Search Results for author: Lei Wang

Found 267 papers, 77 papers with code

ReDro: Efficiently Learning Large-sized SPD Visual Representation

no code implementations ECCV 2020 Saimunur Rahman, Lei Wang, Changming Sun, Luping Zhou

When learning this representation in deep networks, eigen-decomposition of covariance matrix is usually needed for a key step called matrix normalisation.

Fine-Grained Image Classification

基于预训练语言模型的案件要素识别方法(A Method for Case Factor Recognition Based on Pre-trained Language Models)

no code implementations CCL 2020 Haishun Liu, Lei Wang, Yanguang Chen, Shuchen Zhang, Yuanyuan Sun, Hongfei Lin

案件要素识别指将案件描述中重要事实描述自动抽取出来, 并根据领域专家设计的要素体系进行分类, 是智慧司法领域的重要研究内容。基于传统神经网络的文本编码难以提取深层次特征, 基于阈值的多标签分类难以捕获标签间依赖关系, 因此本文提出了基于预训练语言模型的多标签文本分类模型。该模型采用以Layer-attentive策略进行特征融合的语言模型作为编码器, 使用基于LSTM的序列生成模型作为解码器。在“CAIL2019”数据集上进行实验, 该方法比基于循环神经网络的算法在F1值上最高可提升7. 6%, 在相同超参数设置下比基础语言模型(BERT)提升约3. 2%。

RotateCT: Knowledge Graph Embedding by Rotation and Coordinate Transformation in Complex Space

no code implementations COLING 2022 Yao Dong, Lei Wang, Ji Xiang, Xiaobo Guo, Yuqiang Xie

Knowledge graph embedding, which aims to learn representations of entities and relations in knowledge graphs, finds applications in various downstream tasks.

Knowledge Graph Embedding Knowledge Graphs +1

CMLCompiler: A Unified Compiler for Classical Machine Learning

no code implementations31 Jan 2023 Xu Wen, Wanling Gao, Anzheng Li, Lei Wang, Zihan Jiang, Jianfeng Zhan

Without a unified framework, the hybrid deployments of deep learning (DL) and CML also suffer from severe performance and portability issues.

High-level semantic feature matters few-shot unsupervised domain adaptation

no code implementations5 Jan 2023 Lei Yu, Wanqi Yang, Shengqi Huang, Lei Wang, Ming Yang

However, the goal of FS-UDA and FSL are relevant yet distinct, since FS-UDA aims to classify the samples in target domain rather than source domain.

Few-Shot Learning Unsupervised Domain Adaptation

A GOA-Based Fault-Tolerant Trajectory Tracking Control for an Underwater Vehicle of Multi-Thruster System without Actuator Saturation

no code implementations4 Jan 2023 Danjie Zhu, Lei Wang, Hua Zhang, Simon X. Yang

This paper proposes an intelligent fault-tolerant control (FTC) strategy to tackle the trajectory tracking problem of an underwater vehicle (UV) under thruster damage (power loss) cases and meanwhile resolve the actuator saturation brought by the vehicle's physical constraints.

Quality at the Tail

no code implementations25 Dec 2022 Zhengxin Yang, Wanling Gao, Chunjie Luo, Lei Wang, Jianfeng Zhan

However, we found that the inference quality of state-of-the-art and state-of-the-practice in practical applications has a long tail distribution.

a cognitive frequency allocation strategy for multi-carrier radar against communication interference

no code implementations23 Dec 2022 Zhao Shan, Lei Wang, PengFei Liu, Tianyao Huang, Yimin Liu

To address this challenge, we use a novel iteratively selecting technique which breaks a difficult decision task into several easy tasks.

ToL: A Tensor of List-Based Unified Computation Model

no code implementations21 Dec 2022 Hongxiao Li, Wanling Gao, Lei Wang, Jianfeng Zhan

This article presents a unified computation model with generalized expression ability and a concise set of primitive operators for programming high-level algorithms.

Domain Generalization by Learning and Removing Domain-specific Features

1 code implementation14 Dec 2022 Yu Ding, Lei Wang, Bin Liang, Shuming Liang, Yang Wang, Fang Chen

With the images output by the encoder-decoder network, another classifier is designed to learn the domain-invariant features to conduct image classification.

Domain Generalization Image Classification

Generalizing Math Word Problem Solvers via Solution Diversification

1 code implementation1 Dec 2022 Zhenwen Liang, Jipeng Zhang, Lei Wang, Yan Wang, Jie Shao, Xiangliang Zhang

In this paper, we design a new training framework for an MWP solver by introducing a solution buffer and a solution discriminator.

Recent Advances in RecBole: Extensions with more Practical Considerations

1 code implementation28 Nov 2022 Lanling Xu, Zhen Tian, Gaowei Zhang, Lei Wang, Junjie Zhang, Bowen Zheng, YiFan Li, Yupeng Hou, Xingyu Pan, Yushuo Chen, Wayne Xin Zhao, Xu Chen, Ji-Rong Wen

In order to show the recent update in RecBole, we write this technical report to introduce our latest improvements on RecBole.

Alignment-Enriched Tuning for Patch-Level Pre-trained Document Image Models

1 code implementation27 Nov 2022 Lei Wang, Jiabang He, Xing Xu, Ning Liu, Hui Liu

In this paper, we propose a new model architecture with alignment-enriched tuning (dubbed AETNet) upon pre-trained document image models, to adapt downstream tasks with the joint task-specific supervised and alignment-aware contrastive objective.

A Unified Framework for Contrastive Learning from a Perspective of Affinity Matrix

no code implementations26 Nov 2022 Wenbin Li, Meihao Kong, Xuesong Yang, Lei Wang, Jing Huo, Yang Gao, Jiebo Luo

In this study, we present a new unified contrastive learning representation framework (named UniCLR) suitable for all the above four kinds of methods from a novel perspective of basic affinity matrix.

Contrastive Learning Representation Learning

Explainable and Safe Reinforcement Learning for Autonomous Air Mobility

1 code implementation24 Nov 2022 Lei Wang, Hongyu Yang, Yi Lin, Suwan Yin, Yuankai Wu

Although DRL has achieved important advancements in this field, the existing works pay little attention to the explainability and safety issues related to DRL controllers, particularly the safety under adversarial attacks.

