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 …

Factor Graph Neural Network

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

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 …

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 …

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 …

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. …

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 …

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 …

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 …

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 …

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 …