Search Results for author: Xiaodong Wang

Found 52 papers, 12 papers with code

RSGT: Relational Structure Guided Temporal Relation Extraction

no code implementations COLING 2022 Jie zhou, Shenpo Dong, Hongkui Tu, Xiaodong Wang, Yong Dou

In this paper, we propose RSGT: Relational Structure Guided Temporal Relation Extraction to extract the relational structure features that can fit for both inter-sentence and intra-sentence relations.

Natural Language Understanding Temporal Relation Classification

ORES: Open-vocabulary Responsible Visual Synthesis

1 code implementation26 Aug 2023 Minheng Ni, Chenfei Wu, Xiaodong Wang, Shengming Yin, Lijuan Wang, Zicheng Liu, Nan Duan

In this work, we formalize a new task, Open-vocabulary Responsible Visual Synthesis (ORES), where the synthesis model is able to avoid forbidden visual concepts while allowing users to input any desired content.

Image Generation Language Modelling

Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models

2 code implementations8 Mar 2023 Chenfei Wu, Shengming Yin, Weizhen Qi, Xiaodong Wang, Zecheng Tang, Nan Duan

To this end, We build a system called \textbf{Visual ChatGPT}, incorporating different Visual Foundation Models, to enable the user to interact with ChatGPT by 1) sending and receiving not only languages but also images 2) providing complex visual questions or visual editing instructions that require the collaboration of multiple AI models with multi-steps.

SATBA: An Invisible Backdoor Attack Based On Spatial Attention

no code implementations25 Feb 2023 Huasong Zhou, Xiaowei Xu, Xiaodong Wang, Leon Bevan Bullock

Our attack leverages spatial attention mechanism to extract data features and generate invisible trigger patterns that are correlated with clean data.

Backdoor Attack backdoor defense +1

RD-NAS: Enhancing One-shot Supernet Ranking Ability via Ranking Distillation from Zero-cost Proxies

1 code implementation24 Jan 2023 Peijie Dong, Xin Niu, Lujun Li, Zhiliang Tian, Xiaodong Wang, Zimian Wei, Hengyue Pan, Dongsheng Li

In this paper, we propose Ranking Distillation one-shot NAS (RD-NAS) to enhance ranking consistency, which utilizes zero-cost proxies as the cheap teacher and adopts the margin ranking loss to distill the ranking knowledge.

Neural Architecture Search

Progressive Meta-Pooling Learning for Lightweight Image Classification Model

no code implementations24 Jan 2023 Peijie Dong, Xin Niu, Zhiliang Tian, Lujun Li, Xiaodong Wang, Zimian Wei, Hengyue Pan, Dongsheng Li

Practical networks for edge devices adopt shallow depth and small convolutional kernels to save memory and computational cost, which leads to a restricted receptive field.

Classification Image Classification

Unsupervised Knowledge Graph Construction and Event-centric Knowledge Infusion for Scientific NLI

no code implementations27 Oct 2022 Chenglin Wang, Yucheng Zhou, Guodong Long, Xiaodong Wang, Xiaowei Xu

Therefore, we propose an unsupervised knowledge graph construction method to build a scientific knowledge graph (SKG) without any labeled data.

graph construction Natural Language Inference

Radar-enabled ambient backscatter communications

no code implementations15 Aug 2022 Luca Venturino, Emanuele Grossi, Marco Lops, Jeremy Johnston, Xiaodong Wang

In this work, we exploit the radar clutter (i. e., the ensemble of echoes generated by the terrain and/or the surrounding objects in response to the signal emitted by a radar transmitter) as a carrier signal to enable an ambient backscatter communication from a source (tag) to a destination (reader).


MIMO OFDM Dual-Function Radar-Communication Under Error Rate and Beampattern Constraints

no code implementations24 Aug 2021 Jeremy Johnston, Luca Venturino, Emanuele Grossi, Marco Lops, Xiaodong Wang

In this work we consider a multiple-input multiple-output (MIMO) dual-function radar-communication (DFRC) system, which senses multiple spatial directions and serves multiple users.

Learning Invariant Representation with Consistency and Diversity for Semi-supervised Source Hypothesis Transfer

1 code implementation7 Jul 2021 Xiaodong Wang, Junbao Zhuo, Shuhao Cui, Shuhui Wang

Semi-supervised domain adaptation (SSDA) aims to solve tasks in target domain by utilizing transferable information learned from the available source domain and a few labeled target data.