Adversarial Attack Q-Learning +3

A Review of Intelligent Music Generation Systems

no code implementations16 Nov 2022 Ziyi Zhao, Hanwei Liu, Song Li, Junwei Pang, Maoqing Zhang, Yi Qin, Lei Wang, Qidi Wu

Intelligent music generation, one of the most popular subfields of computer creativity, can lower the creative threshold for non-specialists and increase the efficiency of music creation.

Music Generation

Syntax-Guided Domain Adaptation for Aspect-based Sentiment Analysis

no code implementations10 Nov 2022 Anguo Dong, Cuiyun Gao, Yan Jia, Qing Liao, Xuan Wang, Lei Wang, Jing Xiao

In this work, we propose a novel Syntax-guided Domain Adaptation Model, named SDAM, for more effective cross-domain ABSA.

Aspect-Based Sentiment Analysis Domain Adaptation +1

Mitigating Popularity Bias in Recommendation with Unbalanced Interactions: A Gradient Perspective

no code implementations31 Oct 2022 Weijieying Ren, Lei Wang, Kunpeng Liu, Ruocheng Guo, Lim Ee Peng, Yanjie Fu

We present a gradient perspective to understand two negative impacts of popularity bias in recommendation model optimization: (i) the gradient direction of popular item embeddings is closer to that of positive interactions, and (ii) the magnitude of positive gradient for popular items are much greater than that of unpopular items.

Model Optimization Recommendation Systems

Uncertainty-DTW for Time Series and Sequences

no code implementations30 Oct 2022 Lei Wang, Piotr Koniusz

Dynamic Time Warping (DTW) is used for matching pairs of sequences and celebrated in applications such as forecasting the evolution of time series, clustering time series or even matching sequence pairs in few-shot action recognition.

Dynamic Time Warping Few-Shot action recognition +2

Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition

no code implementations30 Oct 2022 Lei Wang, Piotr Koniusz

To factor out misalignment between query and support sequences of 3D body joints, we propose an advanced variant of Dynamic Time Warping which jointly models each smooth path between the query and support frames to achieve simultaneously the best alignment in the temporal and simulated camera viewpoint spaces for end-to-end learning under the limited few-shot training data.

Dynamic Time Warping Few-Shot action recognition +3

Time-rEversed diffusioN tEnsor Transformer: A new TENET of Few-Shot Object Detection

1 code implementation30 Oct 2022 Shan Zhang, Naila Murray, Lei Wang, Piotr Koniusz

To address these drawbacks, we propose a Time-rEversed diffusioN tEnsor Transformer (TENET), which i) forms high-order tensor representations that capture multi-way feature occurrences that are highly discriminative, and ii) uses a transformer that dynamically extracts correlations between the query image and the entire support set, instead of a single average-pooled support embedding.

Few-Shot Object Detection object-detection

COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models

1 code implementation27 Oct 2022 Bowen Shen, Zheng Lin, Yuanxin Liu, Zhengxiao Liu, Lei Wang, Weiping Wang

Motivated by such considerations, we propose a collaborative optimization for PLMs that integrates static model compression and dynamic inference acceleration.

Model Compression

Recommendation with User Active Disclosing Willingness

no code implementations25 Oct 2022 Lei Wang, Xu Chen, Quanyu Dai, Zhenhua Dong

Recommender system has been deployed in a large amount of real-world applications, profoundly influencing people's daily life and production. Traditional recommender models mostly collect as comprehensive as possible user behaviors for accurate preference estimation.

Recommendation Systems

TPU-MLIR: A Compiler For TPU Using MLIR

1 code implementation23 Oct 2022 Pengchao Hu, Man Lu, Lei Wang, Guoyue Jiang

Multi-level intermediate representations (MLIR) show great promise for reducing the cost of building domain-specific compilers by providing a reusable and extensible compiler infrastructure.

S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attention

1 code implementation22 Oct 2022 Chiyu Zhang, Jun Yang, Lei Wang, Zaiyan Dai

This paper presents a new hierarchical vision Transformer for image style transfer, called Strips Window Attention Transformer (S2WAT), which serves as an encoder of encoder-transfer-decoder architecture.

Style Transfer

Synthetic Voice Detection and Audio Splicing Detection using SE-Res2Net-Conformer Architecture

no code implementations7 Oct 2022 Lei Wang, Benedict Yeoh, Jun Wah Ng

Synthetic voice and splicing audio clips have been generated to spoof Internet users and artificial intelligence (AI) technologies such as voice authentication.

Cloud-based Automatic Speech Recognition Systems for Southeast Asian Languages

no code implementations7 Oct 2022 Lei Wang, Rong Tong, Cheung Chi Leung, Sunil Sivadas, Chongjia Ni, Bin Ma

This paper provides an overall introduction of our Automatic Speech Recognition (ASR) systems for Southeast Asian languages.

Automatic Speech Recognition speech-recognition

Pseudo-Label Generation and Various Data Augmentation for Semi-Supervised Hyperspectral Object Detection

1 code implementation Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2022 Jun Yu, Liwen Zhang, Shenshen Du, Hao Chang, Keda Lu, Zhong Zhang, Ye Yu, Lei Wang, Qiang Ling

To overcome these difficulties, this paper first select fewer but suitable data augmentation methods to improve the accuracy of the supervised model based on the labeled training set, which is suitable for the characteristics of hyperspectral images.

Data Augmentation object-detection +3

On Embeddings and Inverse Embeddings of Input Design for Regularized System Identification

no code implementations27 Sep 2022 Biqiang Mu, Tianshi Chen, He Kong, Bo Jiang, Lei Wang, Junfeng Wu

For the emerging regularized system identification, the study on input design has just started, and it is often formulated as a non-convex optimization problem that minimizes a scalar measure of the Bayesian mean squared error matrix subject to certain constraints, and the state-of-art method is the so-called quadratic mapping and inverse embedding (QMIE) method, where a time domain inverse embedding (TDIE) is proposed to find the inverse of the quadratic mapping.

