3 satellites. Visual and quantitative assessment results demonstrate that PSMD-Net yields higher-resolution fusion images than the state-of-the-art methods.
- 16 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 59 (6) , 4957-4971
PSMD-Net: A Novel Pan-Sharpening Method Based on a Multiscale Dense Network
Pan sharpening is used to fuse a low-resolution multispectral (MS) image and a high-resolution panchromatic (PAN) image to obtain a high-resolution MS image. This article proposes PSMD-Net, an end-to-end pan-sharpening method based on a multi-scale dense network. A shallow feature extraction layer (SFEL) extracts the shallow features from the original images, and these are used as an input to a global dense feature fusion (GDFF) network to learn the global features for image reconstruction. A multiscale dense block (MDB) is designed to fully extract the spatial and spectral information from the shallow features in the GDFF network. In the proposed network, multiple MDBs are stacked to extract rich, multi-scale dense hierarchical features, and a global dense connection (GDC) is designed to allow direct connections from the state of the current MDB to all subsequent MDBs to extract more advanced features. The extracted hierarchical features are sent to the global feature fusion layer (GFFL) to adaptively learn the global features for image reconstruction. Finally, global residual learning (GRL) is adopted to force the network to pay more attention to the changing part of the image. We perform experiments on simulated and real data from WorldView-2 and WorldView-3 satellites. Visual and quantitative assessment results demonstrate that PSMD-Net yields higher-resolution fusion images than the state-of-the-art methods.
- 1 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 65-68
Structural Dissimilarity Learning Dictionary via Block Feature Coding for Image Super-Resolution
In this paper, we present an improved single image super-resolution method. The improvements are mainly attributed to block feature coding (BFC) that is to select structurally dissimilar image patches by coding the edge and direction features of image patches. A structural dissimilarity learning dictionary (SDLD-BFC) pair are trained on a small training image patches set. Numerous experiments demonstrate efficient SDLD-BFC training and robust SDLDBFC method. Compared with other SR methods, SDLD-BFC significantly improves efficiency, while recovering good edge and texture.
- 1 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 65-68
Structural Dissimilarity Learning Dictionary via Block Feature Coding for Image Super-Resolution
In this paper, we present an improved single image super-resolution method. The improvements are mainly attributed to block feature coding (BFC) that is to select structurally dissimilar image patches by coding the edge and direction features of image patches. A structural dissimilarity learning dictionary (SDLD-BFC) pair are trained on a small training image patches set. Numerous experiments demonstrate efficient SDLD-BFC training and robust SDLDBFC method. Compared with other SR methods, SDLD-BFC significantly improves efficiency, while recovering good edge and texture.
- Open Access
Super-Resolved Image Perceptual Quality Improvement via Multi-Feature Discriminators
Generative adversarial network (GAN) for image super-resolution (SR) has attracted enormous interests in recent years. However, the GAN-based SR methods only use image discriminator to distinguish SR images and high-resolution (HR) images. Image discriminator fails to discriminate images accurately since image features cannot be fully expressed. In this paper, we design a new GAN-based SR framework GAN-IMC which includes generator, image discriminator, morphological component discriminator and color discriminator. The combination of multiple feature discriminators improves the accuracy of image discrimination. Adversarial training between the generator and multi-feature discriminators forces SR images to converge with HR images in terms of data and features distribution. Moreover, in some cases, feature enhancement of salient regions is also worth considering. GAN-IMC is further optimized by weighted content loss (GAN-IMCW), which effectively restores and enhances salient regions in SR images. The effectiveness and robustness of our method are confirmed by extensive experiments on public datasets. Compared with state-of-the-art methods, the proposed method not only achieves competitive Perceptual Index (PI) and Natural Image Quality Evaluator (NIQE) values but also obtains pleasant visual perception in image edge, texture, color and salient regions.
Open AccessSuper-Resolved Image Perceptual Quality Improvement via Multi-Feature Discriminators
Generative adversarial network (GAN) for image super-resolution (SR) has attracted enormous interests in recent years. However, the GAN-based SR methods only use image discriminator to distinguish SR images and high-resolution (HR) images. Image discriminator fails to discriminate images accurately since image features cannot be fully expressed. In this paper, we design a new GAN-based SR framework GAN-IMC which includes generator, image discriminator, morphological component discriminator and color discriminator. The combination of multiple feature discriminators improves the accuracy of image discrimination. Adversarial training between the generator and multi-feature discriminators forces SR images to converge with HR images in terms of data and features distribution. Moreover, in some cases, feature enhancement of salient regions is also worth considering. GAN-IMC is further optimized by weighted content loss (GAN-IMCW), which effectively restores and enhances salient regions in SR images. The effectiveness and robustness of our method are confirmed by extensive experiments on public datasets. Compared with state-of-the-art methods, the proposed method not only achieves competitive Perceptual Index (PI) and Natural Image Quality Evaluator (NIQE) values but also obtains pleasant visual perception in image edge, texture, color and salient regions.
- 7 August 2018
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 78 (6) , 7143-7154
Multi-frame image super-resolution reconstruction via low-rank fusion combined with sparse coding
- 7 August 2018
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 78 (6) , 7143-7154
Multi-frame image super-resolution reconstruction via low-rank fusion combined with sparse coding
- Open Access
- 1 January 2017
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2017 (1)
Image Super‐Resolution Based on Sparse Representation via Direction and Edge Dictionaries
Sparse representation has recently attracted enormous interests in the field of image super‐resolution. The sparsity‐based methods usually train a pair of global dictionaries. However, only a pair of global dictionaries cannot best sparsely represent different kinds of image patches, as it neglects two most important image features: edge and direction. In this paper, we propose to train two novel pairs of Direction and Edge dictionaries for super‐resolution. For single‐image super‐resolution, the training image patches are, respectively, divided into two clusters by two new templates representing direction and edge features. For each cluster, a pair of Direction and Edge dictionaries is learned. Sparse coding is combined with the Direction and Edge dictionaries to realize super‐resolution. The above single‐image super‐resolution can restore the faithful high‐frequency details, and the POCS is convenient for incorporating any kind of constraints or priors. Therefore, we combine the two methods to realize multiframe super‐resolution. Extensive experiments on image super‐resolution are carried out to validate the generality, effectiveness, and robustness of the proposed method. Experimental results demonstrate that our method can recover better edge structure and details.
- 1 January 2017
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2017 (1)
Open AccessImage Super‐Resolution Based on Sparse Representation via Direction and Edge Dictionaries
Sparse representation has recently attracted enormous interests in the field of image super‐resolution. The sparsity‐based methods usually train a pair of global dictionaries. However, only a pair of global dictionaries cannot best sparsely represent different kinds of image patches, as it neglects two most important image features: edge and direction. In this paper, we propose to train two novel pairs of Direction and Edge dictionaries for super‐resolution. For single‐image super‐resolution, the training image patches are, respectively, divided into two clusters by two new templates representing direction and edge features. For each cluster, a pair of Direction and Edge dictionaries is learned. Sparse coding is combined with the Direction and Edge dictionaries to realize super‐resolution. The above single‐image super‐resolution can restore the faithful high‐frequency details, and the POCS is convenient for incorporating any kind of constraints or priors. Therefore, we combine the two methods to realize multiframe super‐resolution. Extensive experiments on image super‐resolution are carried out to validate the generality, effectiveness, and robustness of the proposed method. Experimental results demonstrate that our method can recover better edge structure and details.