Domain Adaptation Semi-supervised Domain Adaptation

Two stages for visual object tracking

no code implementations28 Apr 2021 Fei Chen, Fuhan Zhang, Xiaodong Wang

Then more accurate tracking results are obtained by segmentation module given the coarse state estimation in the first stage.

Image Segmentation Segmentation +3

Coarse- and fine-scale geometric information content of Multiclass Classification and implied Data-driven Intelligence

no code implementations15 Apr 2021 Fushing Hsieh, Xiaodong Wang

Under any Multiclass Classification (MCC) setting defined by a collection of labeled point-cloud specified by a feature-set, we extract only stochastic partial orderings from all possible triplets of point-cloud without explicitly measuring the three cloud-to-cloud distances.

Towards Extremely Compact RNNs for Video Recognition with Fully Decomposed Hierarchical Tucker Structure

no code implementations CVPR 2021 Miao Yin, Siyu Liao, Xiao-Yang Liu, Xiaodong Wang, Bo Yuan

Although various prior works have been proposed to reduce the RNN model sizes, executing RNN models in resource-restricted environments is still a very challenging problem.

Tensor Decomposition Video Recognition

Privacy-preserving Channel Estimation in Cell-free Hybrid Massive MIMO Systems

no code implementations26 Jan 2021 Jun Xu, Xiaodong Wang, Pengcheng Zhu, Xiaohu You

We consider a cell-free hybrid massive multiple-input multiple-output (MIMO) system with $K$ users and $M$ access points (APs), each with $N_a$ antennas and $N_r< N_a$ radio frequency (RF) chains.

Low-Rank Matrix Completion Information Theory Signal Processing Information Theory

Unraveling S&P500 stock volatility and networks -- An encoding-and-decoding approach

no code implementations23 Jan 2021 Xiaodong Wang, Fushing Hsieh

In the real data applications, we introduce the application of our approach in forecasting stock returns.

Time Series Time Series Analysis

Understanding Training Efficiency of Deep Learning Recommendation Models at Scale

no code implementations11 Nov 2020 Bilge Acun, Matthew Murphy, Xiaodong Wang, Jade Nie, Carole-Jean Wu, Kim Hazelwood

The use of GPUs has proliferated for machine learning workflows and is now considered mainstream for many deep learning models.

ADMM-Net for Communication Interference Removal in Stepped-Frequency Radar

no code implementations26 Sep 2020 Jeremy Johnston, Yinchuan Li, Marco Lops, Xiaodong Wang

Complex ADMM-Net, a complex-valued neural network architecture inspired by the alternating direction method of multipliers (ADMM), is designed for interference removal in super-resolution stepped frequency radar angle-range-doppler imaging.


Multi-mode OAM Radio Waves: Generation, Angle of Arrival Estimation and Reception With UCAs

no code implementations2 Jul 2020 Rui Chen, Wen-Xuan Long, Xiaodong Wang, Jiandong Li

To solve these problems, we propose an overall scheme of the line-of-sight multi-carrier and multi-mode OAM (LoS MCMM-OAM) communication based on uniform circular arrays (UCAs).

From learning gait signatures of many individuals to reconstructing gait dynamics of one single individual

no code implementations21 May 2020 Fushing Hsieh, Xiaodong Wang

With proper color-coding and stacking, we reconstruct and represent an individual's gait dynamics via a 3D cylinder to collectively reveal universal deterministic and stochastic structural patterns on centisecond (10 milliseconds) scale across all rhythmic cycles.

Time Series Analysis

GEVO: GPU Code Optimization using Evolutionary Computation

1 code implementation17 Apr 2020 Jhe-Yu Liou, Xiaodong Wang, Stephanie Forrest, Carole-Jean Wu

If kernel output accuracy is relaxed to tolerate up to 1% error, GEVO can find kernel variants that outperform the baseline version by an average of 51. 08%.