GaitFM: Fine-grained Motion Representation for Gait Recognition

no code implementations18 Sep 2022 Lei Wang, Fangfang Liang, Bincheng Wang, Bo Liu

Gait recognition aims at identifying individual-specific walking patterns, which is highly dependent on the observation of the different periodic movements of each body part.

Gait Recognition

A deep variational free energy approach to dense hydrogen

1 code implementation13 Sep 2022 Hao Xie, Zi-Hang Li, Han Wang, Linfeng Zhang, Lei Wang

We present a deep generative model-based variational free energy approach to the equations of state of dense hydrogen.

Explanation Guided Contrastive Learning for Sequential Recommendation

1 code implementation3 Sep 2022 Lei Wang, Ee-Peng Lim, Zhiwei Liu, Tianxiang Zhao

Recently, contrastive learning has been applied to the sequential recommendation task to address data sparsity caused by users with few item interactions and items with few user adoptions.

Contrastive Learning Representation Learning +1

Improving Compositional Generalization in Math Word Problem Solving

1 code implementation3 Sep 2022 Yunshi Lan, Lei Wang, Jing Jiang, Ee-Peng Lim

To improve the compositional generalization in MWP solving, we propose an iterative data augmentation method that includes diverse compositional variation into training data and could collaborate with MWP methods.

Data Augmentation Math Word Problem Solving

A Medical Semantic-Assisted Transformer for Radiographic Report Generation

no code implementations22 Aug 2022 Zhanyu Wang, Mingkang Tang, Lei Wang, Xiu Li, Luping Zhou

Automated radiographic report generation is a challenging cross-domain task that aims to automatically generate accurate and semantic-coherence reports to describe medical images.

Image Captioning Medical Report Generation

Private, Efficient, and Accurate: Protecting Models Trained by Multi-party Learning with Differential Privacy

no code implementations18 Aug 2022 Wenqiang Ruan, Mingxin Xu, Wenjing Fang, Li Wang, Lei Wang, Weili Han

Second, to reduce the accuracy loss led by differential privacy noise and the huge communication overhead of MPL, we propose two optimization methods for the training process of MPL: (1) the data-independent feature extraction method, which aims to simplify the trained model structure; (2) the local data-based global model initialization method, which aims to speed up the convergence of the model training.

Instance Image Retrieval by Learning Purely From Within the Dataset

no code implementations12 Aug 2022 Zhongyan Zhang, Lei Wang, Yang Wang, Luping Zhou, Jianjia Zhang, Peng Wang, Fang Chen

Although achieving promising results, this approach is restricted by two issues: 1) the domain gap between benchmark datasets and the dataset of a given retrieval task; 2) the required auxiliary dataset cannot be readily obtained.

Image Retrieval Retrieval +1

RDA: Reciprocal Distribution Alignment for Robust Semi-supervised Learning

1 code implementation9 Aug 2022 Yue Duan, Lei Qi, Lei Wang, Luping Zhou, Yinghuan Shi

In this work, we propose Reciprocal Distribution Alignment (RDA) to address semi-supervised learning (SSL), which is a hyperparameter-free framework that is independent of confidence threshold and works with both the matched (conventionally) and the mismatched class distributions.

Semi-Supervised Image Classification

Primitive Graph Learning for Unified Vector Mapping

no code implementations28 Jun 2022 Lei Wang, Min Dai, Jianan He, Jingwei Huang, Mingwei Sun

Then, we convert vector shape prediction, regularization, and topology reconstruction into a unique primitive graph learning problem.

Graph Learning

Attitude estimation from vector measurements: Necessary and sufficient conditions and convergent observer design

no code implementations27 Jun 2022 Bowen Yi, Lei Wang, Ian R. Manchester

The paper addresses the problem of attitude estimation for rigid bodies using (possibly time-varying) vector measurements, for which we provide a necessary and sufficient condition of distinguishability.

Constructing Cross-lingual Consumer Health Vocabulary with Word-Embedding from Comparable User Generated Content

no code implementations23 Jun 2022 Chia-Hsuan Chang, Lei Wang, Christopher C. Yang

To analyze the health consumer-generated content (HCGC) from the OHCs, identifying the colloquial medical expressions used by laypeople is a critical challenge.

TC-SfM: Robust Track-Community-Based Structure-from-Motion

no code implementations13 Jun 2022 Lei Wang, Linlin Ge, Shan Luo, Zihan Yan, Zhaopeng Cui, Jieqing Feng

Specifically, a novel structure is proposed, namely, {\textit{track-community}}, in which each community consists of a group of tracks and represents a local segment in the scene.

Community Detection

Contrastive Centroid Supervision Alleviates Domain Shift in Medical Image Classification

no code implementations31 May 2022 Wenshuo Zhou, Dalu Yang, Binghong Wu, Yehui Yang, Junde Wu, Xiaorong Wang, Lei Wang, Haifeng Huang, Yanwu Xu

Deep learning based medical imaging classification models usually suffer from the domain shift problem, where the classification performance drops when training data and real-world data differ in imaging equipment manufacturer, image acquisition protocol, patient populations, etc.

Domain Generalization Image Classification +2

Fast and Arbitrary Beam Pattern Design for RIS-Assisted Terahertz Wireless Communication

no code implementations6 May 2022 Jian Dang, Zaichen Zhang, Yewei Li, Liang Wu, Bingcheng Zhu, Lei Wang

Reconfigurable intelligent surface (RIS) can assist terahertz wireless communication to restore the fragile line-of-sight links and facilitate beam steering.

Revealing the CO2 emission reduction of ridesplitting and its determinants based on real-world data

no code implementations2 Apr 2022 Wenxiang Li, Yuanyuan Li, Ziyuan Pu, Long Cheng, Lei Wang, Linchuan Yang

Integrating the trip data with the COPERT model, this study calculates the CO2 emissions of shared rides (ridesplitting) and their substituted single rides (regular ridesourcing) to estimate the CO2 emission reduction of each ridesplitting trip.

