Search Results for author: Tingting Wang

Found 12 papers, 2 papers with code

Weighted Graph Structure Learning with Attention Denoising for Node Classification

1 code implementation15 Mar 2025 Tingting Wang, Jiaxin Su, Haobing Liu, Ruobing Jiang

EWGSL improves node classification by redefining attention coefficients in graph attention networks to incorporate node features and edge weights.

Classification Denoising +2

Time-Graph Frequency Representation with Singular Value Decomposition for Neural Speech Enhancement

1 code implementation22 Dec 2024 Tingting Wang, Tianrui Wang, Meng Ge, Qiquan Zhang, Zirui Ge, Zhen Yang

However, most methods suffer from the alignment modeling of amplitude and phase (real and imaginary pairs) in a two-stream network framework, which inevitably incurs performance restrictions.

Speech Enhancement

A Comprehensive Survey on Root Cause Analysis in (Micro) Services: Methodologies, Challenges, and Trends

no code implementations23 Jul 2024 Tingting Wang, Guilin Qi

The complex dependencies and propagative faults inherent in microservices, characterized by a dense network of interconnected services, pose significant challenges in identifying the underlying causes of issues.

Incorporating Higher-order Structural Information for Graph Clustering

no code implementations17 Mar 2024 Qiankun Li, Haobing Liu, Ruobing Jiang, Tingting Wang

In recent years, graph convolutional network (GCN) has emerged as a powerful tool for deep clustering, integrating both graph structural information and node attributes.

Clustering Deep Clustering +1

KGroot: Enhancing Root Cause Analysis through Knowledge Graphs and Graph Convolutional Neural Networks

no code implementations11 Feb 2024 Tingting Wang, Guilin Qi, Tianxing Wu

To achieve this, KGroot uses event knowledge and the correlation between events to perform root cause reasoning by integrating knowledge graphs and GCNs for RCA.

Diagnostic Fault Detection +3

Three-Stage Cascade Framework for Blurry Video Frame Interpolation

no code implementations9 Oct 2023 Pengcheng Lei, Zaoming Yan, Tingting Wang, Faming Fang, Guixu Zhang

Besides, experiments on real-world blurry videos also indicate the good generalization ability of our model.

Deblurring Video Frame Interpolation

LostNet: A smart way for lost and find

no code implementations5 Jan 2023 Meihua Zhou, Ivan Fung, Li Yang, Nan Wan, Keke Di, Tingting Wang

Due to the enormous population growth of cities in recent years, objects are frequently lost and unclaimed on public transportation, in restaurants, or any other public areas.

Universal Graph Filter Design based on Butterworth, Chebyshev and Elliptic Functions

no code implementations28 Mar 2022 Zirui Ge, Haiyan Guo, Tingting Wang, Zhen Yang

In this paper, we propose to design universal IIR graph filters with low computational complexity by using three kinds of functions, which are Butterworth, Chebyshev, and Elliptic functions, respectively.

Optimal Fractional Fourier Filtering in Time-vertex Graphs signal processing

no code implementations12 Jan 2022 Zirui Ge, Haiyan Guo, Tingting Wang, Zhen Yang

Furthermore, the optimal time-vertex graph filter in fractional domains is also developed, using the graph fractional Laplacian operator and graph fractional Fourier transform.

Web-Scale Generic Object Detection at Microsoft Bing

no code implementations5 Jul 2021 Stephen Xi Chen, Saurajit Mukherjee, Unmesh Phadke, Tingting Wang, Junwon Park, Ravi Theja Yada

In this paper, we present Generic Object Detection (GenOD), one of the largest object detection systems deployed to a web-scale general visual search engine that can detect over 900 categories for all Microsoft Bing Visual Search queries in near real-time.

Object object-detection +1

A survey on natural language processing (nlp) and applications in insurance

no code implementations1 Oct 2020 Antoine Ly, Benno Uthayasooriyar, Tingting Wang

It brings today, many opportunities for the insurance industry. Understanding those methods and, above all, knowing how to apply them is a major challenge and key to unleash the value of text data that have been stored for many years.

An Iterative Graph Spectral Subtraction Method for Speech Enhancement

no code implementations15 Jun 2020 Xue Yan, Zhen Yang, Tingting Wang, Haiyan Guo

In this paper, we investigate the application of graph signal processing (GSP) theory in speech enhancement.

Speech Enhancement

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