JHJingwu He

Jingwu He

*This is an algorithmically generated author record based on publicly available information.

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


Jingwu He has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Affinity Fusion Graph-Based Framework for Natural Image Segmentation

    by Yang Zhang, Moyun Liu, Jingwu He, Fei Pan, Yanwen Guo

    This paper proposes an affinity fusion graph framework to effectively connect different graphs with highly discriminating power and nonlinearity for natural image segmentation. The proposed framework combines adjacency-graphs and kernel spectral clustering based graphs (KSC-graphs) according to a new definition named affinity nodes of multi-scale superpixels. These affinity nodes are selected based on a better affiliation of superpixels, namely subspace-preserving representation which is generated by sparse subspace clustering based on subspace pursuit. Then a KSC-graph is built via a novel kernel spectral clustering to explore the nonlinear relationships among these affinity nodes. Moreover, an adjacency-graph at each scale is constructed, which is further used to update the proposed KSC-graph at affinity nodes. The fusion graph is built across different scales, and it is partitioned to obtain final segmentation result. Experimental results on the Berkeley segmentation dataset and Microsoft Research Cambridge dataset show the superiority of our framework in comparison with the state-of-the-art methods. The code is available at https://github.com/Yangzhangcst/AF-graph.


  • Open Access

    Affinity Fusion Graph-based Framework for Natural Image Segmentation

    by Yang Zhang, Moyun Liu, Jingwu He, Fei Pan, Yanwen Guo

    This paper proposes an affinity fusion graph framework to effectively connect different graphs with highly discriminating power and nonlinearity for natural image segmentation. The proposed framework combines adjacency-graphs and kernel spectral clustering based graphs (KSC-graphs) according to a new definition named affinity nodes of multi-scale superpixels. These affinity nodes are selected based on a better affiliation of superpixels, namely subspace-preserving representation which is generated by sparse subspace clustering based on subspace pursuit. Then a KSC-graph is built via a novel kernel spectral clustering to explore the nonlinear relationships among these affinity nodes. Moreover, an adjacency-graph at each scale is constructed, which is further used to update the proposed KSC-graph at affinity nodes. The fusion graph is built across different scales, and it is partitioned to obtain final segmentation result. Experimental results on the Berkeley segmentation dataset and Microsoft Research Cambridge dataset show the superiority of our framework in comparison with the state-of-the-art methods. The code is available at https://github.com/Yangzhangcst/AF-graph.

  • Open Access

    FA-GANs: Facial Attractiveness Enhancement with Generative Adversarial Networks on Frontal Faces

    by Jingwu He, Chuan Wang, Yang Zhang, Jie Guo, Yanwen Guo

    Facial attractiveness enhancement has been an interesting application in Computer Vision and Graphics over these years. It aims to generate a more attractive face via manipulations on image and geometry structure while preserving face identity. In this paper, we propose the first Generative Adversarial Networks (GANs) for enhancing facial attractiveness in both geometry and appearance aspects, which we call "FA-GANs". FA-GANs contain two branches and enhance facial attractiveness in two perspectives: facial geometry and facial appearance. Each branch consists of individual GANs with the appearance branch adjusting the facial image and the geometry branch adjusting the facial landmarks in appearance and geometry aspects, respectively. Unlike the traditional facial manipulations learning from paired faces, which are infeasible to collect before and after enhancement of the same individual, we achieve this by learning the features of attractiveness faces through unsupervised adversarial learning. The proposed FA-GANs are able to extract attractiveness features and impose them on the enhancement results. To better enhance faces, both the geometry and appearance networks are considered to refine the facial attractiveness by adjusting the geometry layout of faces and the appearance of faces independently. To the best of our knowledge, we are the first to enhance the facial attractiveness with GANs in both geometry and appearance aspects. The experimental results suggest that our FA-GANs can generate compelling perceptual results in both geometry structure and facial appearance and outperform current state-of-the-art methods.

  • Image-Based 3D Model Retrieval for Indoor Scenes by Simulating Scene Context

    by Mingming Liu, Yunfeng Zhang, Jingwu He, Jie Guo, Yanwen Guo

    We propose a single image-based 3D model retrieval method for indoor scenes. By simulating the scene context of the input image, our method is able to handle several challenging scenarios featuring cluttered backgrounds and severe occlusions. To use our system, the user only needs to drag a few semantic bounding boxes for the query objects. The proposed approach then retrieves the most similar 3D models from the ShapeNet model repository, and aligns them with the corresponding objects automatically. This requires that the 3D models are represented by calibrated view-dependent visual elements learned from the rendered views. With the estimated occlusion relationships, the rendered model images are stacked at the corresponding locations to simulate the scene context. By conducting matching between these synthesized scenes and the input image, the most similar 3D models under the approximate poses are retrieved. Moreover, we show that the retrieving time can be significantly reduced based on a novel greedy algorithm. Experimental results demonstrate the effectiveness of our proposed method.