Interpretable Machine Learning

MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularization

1 code implementation27 Mar 2022 Yue Duan, Zhen Zhao, Lei Qi, Lei Wang, Luping Zhou, Yinghuan Shi, Yang Gao

The core issue in semi-supervised learning (SSL) lies in how to effectively leverage unlabeled data, whereas most existing methods tend to put a great emphasis on the utilization of high-confidence samples yet seldom fully explore the usage of low-confidence samples.

Semi-Supervised Image Classification

Topological EEG Nonlinear Dynamics Analysis for Emotion Recognition

no code implementations14 Mar 2022 Yan Yan, Xuankun Wu, Chengdong Li, Yini He, Zhicheng Zhang, Huihui Li, Ang Li, Lei Wang

The proposed work is the first investigation in the emotion recognition oriented EEG topological feature analysis, which brought a novel insight into the brain neural system nonlinear dynamics analysis and feature extraction.

Arousal Estimation Dominance Estimation +6

Deep Transfer Learning with Graph Neural Network for Sensor-Based Human Activity Recognition

no code implementations14 Mar 2022 Yan Yan, Tianzheng Liao, Jinjin Zhao, Jiahong Wang, Liang Ma, Wei Lv, Jing Xiong, Lei Wang

Given this observation, we devised a graph-inspired deep learning approach toward the sensor-based HAR tasks, which was further used to build a deep transfer learning model toward giving a tentative solution for these two challenging problems.

Few-Shot Learning Human Activity Recognition +1

Two-stream Hierarchical Similarity Reasoning for Image-text Matching

no code implementations10 Mar 2022 Ran Chen, Hanli Wang, Lei Wang, Sam Kwong

Second, previous approaches only consider learning single-stream similarity alignment (i. e., image-to-text level or text-to-image level), which is inadequate to fully use similarity information for image-text matching.

Text Matching

CenGCN: Centralized Convolutional Networks with Vertex Imbalance for Scale-Free Graphs

no code implementations16 Feb 2022 Feng Xia, Lei Wang, Tao Tang, Xin Chen, Xiangjie Kong, Giles Oatley, Irwin King

In each non-output layer of the GCN, this framework uses a hub attention mechanism to assign new weights to connected non-hub vertices based on their common information with hub vertices.

Link Prediction

Active and Passive Hybrid Detection Method for Power CPS False Data Injection Attacks with Improved AKF and GRU-CNN

no code implementations14 Feb 2022 Zhaoyang Qu, Xiaoyong Bo, Tong Yu, Yaowei Liu, Yunchang Dong, Zhongfeng Kan, Lei Wang, Yang Li

Taking account of the fact that the existing knowledge-driven detection process for FDIAs has been in a passive detection state for a long time and ignores the advantages of data-driven active capture of features, an active and passive hybrid detection method for power CPS FDIAs with improved adaptive Kalman filter (AKF) and convolutional neural networks (CNN) is proposed in this paper.

AD-NEGF: An End-to-End Differentiable Quantum Transport Simulator for Sensitivity Analysis and Inverse Problems

no code implementations10 Feb 2022 Yingzhanghao Zhou, Xiang Chen, Peng Zhang, Jun Wang, Lei Wang, Hong Guo

Since proposed in the 70s, the Non-Equilibrium Green Function (NEGF) method has been recognized as a standard approach to quantum transport simulations.

A Novel Mix-normalization Method for Generalizable Multi-source Person Re-identification

no code implementations24 Jan 2022 Lei Qi, Lei Wang, Yinghuan Shi, Xin Geng

Different from the conventional data augmentation, the proposed domain-aware mix-normalization to enhance the diversity of features during training from the normalization view of the neural network, which can effectively alleviate the model overfitting to the source domains, so as to boost the generalization capability of the model in the unseen domain.

Data Augmentation Person Re-Identification

Indirect Adaptive Control of Nonlinearly Parameterized Nonlinear Dissipative Systems

no code implementations15 Jan 2022 Romeo Ortega, Rafael Cisneros, Lei Wang, Arjan van der Schaft

In this note we address the problem of indirect adaptive (regulation or tracking) control of nonlinear, input affine dissipative systems.

$m^\ast$ of two-dimensional electron gas: a neural canonical transformation study

1 code implementation10 Jan 2022 Hao Xie, Linfeng Zhang, Lei Wang

The quasiparticle effective mass $m^\ast$ of interacting electrons is a fundamental quantity in the Fermi liquid theory.

Kernelized Few-Shot Object Detection With Efficient Integral Aggregation

no code implementations CVPR 2022 Shan Zhang, Lei Wang, Naila Murray, Piotr Koniusz

We design a Kernelized Few-shot Object Detector by leveraging kernelized matrices computed over multiple proposal regions, which yield expressive non-linear representations whose model complexity is learned on the fly.

Few-Shot Object Detection object-detection +1

StyTr2: Image Style Transfer With Transformers

1 code implementation CVPR 2022 Yingying Deng, Fan Tang, WeiMing Dong, Chongyang Ma, Xingjia Pan, Lei Wang, Changsheng Xu

The goal of image style transfer is to render an image with artistic features guided by a style reference while maintaining the original content.

Style Transfer

Decentralized Optimization Over the Stiefel Manifold by an Approximate Augmented Lagrangian Function

no code implementations30 Dec 2021 Lei Wang, Xin Liu

In this paper, we focus on the decentralized optimization problem over the Stiefel manifold, which is defined on a connected network of $d$ agents.

Integrating Quantum Processor Device and Control Optimization in a Gradient-based Framework

no code implementations23 Dec 2021 Xiaotong Ni, Hui-Hai Zhao, Lei Wang, Feng Wu, Jianxin Chen

In a quantum processor, the device design and external controls together contribute to the quality of the target quantum operations.

3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Naïve

no code implementations23 Dec 2021 Lei Wang, Jun Liu, Piotr Koniusz

In this paper, we propose a Few-shot Learning pipeline for 3D skeleton-based action recognition by Joint tEmporal and cAmera viewpoiNt alIgnmEnt (JEANIE).

