Publications

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 Project

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 Code 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 Project 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 Code Project

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 Project 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 Code Project 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 Code Video

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 Code Video

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

PDF Code Project

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