Avatar

张臻

计算机科学博士

个人简介

张臻博士现任阿德莱德大学博士后研究员（导师：史勤峰教授），主要的研究方向为机器学习与计算机视觉，主要包括图神经网络、概率图模型及其在计算机视觉中的应用。 之前其于新加坡国立大学计算机科学系担任博士后研究员（导师：Lee Wee Sun教授。）2010年9月——2017年6月，在西北工业大学计算机学院攻读博士学位（导师：张艳宁教授）。在2012年12月——2014年12月，在阿德莱德大学澳大利亚视觉技术中心参与CSC联合培养博士计划（导师为：Anton van den Hengel教授以及史勤峰教授）。2006年9月——2010年7月，在西北工业大学计算机学院完成本科学习并获学士学位，在此期间曾在张艳宁教授与付中华副教授的指导下工作。

兴趣爱好

  • 机器学习
  • 计算机视觉

教育经历

  • 工学博士——计算机科学与技术, 2017

    西北工业大学计算机学院

  • 工学学士——计算机科学与技术, 2010

    西北工业大学计算机学院

发表论文

Truncated Matrix Power Iteration for Differentiable DAG Learning

Recovering underlying Directed Acyclic Graph structures (DAG) from observational data is highly challenging due to the combinatorial …
PDF

Memory-augmented Dynamic Neural Relational Inference

PDF

Factor Graph Neural Network

Most of the successful deep neural network architectures are structured, often consisting of elements like convolutional neural …
PDF 项目

Learning Deep Gradient Descent Optimization for Image Deconvolution

Dong Gong*, Zhen Zhang*, Qinfeng Shi, Anton van den Hengel, Chunhua Shen, Yanning Zhang (* Equal contribution)
PDF

Visual Relationship Detection with Low Rank Non-Negative Tensor Decomposition

We address the problem of Visual Relationship Detection (VRD) which aims to describe the relationships between pairs of objects in the …
Mohammed Haroon Dupty, Zhen Zhang, Wee Sun Lee
PDF

Deep Graphical Feature Learning for the Feature Matching Problem

The feature matching problem is a fundamental problem in various areas of computer vision including image registration, tracking and …
PDF 代码 Reviews

Convolutional Sequence to Sequence Model for Human Dynamics

Human motion modeling is a classic problem in computer vision and graphics. Challenges in modeling human motion include high …
Chen Li*, Zhen Zhang*, Wee Sun Lee, Gim Hee Lee (* Equal Contribution)
PDF 项目 Reviews

Dynamic Programming Bipartite Belief Propagation For Hyper Graph Matching

Hyper graph matching problems have drawn attention recently due to their robustness to noise, outliers, rotation and scaling variation. …
PDF 代码 项目

Solving Constrained Combinatorial Optimisation Problems Via MAP Inference Without High-order Penalties

Solving constrained combinatorial optimization problems via MAP inference is often achieved by introducing extra potential functions …
PDF 项目 Reviews

Real-time Correlation Filter Tracking by Efficient Dense Belief Propagation with Structure Preserving

Rui Yao, Shixiong Xia, Zhen Zhang, Yanning Zhang
PDF

Pairwise Matching through Max-Weight Bipartite Belief Propagation

Feature matching is a key problem in computer vision and pattern recognition. One way to encode the essential interdependence between …
PDF 代码 项目 Reviews

Joint Probabilistic Matching Using m-Best Solutions

Matching between two sets of objects is typically approached by finding the object pairs that collectively maximize the joint matching …
PDF 代码 视频

Joint Probabilistic Data Association Revisited

In this paper, we revisit the joint probabilistic data association (JPDA) technique and propose a novel solution based on recent …
PDF 代码 视频

Learning graph structure for multi-label image classification via clique generation

PDF 代码 项目

Variable Kernel Density Estimation Based Robust Regression And Its Applications

Zhen Zhang, Yanning Zhang

Constraint reduction using marginal polytope diagrams for MAP LP relaxations

PDF

项目

Factor Graph Neural Network

Abstract Most of the successful deep neural network architectures are structured, often consisting of elements like convolutional …

Graph Matching through Max-Weight Bipartite Belief Propagation

Abstract Graph matching is a key problem in computer vision and pattern recognition. One way to encode the essential interdependence …

MAP Inference Over Constrained Markov Random Field

Under construction.

Contact