Dynamic Time Warping Few-Shot action recognition +3

A Multi-View Framework for BGP Anomaly Detection via Graph Attention Network

no code implementations23 Dec 2021 Songtao Peng, Jiaqi Nie, Xincheng Shu, Zhongyuan Ruan, Lei Wang, Yunxuan Sheng, Qi Xuan

As the default protocol for exchanging routing reachability information on the Internet, the abnormal behavior in traffic of Border Gateway Protocols (BGP) is closely related to Internet anomaly events.

Anomaly Detection Graph Attention +1

Analysis and Evaluation of Kinect-based Action Recognition Algorithms

1 code implementation16 Dec 2021 Lei Wang

Human action recognition still exists many challenging problems such as different viewpoints, occlusion, lighting conditions, human body size and the speed of action execution, although it has been widely used in different areas.

Action Recognition

Unsupervised Domain Generalization for Person Re-identification: A Domain-specific Adaptive Framework

no code implementations30 Nov 2021 Lei Qi, Lei Wang, Yinghuan Shi, Xin Geng

A significance of our work lies in that it shows the potential of unsupervised domain generalization for person ReID and sets a strong baseline for the further research on this topic.

Domain Generalization Person Re-Identification +1

Learning Dynamic Compact Memory Embedding for Deformable Visual Object Tracking

no code implementations23 Nov 2021 Pengfei Zhu, Hongtao Yu, Kaihua Zhang, Yu Wang, Shuai Zhao, Lei Wang, Tianzhu Zhang, QinGhua Hu

To address this issue, segmentation-based trackers have been proposed that employ per-pixel matching to improve the tracking performance of deformable objects effectively.

Visual Object Tracking Visual Tracking

Block-Sparse Recovery Network for Two-Dimensional Harmonic Retrieval

no code implementations15 Nov 2021 Rong Fu, Tianyao Huang, Lei Wang, Yimin Liu

As a typical signal processing problem, multidimensional harmonic retrieval (MHR) has been adapted to a wide range of applications in signal processing.


A Novel Sample-efficient Deep Reinforcement Learning with Episodic Policy Transfer for PID-Based Control in Cardiac Catheterization Robots

no code implementations28 Oct 2021 Olatunji Mumini Omisore, Toluwanimi Akinyemi, Wenke Duan, Wenjing Du, Lei Wang

Robotic catheterization is typically used for percutaneous coronary intervention procedures nowadays and it involves steering flexible endovascular tools to open up occlusion in the coronaries.

R4: A Framework for Route Representation and Route Recommendation

no code implementations20 Oct 2021 Ran Cheng, Chao Chen, Longfei Xu, Shen Li, Lei Wang, Hengbin Cui, Kaikui Liu, Xiaolong Li

For user representation, we utilize a series of historical navigation to extract user preference.

Graph Partner Neural Networks for Semi-Supervised Learning on Graphs

no code implementations18 Oct 2021 Langzhang Liang, Cuiyun Gao, Shiyi Chen, Shishi Duan, Yu Pan, Junjin Zheng, Lei Wang, Zenglin Xu

Graph Convolutional Networks (GCNs) are powerful for processing graph-structured data and have achieved state-of-the-art performance in several tasks such as node classification, link prediction, and graph classification.

Classification Graph Classification +2

High-order Tensor Pooling with Attention for Action Recognition

no code implementations11 Oct 2021 Piotr Koniusz, Lei Wang, Ke Sun

We aim at capturing high-order statistics of feature vectors formed by a neural network, and propose end-to-end second- and higher-order pooling to form a tensor descriptor.

Ranked #2 on Scene Recognition on YUP++ (using extra training data)

Action Recognition Scene Recognition

Differential Privacy with Manifold Data Dependency

no code implementations29 Sep 2021 Lei Wang, Deming Yuan, Guodong Shi

In this paper, we study dataset processing mechanisms generated by linear queries in the presence of manifold data dependency.

Distributed Zeroth-Order Optimization: Convergence Rates That Match Centralized Counterpart

no code implementations29 Sep 2021 Deming Yuan, Lei Wang, Alexandre Proutiere, Guodong Shi

Zeroth-order optimization has become increasingly important in complex optimization and machine learning when cost functions are impossible to be described in closed analytical forms.

Heterologous Normalization

no code implementations29 Sep 2021 Chunjie Luo, Jianfeng Zhan, Lei Wang, Wanling Gao

Specifically, it calculates the mean like Batch Normalization to maintain the advantage of Batch Normalization.

Network Learning in Quadratic Games from Fictitious Plays

no code implementations29 Sep 2021 Kemi Ding, Yijun Chen, Lei Wang, Xiaoqiang Ren, Guodong Shi

Next, in view of the inherent stability and sparsity constraints for the network interaction structure, we propose a stable and sparse system identification framework for learning the interaction graph from full player action observations.

A hierarchical residual network with compact triplet-center loss for sketch recognition

no code implementations28 Sep 2021 Lei Wang, Shihui Zhang, Huan He, Xiaoxiao Zhang, Yu Sang

Last but not least, the compact triplet-center loss is proposed specifically for the sketch recognition task.

Sketch Recognition

NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset

1 code implementation Findings (EMNLP) 2021 Qiyuan Zhang, Lei Wang, Sicheng Yu, Shuohang Wang, Yang Wang, Jing Jiang, Ee-Peng Lim

While diverse question answering (QA) datasets have been proposed and contributed significantly to the development of deep learning models for QA tasks, the existing datasets fall short in two aspects.

Graph Question Answering Question Answering

Progressive Hard-case Mining across Pyramid Levels for Object Detection

1 code implementation15 Sep 2021 Binghong Wu, Yehui Yang, Dalu Yang, Junde Wu, Xiaorong Wang, Haifeng Huang, Lei Wang, Yanwu Xu

Based on focal loss with ATSS-R50, our approach achieves 40. 5 AP, surpassing the state-of-the-art QFL (Quality Focal Loss, 39. 9 AP) and VFL (Varifocal Loss, 40. 1 AP).

object-detection Object Detection

LibFewShot: A Comprehensive Library for Few-shot Learning

1 code implementation10 Sep 2021 Wenbin Li, Ziyi, Wang, Xuesong Yang, Chuanqi Dong, Pinzhuo Tian, Tiexin Qin, Jing Huo, Yinghuan Shi, Lei Wang, Yang Gao, Jiebo Luo

Furthermore, based on LibFewShot, we provide comprehensive evaluations on multiple benchmarks with various backbone architectures to evaluate common pitfalls and effects of different training tricks.