BIG-bench Machine Learning Handwriting Recognition +1

Deep Learning Training in Facebook Data Centers: Design of Scale-up and Scale-out Systems

no code implementations20 Mar 2020 Maxim Naumov, John Kim, Dheevatsa Mudigere, Srinivas Sridharan, Xiaodong Wang, Whitney Zhao, Serhat Yilmaz, Changkyu Kim, Hector Yuen, Mustafa Ozdal, Krishnakumar Nair, Isabel Gao, Bor-Yiing Su, Jiyan Yang, Mikhail Smelyanskiy

Large-scale training is important to ensure high performance and accuracy of machine-learning models.

Distributed, Parallel, and Cluster Computing 68T05, 68M10 H.3.3; I.2.6; C.2.1

Progressive Local Filter Pruning for Image Retrieval Acceleration

no code implementations24 Jan 2020 Xiaodong Wang, Zhedong Zheng, Yang He, Fei Yan, Zhiqiang Zeng, Yi Yang

To verify this, we evaluate our method on two widely-used image retrieval datasets, i. e., Oxford5k and Paris6K, and one person re-identification dataset, i. e., Market-1501.

Image Retrieval Network Pruning +2

DeepRecSys: A System for Optimizing End-To-End At-scale Neural Recommendation Inference

no code implementations8 Jan 2020 Udit Gupta, Samuel Hsia, Vikram Saraph, Xiaodong Wang, Brandon Reagen, Gu-Yeon Wei, Hsien-Hsin S. Lee, David Brooks, Carole-Jean Wu

Neural personalized recommendation is the corner-stone of a wide collection of cloud services and products, constituting significant compute demand of the cloud infrastructure.

Distributed, Parallel, and Cluster Computing

SubCharacter Chinese-English Neural Machine Translation with Wubi encoding

no code implementations7 Nov 2019 Wei Zhang, Feifei Lin, Xiaodong Wang, Zhenshuang Liang, Zhen Huang

However, when the translation task involves Chinese, semantic granularity remains at the word and character level, so there is still need more fine-grained translation model of Chinese.

Machine Translation Model Compression +2

mmWave/THz Channel Estimation Using Frequency-Selective Atomic Norm Minimization

no code implementations27 Aug 2019 Yicheng Xu, Hongyun Chu, Xiaodong Wang

We propose a MIMO channel estimation method for millimeter-wave (mmWave) and terahertz (THz) systems based on frequency-selective atomic norm minimization (FS-ANM).

Exploiting Parallelism Opportunities with Deep Learning Frameworks

1 code implementation13 Aug 2019 Yu Emma Wang, Carole-Jean Wu, Xiaodong Wang, Kim Hazelwood, David Brooks

State-of-the-art machine learning frameworks support a wide variety of design features to enable a flexible machine learning programming interface and to ease the programmability burden on machine learning developers.

BIG-bench Machine Learning

Deep Reinforcement Learning for Unmanned Aerial Vehicle-Assisted Vehicular Networks

no code implementations12 Jun 2019 Ming Zhu, Xiao-Yang Liu, Xiaodong Wang

Unmanned aerial vehicles (UAVs) are envisioned to complement the 5G communication infrastructure in future smart cities.

reinforcement-learning Reinforcement Learning (RL)

Decentralized Computation Offloading for Multi-User Mobile Edge Computing: A Deep Reinforcement Learning Approach

2 code implementations16 Dec 2018 Zhao Chen, Xiaodong Wang

Numerical results are illustrated to demonstrate that efficient policies can be learned at each user, and performance of the proposed DDPG based decentralized strategy outperforms the conventional deep Q-network (DQN) based discrete power control strategy and some other greedy strategies with reduced computation cost.

Edge-computing Reinforcement Learning (RL)

Real-Time Nonparametric Anomaly Detection in High-Dimensional Settings

1 code implementation14 Sep 2018 Mehmet Necip Kurt, Yasin Yilmaz, Xiaodong Wang

In case the observed data have a low intrinsic dimensionality, we learn a submanifold in which the nominal data are embedded and evaluate whether the sequentially acquired data persistently deviate from the nominal submanifold.

Anomaly Detection Vocal Bursts Intensity Prediction

A Simple and Space Efficient Segment Tree Implementation

no code implementations14 Jul 2018 Lei Wang, Xiaodong Wang

The segment tree is an extremely versatile data structure.

