Search Results for author: Hongwei Zhang

Found 9 papers, 2 papers with code

Google Landmark Retrieval 2021 Competition Third Place Solution

no code implementations9 Oct 2021 Qishen Ha, Bo Liu, Hongwei Zhang

We present our solutions to the Google Landmark Challenges 2021, for both the retrieval and the recognition tracks.

ScoreGrad: Multivariate Probabilistic Time Series Forecasting with Continuous Energy-based Generative Models

1 code implementation18 Jun 2021 Tijin Yan, Hongwei Zhang, Tong Zhou, Yufeng Zhan, Yuanqing Xia

However, many existing works can not be widely used because of the constraints of functional form of generative models or the sensitivity to hyperparameters.

Probabilistic Time Series Forecasting Time Series +1

Real-time Forecast Models for TBM Load Parameters Based on Machine Learning Methods

no code implementations12 Apr 2021 Xianjie Gao, Xueguan Song, Maolin Shi, Chao Zhang, Hongwei Zhang

In this paper, based on in-situ TBM operational data, we use the machine-learning (ML) methods to build the real-time forecast models for TBM load parameters, which can instantaneously provide the future values of the TBM load parameters as long as the current data are collected.

Dynamic Anchor Learning for Arbitrary-Oriented Object Detection

1 code implementation8 Dec 2020 Qi Ming, Zhiqiang Zhou, Lingjuan Miao, Hongwei Zhang, Linhao Li

With the newly introduced DAL, we achieve superior detection performance for arbitrary-oriented objects with only a few horizontal preset anchors.

 Ranked #1 on 2D Object Detection on DOTA (using extra training data)

Multi-Oriented Scene Text Detection Object Detection In Aerial Images

Revisiting Graph Convolutional Network on Semi-Supervised Node Classification from an Optimization Perspective

no code implementations24 Sep 2020 Hongwei Zhang, Tijin Yan, Zenjun Xie, Yuanqing Xia, Yuan Zhang

Based on our theoretical and empirical analysis, we establish a universal theoretical framework of GCN from an optimization perspective and derive a novel convolutional kernel named GCN+ which has lower parameter amount while relieving the over-smoothing inherently.

General Classification Node Classification

Stochastic Graph Recurrent Neural Network

no code implementations1 Sep 2020 Tijin Yan, Hongwei Zhang, Zirui Li, Yuanqing Xia

In addition, to alleviate KL-vanishing problem in SGRNN, a simple and interpretable structure is proposed based on the lower bound of KL-divergence.

Representation Learning Variational Inference

ELMV: an Ensemble-Learning Approach for Analyzing Electrical Health Records with Significant Missing Values

no code implementations25 Jun 2020 Lucas J. Liu, Hongwei Zhang, Jianzhong Di, Jin Chen

We propose a novel Ensemble-Learning for Missing Value (ELMV) framework, which introduces an effective approach to construct multiple subsets of the original EHR data with a much lower missing rate, as well as mobilizing a dedicated support set for the ensemble learning in the purpose of reducing the bias caused by substantial missing values.

Ensemble Learning Imputation

Adaptive Cooperative Tracking and Parameter Estimation of an Uncertain Leader over General Directed Graphs

no code implementations24 Mar 2020 Shimin Wang, Hongwei Zhang, Zhiyong Chen

This paper studies cooperative tracking problem of heterogeneous Euler-Lagrange systems with an uncertain leader, with emphasis on simultaneous adaptive estimation of the state and parameters of the leader node.

Cannot find the paper you are looking for? You can Submit a new open access paper.