Data Augmentation Few-Shot Image Classification +1

MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers

1 code implementation2 Sep 2021 Yihuai Lan, Lei Wang, Qiyuan Zhang, Yunshi Lan, Bing Tian Dai, Yan Wang, Dongxiang Zhang, Ee-Peng Lim

Over the last few years, there are a growing number of datasets and deep learning-based methods proposed for effectively solving MWPs.

Math Word Problem Solving

Improving Ranking Correlation of Supernet with Candidates Enhancement and Progressive Training

1 code implementation12 Aug 2021 Ziwei Yang, Ruyi Zhang, Zhi Yang, Xubo Yang, Lei Wang, Zheyang Li

One-shot neural architecture search (NAS) applies weight-sharing supernet to reduce the unaffordable computation overhead of automated architecture designing.

Neural Architecture Search

Cascade Bagging for Accuracy Prediction with Few Training Samples

1 code implementation12 Aug 2021 Ruyi Zhang, Ziwei Yang, Zhi Yang, Xubo Yang, Lei Wang, Zheyang Li

To alleviate this problem, we propose a novel framework to train an accuracy predictor under few training samples.

Data Augmentation Ensemble Learning +1

Few-shot Unsupervised Domain Adaptation with Image-to-class Sparse Similarity Encoding

no code implementations6 Aug 2021 Shengqi Huang, Wanqi Yang, Lei Wang, Luping Zhou, Ming Yang

Inspired by the recent local descriptor based few-shot learning (FSL), our general UDA model is fully built upon local descriptors (LDs) for image classification and domain adaptation.

Few-Shot Learning Image Classification +1

Trade When Opportunity Comes: Price Movement Forecasting via Locality-Aware Attention and Iterative Refinement Labeling

no code implementations26 Jul 2021 Liang Zeng, Lei Wang, Hui Niu, Jian Li, Ruchen Zhang, Zhonghao Dai, Dewei Zhu, Ling Wang

To address this issue, we propose a novel price movement forecasting framework, called Locality-Aware Attention and Iterative Refinement Labeling(LARA), which consists of two main components: 1)Locality-aware attention automatically extracts the potentially profitable samples by attending to surrounding class-aware label information.

Metric Learning Time Series +1

Crosslink-Net: Double-branch Encoder Segmentation Network via Fusing Vertical and Horizontal Convolutions

1 code implementation24 Jul 2021 Qian Yu, Lei Qi, Luping Zhou, Lei Wang, Yilong Yin, Yinghuan Shi, Wuzhang Wang, Yang Gao

Together, the above two schemes give rise to a novel double-branch encoder segmentation framework for medical image segmentation, namely Crosslink-Net.

Image Segmentation Medical Image Segmentation +1

Hand Image Understanding via Deep Multi-Task Learning

1 code implementation ICCV 2021 Xiong Zhang, Hongsheng Huang, Jianchao Tan, Hongmin Xu, Cheng Yang, Guozhu Peng, Lei Wang, Ji Liu

To further improve the performance of these tasks, we propose a novel Hand Image Understanding (HIU) framework to extract comprehensive information of the hand object from a single RGB image, by jointly considering the relationships between these tasks.

3D Hand Pose Estimation Multi-Task Learning +1

Triplet is All You Need with Random Mappings for Unsupervised Visual Representation Learning

no code implementations22 Jul 2021 Wenbin Li, Xuesong Yang, Meihao Kong, Lei Wang, Jing Huo, Yang Gao, Jiebo Luo

However, this type of methods, such as SimCLR and MoCo, relies heavily on a large number of negative pairs and thus requires either large batches or memory banks.

Representation Learning Self-Supervised Learning

A Self-Boosting Framework for Automated Radiographic Report Generation

no code implementations CVPR 2021 Zhanyu Wang, Luping Zhou, Lei Wang, Xiu Li

On one hand, the image-text matching branch helps to learn highly text-correlated visual features for the report generation branch to output high quality reports.

Image Captioning Medical Report Generation +2

Signal Acquisition of Luojia-1A Low Earth Orbit Navigation Augmentation System with Software Defined Receiver

no code implementations31 May 2021 Liang Chen, Xiangchen Lu, Nan Shen, Lei Wang, Yuan Zhuang, Ye Su, Deren Li, Ruizhi Chen

The performance of those integration algorithms on expanding the successful acquisition time range is verified by the real data collected from the Luojia-1A satellite.

RFCBF: enhance the performance and stability of Fast Correlation-Based Filter

no code implementations30 May 2021 Xiongshi Deng, Min Li, Lei Wang, Qikang Wan

Feature selection is a preprocessing step which plays a crucial role in the domain of machine learning and data mining.

StyTr$^2$: Image Style Transfer with Transformers

3 code implementations30 May 2021 Yingying Deng, Fan Tang, WeiMing Dong, Chongyang Ma, Xingjia Pan, Lei Wang, Changsheng Xu

The goal of image style transfer is to render an image with artistic features guided by a style reference while maintaining the original content.

Style Transfer

Hybrid gene selection approach using XGBoost and multi-objective genetic algorithm for cancer classification

no code implementations30 May 2021 Xiongshi Deng, Min Li, Shaobo Deng, Lei Wang

In the second stage, XGBoost-MOGA searches for an optimal gene subset based on the most relevant genes's group using a multi-objective optimization genetic algorithm.

Ab-initio study of interacting fermions at finite temperature with neural canonical transformation

1 code implementation18 May 2021 Hao Xie, Linfeng Zhang, Lei Wang

The variational density matrix is parametrized by a permutation equivariant many-body unitary transformation together with a discrete probabilistic model.

Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition

1 code implementation4 May 2021 Zhenyue Qin, Yang Liu, Pan Ji, Dongwoo Kim, Lei Wang, Bob McKay, Saeed Anwar, Tom Gedeon

Recent skeleton-based action recognition methods extract features from 3D joint coordinates as spatial-temporal cues, using these representations in a graph neural network for feature fusion to boost recognition performance.