  • Viewpoint Assessment and Recommendation for Photographing Architectures

    by Jingwu He, Linbo Wang, Wenzhe Zhou, Hongjie Zhang, Xiufen Cui, Yanwen Guo

    This paper studies the problem of how to assess the quality of photographing viewpoints and how to choose good viewpoints for taking photographs of architectures. We achieve this by learning from photographs of world famous landmarks that are available on the Internet and their viewpoint quality ranked by online user annotation. Unlike previous efforts devoted to photo quality assessment which mainly rely on 2D image features, we show in this paper combining 2D image features extracted from images with 3D geometric features computed on the 3D models can result in more reliable evaluation of viewpoint quality. Specifically, we collect a set of photographs for each of 15 world famous architectures as well as their 3D models from the Internet. Viewpoint recovery for images is carried out through an image-model registration process, after which a newly proposed viewpoint clustering strategy is exploited to validate users' viewpoint preferences when photographing landmarks. Finally, we extract a number of 2D and 3D features for each image based on multiple visual and geometric cues and perform viewpoint recommendation by learning from both 2D and 3D features using a specifically designed SVM-2K multi-view learner, achieving superior performance over using solely 2D or 3D features. We show the effectiveness of the proposed approach through extensive experiments. The experiments also demonstrate that our system can be used to recommend viewpoints for rendering textured 3D models of buildings for the use of architectural design, in addition to viewpoint evaluation of photographs and recommendation of viewpoints for photographing architectures in practice.


  • Open Access

    Viewpoint Selection for Photographing Architectures

    by Jingwu He, Linbo Wang, Wenzhe Zhou, Hongjie Zhang, Xiufen Cui, Yanwen Guo

    This paper studies the problem of how to choose good viewpoints for taking photographs of architectures. We achieve this by learning from professional photographs of world famous landmarks that are available on the Internet. Unlike previous efforts devoted to photo quality assessment which mainly rely on 2D image features, we show in this paper combining 2D image features extracted from images with 3D geometric features computed on the 3D models can result in more reliable evaluation of viewpoint quality. Specifically, we collect a set of photographs for each of 15 world famous architectures as well as their 3D models from the Internet. Viewpoint recovery for images is carried out through an image-model registration process, after which a newly proposed viewpoint clustering strategy is exploited to validate users' viewpoint preferences when photographing landmarks. Finally, we extract a number of 2D and 3D features for each image based on multiple visual and geometric cues and perform viewpoint recommendation by learning from both 2D and 3D features using a specifically designed SVM-2K multi-view learner, achieving superior performance over using solely 2D or 3D features. We show the effectiveness of the proposed approach through extensive experiments. The experiments also demonstrate that our system can be used to recommend viewpoints for rendering textured 3D models of buildings for the use of architectural design, in addition to viewpoint evaluation of photographs and recommendation of viewpoints for photographing architectures in practice.

  • Combinatorial Search Methods for Multi-SNP Disease Association

    by Dumitru Brinza, Jingwu He, Alexander Zelikovsky

    Recent improvements in the accessibility of high-throughput genotyping have brought a deal of attention to genome-wide association studies for common complex diseases. Although, such diseases can be caused by multi-loci interactions, locus-by-locus studies are prevailing. Recently, two-loci analysis has been shown promising (Marchini et al, 2005), and multi-loci analysis is expected to find even deeper disease-associated interactions. Unfortunately, an exhaustive search among all possible corresponding multi-markers can be unfeasible even for small number of SNPs let alone the complete genome. In this paper we first propose to extract informative (indexing) SNPs that can be used for reconstructing of all SNPs almost without loss (He and Zelikovsky, 2006). In the reduced set of SNPs, we then propose to apply a novel combinatorial method for finding disease-associated multi-SNP combinations (MSCs). Our experimental study shows that the proposed methods are able to find MSCs whose disease association is statistically significant even after multiple testing adjustment. For (Daly et al, 2001) data we found a few unphased MSCs associated with Crohn's disease with multiple testing adjusted p-value below 0.05 while no single SNP or pair of SNPs show any significant association. For (Ueda et al, 2003) data we found a few new unphased and phased MSCs associated with autoimmune disorder


  • Family trio phasing and missing data recovery

    by Dumitru Brinza, Jingwu He, Weidong Mao, Alexander Zelikovsky

    Although there exist many phasing methods for unrelated adults or pedigrees, phasing and missing data recovery for data representing family trios is lagging behind. This paper is an attempt to fill this gap by considering the following problem. Given a set of genotypes partitioned into family trios, find for each trio a quartet of parent/offspring haplotypes explaining each trio without recombinations and recovering the SNP values missed in given genotype data. Our contributions include: formulating the pure-parsimony trio phasing without recombinations and the trio missing data recovery problems; proposing new greedy and integer linear programming based solution methods; extensive experimental validation of proposed methods showing advantage over the previously known methods.