arXiv subjects

Ziheng Zhang

Publications and source records attributed to Ziheng Zhang.

78 records · Page 5Linked to original sources

arXiv2020

An Industry Evaluation of Embedding-based Entity Alignment

Embedding-based entity alignment has been widely investigated in recent years, but most proposed methods still rely on an ideal supervised learning setting with a large number of unbiased seed mappings for training and validation, which significantly limits their usage. In this study, we evaluate those state-of-the-art methods in an industrial context, where the impact of seed mappings with different sizes and different biases is explored. Besides the popular benchmarks from DBpedia and Wikidata, we contribute and evaluate a new industrial benchmark that is extracted from two heterogeneous knowledge graphs (KGs) under deployment for medical applications. The experimental results enable the analysis of the advantages and disadvantages of these alignment methods and the further discussion of suitable strategies for their industrial deployment.

cs.CL↗

arXiv2019

Photo-Realistic Facial Details Synthesis from Single Image

We present a single-image 3D face synthesis technique that can handle challenging facial expressions while recovering fine geometric details. Our technique employs expression analysis for proxy face geometry generation and combines supervised and unsupervised learning for facial detail synthesis. On proxy generation, we conduct emotion prediction to determine a new expression-informed proxy. On detail synthesis, we present a Deep Facial Detail Net (DFDN) based on Conditional Generative Adversarial Net (CGAN) that employs both geometry and appearance loss functions. For geometry, we capture 366 high-quality 3D scans from 122 different subjects under 3 facial expressions. For appearance, we use additional 20K in-the-wild face images and apply image-based rendering to accommodate lighting variations. Comprehensive experiments demonstrate that our framework can produce high-quality 3D faces with realistic details under challenging facial expressions.

cs.CV↗

arXiv2019

Learning Semantics-aware Distance Map with Semantics Layering Network for Amodal Instance Segmentation

In this work, we demonstrate yet another approach to tackle the amodal segmentation problem. Specifically, we first introduce a new representation, namely a semantics-aware distance map (sem-dist map), to serve as our target for amodal segmentation instead of the commonly used masks and heatmaps. The sem-dist map is a kind of level-set representation, of which the different regions of an object are placed into different levels on the map according to their visibility. It is a natural extension of masks and heatmaps, where modal, amodal segmentation, as well as depth order information, are all well-described. Then we also introduce a novel convolutional neural network (CNN) architecture, which we refer to as semantic layering network, to estimate sem-dist maps layer by layer, from the global-level to the instance-level, for all objects in an image. Extensive experiments on the COCOA and D2SA datasets have demonstrated that our framework can predict amodal segmentation, occlusion and depth order with state-of-the-art performance.

cs.CV↗

arXiv2019

PPGNet: Learning Point-Pair Graph for Line Segment Detection

In this paper, we present a novel framework to detect line segments in man-made environments. Specifically, we propose to describe junctions, line segments and relationships between them with a simple graph, which is more structured and informative than end-point representation used in existing line segment detection methods. In order to extract a line segment graph from an image, we further introduce the PPGNet, a convolutional neural network that directly infers a graph from an image. We evaluate our method on published benchmarks including York Urban and Wireframe datasets. The results demonstrate that our method achieves satisfactory performance and generalizes well on all the benchmarks. The source code of our work is available at \url{https://github.com/svip-lab/PPGNet}.

cs.CV↗

arXiv2018

Existence and concentration of solution for a fractional Hamiltonian systems with positive semi-definite matrix

We study the existence of solutions for the following fractional Hamiltonian systems $$ \left\{ \begin{array}{ll} - _tD^α_{\infty}(_{-\infty}D^α_{t}u(t))-λL(t)u(t)+\nabla W(t,u(t))=0,\\[0.1cm] u\in H^α(\mathbb{R},\mathbb{R}^n), \end{array} \right. \eqno(\mbox{FHS})_λ$$ where $α\in (1/2,1)$, $t\in \mathbb{R}$, $u\in \mathbb{R}^n$, $λ>0$ is a parameter, $L\in C(\mathbb{R},\mathbb{R}^{n^2})$ is a symmetric matrix for all $t\in \mathbb{R}$, $W\in C^1(\mathbb{R} \times \mathbb{R}^n,\mathbb{R})$. Assuming that $L(t)$ is a positive semi-definite symmetric matrix for all $t\in \mathbb{R}$, that is, $L(t)\equiv 0$ is allowed to occur in some finite interval $T$ of $\mathbb{R}$, $W(t,u)$ satisfies some superquadratic conditions weaker than Ambrosetti-Rabinowitz condition, we show that (FHS)$_λ$ has a solution which vanishes on $\mathbb{R}\setminus T$ as $λ\to \infty$, and converges to some $\tilde{u}\in H^α(\R, \R^n)$. Here, $\tilde{u}\in E_{0}^α$ is a solution of the Dirichlet BVP for fractional systems on the finite interval $T$. Our results are new and improve recent results in the literature even in the case $α=1$.

math.AP↗

arXiv2016

Concentration of ground state solution for a fractional Hamiltonian Systems

In this paper we are concerned with the existence of ground states solutions for the following fractional Hamiltonian systems $$ \left\{ \begin{array}{ll} -_tD^α_\infty(_{-\infty}D^α_t u(t)) - λL(t)u(t)+\nabla W(t,u(t))=0,\\[0.1cm] u \in H^α(\mathbb{R},\mathbb{R}^n), \end{array} \right.\qquad(\hbox{FHS})_λ$$ where $α\in (1/2,1)$, $t\in \mathbb{R}$, $u\in \mathbb{R}^n$, $λ>0$ is a parameter, $L\in C(\mathbb{R},\mathbb{R}^{n^2})$ is a symmetric matrix for all $t\in \mathbb{R}$, $W\in C^1(\mathbb{R} \times \mathbb{R}^n,\mathbb{R})$ and $\nabla W(t,u)$ is the gradient of $W(t,u)$ at $u$. Assuming that $L(t)$ is a positive semi-definite symmetric matrix for all $t\in \mathbb{R}$, that is, $L(t)\equiv 0$ is allowed to occur in some finite interval $T$ of $\mathbb{R}$, $W(t,u)$ satisfies Ambrosetti-Rabinowitz condition and some other reasonable hypotheses, we show that (FHS)$_λ$ has a ground sate solution which vanishes on $\mathbb{R}\setminus T$ as $λ\to \infty$, and converges to $u\in H^α(\mathbb{R}, \mathbb{R}^n)$, where $u\in E_{0}^α$ is a ground state solution of the Dirichlet BVP for fractional systems on the finite interval $T$. Recent results are generalized and significantly improved.

math.AP↗