Action Recognition Skeleton Based Action Recognition

Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification

no code implementations CVPR 2021 Peng Wang, Kai Han, Xiu-Shen Wei, Lei Zhang, Lei Wang

Learning discriminative image representations plays a vital role in long-tailed image classification because it can ease the classifier learning in imbalanced cases.

Classification Contrastive Learning +4

Shift-and-Balance Attention

1 code implementation24 Mar 2021 Chunjie Luo, Jianfeng Zhan, Tianshu Hao, Lei Wang, Wanling Gao

The attention branch is gated using the Sigmoid function and multiplied by the feature map's trunk branch.

DeepStyle: User Style Embedding for Authorship Attribution of Short Texts

no code implementations14 Mar 2021 Zhiqiang Hu, Roy Ka-Wei Lee, Lei Wang, Ee-Peng Lim, Bo Dai

Authorship attribution (AA), which is the task of finding the owner of a given text, is an important and widely studied research topic with many applications.

text-classification Text Classification

Network Representation Learning: From Traditional Feature Learning to Deep Learning

no code implementations7 Mar 2021 Ke Sun, Lei Wang, Bo Xu, Wenhong Zhao, Shyh Wei Teng, Feng Xia

Network representation learning (NRL) is an effective graph analytics technique and promotes users to deeply understand the hidden characteristics of graph data.

Recommendation Systems Representation Learning

Coordinated Cyber-Attack Detection Model of Cyber-Physical Power System Based on the Operating State Data Link

no code implementations27 Feb 2021 Lei Wang, Pengcheng Xu, Zhaoyang Qu, Xiaoyong Bo, Yunchang Dong, Zhenming Zhang, Yang Li

Existing coordinated cyber-attack detection methods have low detection accuracy and efficiency and poor generalization ability due to difficulties dealing with unbalanced attack data samples, high data dimensionality, and noisy data sets.

Cyber Attack Detection

HPC AI500: Representative, Repeatable and Simple HPC AI Benchmarking

no code implementations25 Feb 2021 Zihan Jiang, Wanling Gao, Fei Tang, Xingwang Xiong, Lei Wang, Chuanxin Lan, Chunjie Luo, Hongxiao Li, Jianfeng Zhan

Recent years witness a trend of applying large-scale distributed deep learning algorithms (HPC AI) in both business and scientific computing areas, whose goal is to speed up the training time to achieve a state-of-the-art quality.

Image Classification Performance

Modeling Method for the Coupling Relations of Microgrid Cyber-Physical Systems Driven by Hybrid Spatiotemporal Events

no code implementations1 Feb 2021 Xiaoyong Bo, Xiaoyu Chen, Huashun Li, Yunchang Dong, Zhaoyang Qu, Lei Wang, Yang Li

Considering the constraints of the temporal conversion of information flow and energy flow, a microgrid CPS coupling model is established, the effectiveness of which is verified by simulating false data injection attack (FDIA) scenarios.

Decision Making

Unified First-Principles Study of the Anomalous Hall Effect Based on Exact Muffin-Tin Orbitals

no code implementations29 Jan 2021 Lei Wang, Tai Min, Ke Xia

Based on the exact muffin-tin orbitals (EMTOs), we developed a first-principles method to calculate the current operators and investigated the anomalous Hall effect in bcc Fe as an example, with which we successfully separated the skew scattering contribution from the side jump and intrinsic contributions by fitting the scaling law with the introduction of sparse impurities.

Materials Science Mesoscale and Nanoscale Physics

Pruning and Quantization for Deep Neural Network Acceleration: A Survey

no code implementations24 Jan 2021 Tailin Liang, John Glossner, Lei Wang, Shaobo Shi, Xiaotong Zhang

We discuss trade-offs in element-wise, channel-wise, shape-wise, filter-wise, layer-wise and even network-wise pruning.


BV-Person: A Large-Scale Dataset for Bird-View Person Re-Identification

no code implementations ICCV 2021 Cheng Yan, Guansong Pang, Lei Wang, Jile Jiao, Xuetao Feng, Chunhua Shen, Jingjing Li

In this work we introduce a new ReID task, bird-view person ReID, which aims at searching for a person in a gallery of horizontal-view images with the query images taken from a bird's-eye view, i. e., an elevated view of an object from above.

Person Re-Identification

Optimizing Information Bottleneck in Reinforcement Learning: A Stein Variational Approach

no code implementations1 Jan 2021 Pei Yingjun, Hou Xinwen, Li Jian, Lei Wang

We also show that our method achieves better performance than VIB and mutual information neural estimation (MINE), two other popular approaches to optimize the information bottleneck framework in supervised learning.

reinforcement-learning reinforcement Learning

Pretrain-to-Finetune Adversarial Training via Sample-wise Randomized Smoothing

no code implementations1 Jan 2021 Lei Wang, Runtian Zhai, Di He, LiWei Wang, Li Jian

For certification, we carefully allocate specific robust regions for each test sample.

LoFGAN: Fusing Local Representations for Few-Shot Image Generation

1 code implementation ICCV 2021 Zheng Gu, Wenbin Li, Jing Huo, Lei Wang, Yang Gao

Given only a few available images for a novel unseen category, few-shot image generation aims to generate more data for this category.

Image Generation

Tensor Representations for Action Recognition

no code implementations28 Dec 2020 Piotr Koniusz, Lei Wang, Anoop Cherian

In this paper, we propose novel tensor representations for compactly capturing such higher-order relationships between visual features for the task of action recognition.

Action Recognition Action Recognition In Videos +1

Finite Simple Groups: Factorizations, Regular Subgroups, and Cayley Graphs

no code implementations17 Dec 2020 Cai Heng Li, Lei Wang, Binzhou Xia

This paper addresses the factorization problem of almost simple groups, studies regular subgroups of quasiprimitive permutation groups, and characterizes $s$-arc transitive Cayley graphs of finite simple groups.

Group Theory

Visual place recognition: A survey from deep learning perspective

1 code implementation28 Nov 2020 Xiwu Zhang, Lei Wang, Yan Su

Visual place recognition has attracted widespread research interest in multiple fields such as computer vision and robotics.

