Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Jiahua Wu has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Pseudo Labels Refinement with Stable Cluster Reconstruction for Unsupervised Re-identification

    by Zhenyu Liu, Jiawei Lian, Jiahua Wu, Da-Han Wang, Yun Wu, Shunzhi Zhu, Dewu Ge

  • Partial Attention CenterNet for Bottom-Up Human Pose Estimation

    by Jiahua Wu, Hyo Jong Lee

    The typical bottom-up human pose estimation methods can be divided into two steps, keypoint detection and grouping. The traditional keypoint regression-based methods exploit an effective backbone (like HRNet) and different prediction heads to acquire the body center and body joint. Then they utilize the offset between the body center and body joint to figure out the grouping task. In this paper, we first propose a body branch module and keypoint attention module to improve keypoint detection and keypoint regression. In body branch module, we exploit a multi-branch structure for keypoint detection and keypoint regression. Each branch represents a part of human body. In keypoint attention module, two simple yet reliable pooling layers are adopted to extract the attention areas of different kinds of keypoints. Combining these two modules, we propose a Partial Attention CenterNet for multi-person human pose estimation. The proposed method outperforms the traditional keypoint regression-based methods. Experiments have demonstrated the obvious performance improvements on COCO dataset brought by the introduced components.


  • Open Access

    A New Multi-Person Pose Estimation Method Using the Partitioned CenterPose Network

    by Jiahua Wu, Hyo-Jong Lee

    In bottom-up multi-person pose estimation, grouping joint candidates into the appropriately structured corresponding instance of a person is challenging. In this paper, a new bottom-up method, the Partitioned CenterPose (PCP) Network, is proposed to better cluster the detected joints. To achieve this goal, we propose a novel approach called Partition Pose Representation (PPR) which integrates the instance of a person and its body joints based on joint offset. PPR leverages information about the center of the human body and the offsets between that center point and the positions of the body’s joints to encode human poses accurately. To enhance the relationships between body joints, we divide the human body into five parts, and then, we generate a sub-PPR for each part. Based on this PPR, the PCP Network can detect people and their body joints simultaneously, then group all body joints according to joint offset. Moreover, an improved l1 loss is designed to more accurately measure joint offset. Using the COCO keypoints and CrowdPose datasets for testing, it was found that the performance of the proposed method is on par with that of existing state-of-the-art bottom-up methods in terms of accuracy and speed.


  • Multiexposure Estimation and Fusion Based on a Sparsity Exposure Dictionary

    by Yong Yang, Jiahua Wu, Shuying Huang, Pan Lin

    Multi-exposure image fusion (MEF), which is an emerging hot research topic, aims to fuse multi-exposure images into a high quality low dynamic range (LDR) image. In this paper, we propose a novel exposure estimation based MEF method with sparse decomposition and a designed sparsity exposure dictionary (SED). First, in order to represent more elementary information of multi-exposure images, SED is trained by under and over-exposed images and constructed by the K-SVD algorithm. Next, the SED is applied to construct exposure estimation maps by the number of atoms of the image patch, which is obtained by sparse decomposition. When the exposure estimation maps are obtained, a novel fusion framework that uses these maps to fuse multi-exposure images is presented. In this framework, we employ the exposure estimation maps and an adaptive guided filter to construct the final fusion decision maps. The two factors of guided filter are adaptively determined without manual interference to obtain an optimal representation effect for multi-exposure image sequences with different sizes and number. Finally, a fused image is generated via the pyramid merging method. The proposed fusion method is conducted on a series of multi-exposure image sequences and compared to seven popular MEF methods. The experimental results clearly demonstrate that the proposed method outperforms the state-of-the-art methods in terms of subjective visual and quantitative evaluations.


  • Multilevel Features Convolutional Neural Network for Multifocus Image Fusion

    by Yong Yang, Zhipeng Nie, Shuying Huang, Pan Lin, Jiahua Wu

    Multi-focus image fusion is an important technique that aims to generate a single clean image by fusing multiple input images. In this paper, we propose a novel multi-level features convolutional neural network (MLFCNN) architecture for image fusion. In the MLFCNN model, all features learned from previous layers are passed to the subsequent layer. Inside every path between the previous layer and the subsequent layer, we add a 1x1 convolution module to reduce the redundancy. In our method, the source images first are fed to our pre-trained MLFCNN model to obtain the initial focus map. Then, the initial focus map is performed by morphological opening and closing operations and followed by a Gaussian filter to obtain the final decision map. Finally, the fused all-in-focus image is generated based on a weighted-sum strategy with the decision map. The experimental results demonstrate that the proposed method outperforms some state-of-the-art image fusion algorithms in terms of both qualitative and objective evaluations.


  • Multimodal Medical Image Fusion Based on Fuzzy Discrimination With Structural Patch Decomposition

    by Yong Yang, Jiahua Wu, Shuying Huang, Yuming Fang, Pan Lin, Yue Que

    Multimodal medical image fusion, emerging as a hot topic, aims to fuse images with complementary multi-source information. In this paper, we propose a novel multimodal medical image fusion method based on structural patch decomposition (SPD) and fuzzy logic technology. First, the SPD method is employed to extract two salient features for fusion discrimination. Next, two novel fusion decision maps called an incomplete fusion map and supplemental fusion map are constructed from salient features. In this step, the supplemental map is constructed by our defined two different fuzzy logic systems. The supplemental and incomplete maps are then combined to construct an initial fusion map. The final fusion map is obtained by processing the initial fusion map with a Gaussian filter. Finally, a weighted average approach is adopted to create the final fused image. Additionally, an effective color medical image fusion scheme that can effectively prevent color distortion and obtain superior diagnostic effects is also proposed to enhance fused images. Experimental results clearly demonstrate that the proposed method outperforms state-of-the-art methods in terms of subjective visual and quantitative evaluations.


  • Compensation Details-Based Injection Model for Remote Sensing Image Fusion

    by Yong Yang, Lei Wu, Shuying Huang, Jiancheng Sun, Weiguo Wan, Jiahua Wu

    Remote sensing image fusion has a potential spectral distortion problem due to the global/local spectral and spatial correlations between panchromatic (PAN) and multispectral (MS) images. To overcome this problem, in this letter, a compensation details-based injection (CDI) fusion model is presented from a new perspective of compensatory learning. In contrast to the traditional method, the two categories of details, namely, the PAN details and the CD, are considered to compensate for the spatial and spectral differences between low-resolution MS (LRMS) and high-resolution MS images. To obtain the CD, a robust sparse representation was employed to calculate the difference between the PAN and MS images during the fusion. The CD combined with the PAN details extracted by a multiscale-guided filter are then injected into the upsampled LRMS image to achieve a fused image. Extensive experiments were undertaken on several image data sets, and the results demonstrate the effectiveness of the proposed CDI method.