Search Results for author: XiaoDong Li

Found 18 papers, 9 papers with code

Low-latency Monaural Speech Enhancement with Deep Filter-bank Equalizer

no code implementations14 Feb 2022 Chengshi Zheng, Wenzhe Liu, Andong Li, Yuxuan Ke, XiaoDong Li

To improve the performance of traditional low-latency speech enhancement algorithms, a deep filter-bank equalizer (FBE) framework was proposed, which integrated a deep learning-based subband noise reduction network with a deep learning-based shortened digital filter mapping network.

Frame Speech Enhancement

A deep complex multi-frame filtering network for stereophonic acoustic echo cancellation

no code implementations3 Feb 2022 Linjuan Cheng, Chengshi Zheng, Andong Li, Yuquan Wu, Renhua Peng, XiaoDong Li

In hands-free communication system, the coupling between loudspeaker and microphone generates echo signal, which can severely influence the quality of communication.

Acoustic echo cancellation Frame

Pseudo-labelling and Meta Reweighting Learning for Image Aesthetic Quality Assessment

no code implementations8 Jan 2022 Xin Jin, Hao Lou, Huang Heng, XiaoDong Li, Shuai Cui, Xiaokun Zhang, Xiqiao Li

In the tasks of image aesthetic quality evaluation, it is difficult to reach both the high score area and low score area due to the normal distribution of aesthetic datasets.

Classification

Novelty-Driven Binary Particle Swarm Optimisation for Truss Optimisation Problems

1 code implementation15 Dec 2021 Hirad Assimi, Frank Neumann, Markus Wagner, XiaoDong Li

Topology optimisation of trusses can be formulated as a combinatorial and multi-modal problem in which locating distinct optimal designs allows practitioners to choose the best design based on their preferences.

Enhancing Column Generation by a Machine-Learning-Based Pricing Heuristic for Graph Coloring

1 code implementation8 Dec 2021 Yunzhuang Shen, Yuan Sun, XiaoDong Li, Andrew Eberhard, Andreas Ernst

In each iteration of CG, our MLPH leverages an ML model to predict the optimal solution of the pricing problem, which is then used to guide a sampling method to efficiently generate multiple high-quality columns.

Unbiased IoU for Spherical Image Object Detection

no code implementations18 Aug 2021 Qiang Zhao, Bin Chen, Hang Xu, Yike Ma, XiaoDong Li, Bailan Feng, Chenggang Yan, Feng Dai

In this paper, we first identify that spherical rectangles are unbiased bounding boxes for objects in spherical images, and then propose an analytical method for IoU calculation without any approximations.

Object Detection

Focusing on Persons: Colorizing Old Images Learning from Modern Historical Movies

1 code implementation14 Aug 2021 Xin Jin, Zhonglan Li, Ke Liu, Dongqing Zou, XiaoDong Li, Xingfan Zhu, Ziyin Zhou, Qilong Sun, Qingyu Liu

Classification sub-module supplies classifying of images according to the eras, nationalities and garment types; Parsing sub-network supplies the semantic for person contours, clothing and background in the image to achieve more accurate colorization of clothes and persons and prevent color overflow.

Classification Colorization +1

Generating Large-scale Dynamic Optimization Problem Instances Using the Generalized Moving Peaks Benchmark

1 code implementation23 Jul 2021 Mohammad Nabi Omidvar, Danial Yazdani, Juergen Branke, XiaoDong Li, Shengxiang Yang, Xin Yao

This document describes the generalized moving peaks benchmark (GMPB) and how it can be used to generate problem instances for continuous large-scale dynamic optimization problems.

Learning Linear Polytree Structural Equation Models

1 code implementation22 Jul 2021 Xingmei Lou, Yu Hu, XiaoDong Li

Under the Gaussian polytree models, we study sufficient conditions on the sample sizes for the well-known Chow-Liu algorithm to exactly recover both the skeleton and the equivalence class of the polytree, which is uniquely represented by a CPDAG.

Learning Primal Heuristics for Mixed Integer Programs

1 code implementation2 Jul 2021 Yunzhuang Shen, Yuan Sun, Andrew Eberhard, XiaoDong Li

This paper proposes a novel primal heuristic for Mixed Integer Programs, by employing machine learning techniques.

Combinatorial Optimization

A Robust Maximum Likelihood Distortionless Response Beamformer based on a Complex Generalized Gaussian Distribution

no code implementations19 Feb 2021 Weixin Meng, Chengshi Zheng, XiaoDong Li

The proposed beamformer can be regarded as a generalization of the minimum power distortionless response beamformer and its improved variations.

Speech Enhancement

Instance Space Analysis for the Car Sequencing Problem

no code implementations18 Dec 2020 Yuan Sun, Samuel Esler, Dhananjay Thiruvady, Andreas T. Ernst, XiaoDong Li, Kerri Morgan

We investigate an important research question for solving the car sequencing problem, that is, which characteristics make an instance hard to solve?

Dimensionality Reduction

A Deep Drift-Diffusion Model for Image Aesthetic Score Distribution Prediction

no code implementations15 Oct 2020 Xin Jin, Xiqiao Li, Heng Huang, XiaoDong Li, Xinghui Zhou

In this paper, we propose a Deep Drift-Diffusion (DDD) model inspired by psychologists to predict aesthetic score distribution from images.

Consistency of Spectral Clustering on Hierarchical Stochastic Block Models

no code implementations30 Apr 2020 Lihua Lei, XiaoDong Li, Xingmei Lou

We study the hierarchy of communities in real-world networks under a generic stochastic block model, in which the connection probabilities are structured in a binary tree.

Stochastic Block Model

Rapid, Robust, and Reliable Blind Deconvolution via Nonconvex Optimization

1 code implementation15 Jun 2016 XiaoDong Li, Shuyang Ling, Thomas Strohmer, Ke Wei

To the best of our knowledge, our algorithm is the first blind deconvolution algorithm that is numerically efficient, robust against noise, and comes with rigorous recovery guarantees under certain subspace conditions.

Information Theory Information Theory

Stable Principal Component Pursuit

1 code implementation14 Jan 2010 Zihan Zhou, XiaoDong Li, John Wright, Emmanuel Candes, Yi Ma

We further prove that the solution to a related convex program (a relaxed PCP) gives an estimate of the low-rank matrix that is simultaneously stable to small entrywise noise and robust to gross sparse errors.

Information Theory Information Theory

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