Data Structures and Algorithms

An Online Ride-Sharing Path Planning Strategy for Public Vehicle Systems

no code implementations27 Dec 2017 Ming Zhu, Xiao-Yang Liu, Xiaodong Wang

As efficient traffic-management platforms, public vehicle (PV) systems are envisioned to be a promising approach to solving traffic congestions and pollutions for future smart cities.

Management Scheduling

On Deterministic Sampling Patterns for Robust Low-Rank Matrix Completion

no code implementations5 Dec 2017 Morteza Ashraphijuo, Vaneet Aggarwal, Xiaodong Wang

In this letter, we study the deterministic sampling patterns for the completion of low rank matrix, when corrupted with a sparse noise, also known as robust matrix completion.

Low-Rank Matrix Completion valid

Scaled Nuclear Norm Minimization for Low-Rank Tensor Completion

no code implementations25 Jul 2017 Morteza Ashraphijuo, Xiaodong Wang

Minimizing the nuclear norm of a matrix has been shown to be very efficient in reconstructing a low-rank sampled matrix.

Rank Determination for Low-Rank Data Completion

no code implementations3 Jul 2017 Morteza Ashraphijuo, Xiaodong Wang, Vaneet Aggarwal

Moreover, for both single-view matrix and CP tensor, we are able to show that the obtained upper bound is exactly equal to the unknown rank if the lowest-rank completion is given.

Place recognition: An Overview of Vision Perspective

no code implementations17 Jun 2017 Zhiqiang Zeng, Jian Zhang, Xiaodong Wang, Yuming Chen, Chaoyang Zhu

Place recognition is one of the most fundamental topics in computer vision and robotics communities, where the task is to accurately and efficiently recognize the location of a given query image.

Image Classification Image Retrieval +4

Fourth-order Tensors with Multidimensional Discrete Transforms

4 code implementations3 May 2017 Xiao-Yang Liu, Xiaodong Wang

The multidimensional feature and huge volume of big data put urgent requirements to the development of multilinear modeling tools and efficient algorithms.

Numerical Analysis Information Theory Information Theory

Fundamental Conditions for Low-CP-Rank Tensor Completion

no code implementations31 Mar 2017 Morteza Ashraphijuo, Xiaodong Wang

Our proposed approach results in characterizing the maximum number of algebraically independent polynomials in terms of a simple geometric structure of the sampling pattern, and therefore we obtain the deterministic necessary and sufficient condition on the sampling pattern for finite completability of the sampled tensor.

Matrix Completion

Characterization of Deterministic and Probabilistic Sampling Patterns for Finite Completability of Low Tensor-Train Rank Tensor

no code implementations22 Mar 2017 Morteza Ashraphijuo, Xiaodong Wang

In this paper, we analyze the fundamental conditions for low-rank tensor completion given the separation or tensor-train (TT) rank, i. e., ranks of unfoldings.

Deterministic and Probabilistic Conditions for Finite Completability of Low-rank Multi-View Data

no code implementations3 Jan 2017 Morteza Ashraphijuo, Xiaodong Wang, Vaneet Aggarwal

We provide a deterministic necessary and sufficient condition on the sampling pattern for finite completability.

Matrix Completion

Deterministic and Probabilistic Conditions for Finite Completability of Low-Tucker-Rank Tensor

no code implementations6 Dec 2016 Morteza Ashraphijuo, Vaneet Aggarwal, Xiaodong Wang

We investigate the fundamental conditions on the sampling pattern, i. e., locations of the sampled entries, for finite completability of a low-rank tensor given some components of its Tucker rank.

Low-tubal-rank Tensor Completion using Alternating Minimization

no code implementations5 Oct 2016 Xiao-Yang Liu, Shuchin Aeron, Vaneet Aggarwal, Xiaodong Wang

The low-tubal-rank tensor model has been recently proposed for real-world multidimensional data.

Low-Rank Matrix Completion

Adaptive Sampling of RF Fingerprints for Fine-grained Indoor Localization

no code implementations10 Aug 2015 Xiao-Yang Liu, Shuchin Aeron, Vaneet Aggarwal, Xiaodong Wang, Min-You Wu

In contrast to several existing work that rely on random sampling, this paper shows that adaptivity in sampling can lead to significant improvements in localization accuracy.

Indoor Localization

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