Loop Closure Detection Scene Understanding +3

Decoding PPP Corrections from BDS B2b Signals Using a Software-defined Receiver: an Initial Performance Evaluation

no code implementations27 Nov 2020 Xiangchen Lu, Liang Chen, Nan Shen, Lei Wang, Zhenhang Jiao, Ruizhi Chen

With the rapid development of China's BeiDou Navigation Satellite System(BDS), the application of real-time precise point positioning (RTPPP) based on BDS has become an active research area in the field of Global Navigation Satellite System (GNSS).

ASMFS: Adaptive-Similarity-based Multi-modality Feature Selection for Classification of Alzheimer's Disease

no code implementations16 Oct 2020 Yuang Shi, Chen Zu, Mei Hong, Luping Zhou, Lei Wang, Xi Wu, Jiliu Zhou, Daoqiang Zhang, Yan Wang

With the increasing amounts of high-dimensional heterogeneous data to be processed, multi-modality feature selection has become an important research direction in medical image analysis.

General Classification

Supervised Learning with Projected Entangled Pair States

no code implementations12 Sep 2020 Song Cheng, Lei Wang, Pan Zhang

Tensor networks, a model that originated from quantum physics, has been gradually generalized as efficient models in machine learning in recent years.

BIG-bench Machine Learning Tensor Networks

When Homomorphic Encryption Marries Secret Sharing: Secure Large-Scale Sparse Logistic Regression and Applications in Risk Control

no code implementations20 Aug 2020 Chaochao Chen, Jun Zhou, Li Wang, Xibin Wu, Wenjing Fang, Jin Tan, Lei Wang, Alex X. Liu, Hao Wang, Cheng Hong

In this paper, we first present CAESAR, which combines HE and SS to build secure large-scale sparse logistic regression model and achieves both efficiency and security.


Shifu2: A Network Representation Learning Based Model for Advisor-advisee Relationship Mining

no code implementations17 Aug 2020 Jiaying Liu, Feng Xia, Lei Wang, Bo Xu, Xiangjie Kong, Hanghang Tong, Irwin King

The advisor-advisee relationship represents direct knowledge heritage, and such relationship may not be readily available from academic libraries and search engines.

Representation Learning

Tropical Tensor Network for Ground States of Spin Glasses

1 code implementation16 Aug 2020 Jin-Guo Liu, Lei Wang, Pan Zhang

We present a unified exact tensor network approach to compute the ground state energy, identify the optimal configuration, and count the number of solutions for spin glasses.

Statistical Mechanics Quantum Physics Computation

MODEL: Motif-based Deep Feature Learning for Link Prediction

no code implementations9 Aug 2020 Lei Wang, Jing Ren, Bo Xu, Jian-Xin Li, Wei Luo, Feng Xia

Link prediction plays an important role in network analysis and applications.

Link Prediction

Residual-CycleGAN based Camera Adaptation for Robust Diabetic Retinopathy Screening

no code implementations31 Jul 2020 Dalu Yang, Yehui Yang, Tiantian Huang, Binghong Wu, Lei Wang, Yanwu Xu

How can we train a classification model on labeled fundus images ac-quired from only one camera brand, yet still achieves good performance on im-ages taken by other brands of cameras?

Classification Domain Adaptation +1

Robust Retinal Vessel Segmentation from a Data Augmentation Perspective

1 code implementation31 Jul 2020 Xu Sun, Huihui Fang, Yehui Yang, Dongwei Zhu, Lei Wang, Junwei Liu, Yanwu Xu

In this paper, we propose two new data augmentation modules, namely, channel-wise random Gamma correction and channel-wise random vessel augmentation.

Data Augmentation Retinal Vessel Segmentation

Graph-to-Tree Learning for Solving Math Word Problems

1 code implementation ACL 2020 Jipeng Zhang, Lei Wang, Roy Ka-Wei Lee, Yi Bin, Yan Wang, Jie Shao, Ee-Peng Lim

While the recent tree-based neural models have demonstrated promising results in generating solution expression for the math word problem (MWP), most of these models do not capture the relationships and order information among the quantities well.

Math Word Problem Solving

Human Activity Recognition based on Dynamic Spatio-Temporal Relations

no code implementations29 Jun 2020 Zhenyu Liu, Yaqiang Yao, Yan Liu, Yuening Zhu, Zhenchao Tao, Lei Wang, Yuhong Feng

In the proposed method, an activity is divided into several successive actions represented by spatio temporal patterns, and the evolution of these actions are captured by a sequential model.

Human Activity Recognition

SeqXFilter: A Memory-efficient Denoising Filter for Dynamic Vision Sensors

no code implementations2 Jun 2020 Shasha Guo, Lei Wang, Xiaofan Chen, Limeng Zhang, Ziyang Kang, Weixia Xu

We not only give the visual denoising effect of the filter but also use two metrics for quantitatively analyzing the filter's performance.


Large-Scale Secure XGB for Vertical Federated Learning

no code implementations18 May 2020 Wenjing Fang, Derun Zhao, Jin Tan, Chaochao Chen, Chaofan Yu, Li Wang, Lei Wang, Jun Zhou, Benyu Zhang

Privacy-preserving machine learning has drawn increasingly attention recently, especially with kinds of privacy regulations come into force.

BIG-bench Machine Learning Federated Learning +1

Finet: Using Fine-grained Batch Normalization to Train Light-weight Neural Networks

no code implementations14 May 2020 Chunjie Luo, Jianfeng Zhan, Lei Wang, Wanling Gao

To build light-weight network, we propose a new normalization, Fine-grained Batch Normalization (FBN).

Comparison and Benchmarking of AI Models and Frameworks on Mobile Devices

no code implementations7 May 2020 Chunjie Luo, Xiwen He, Jianfeng Zhan, Lei Wang, Wanling Gao, Jiahui Dai

Due to increasing amounts of data and compute resources, deep learning achieves many successes in various domains.

AIBench Scenario: Scenario-distilling AI Benchmarking

no code implementations6 May 2020 Wanling Gao, Fei Tang, Jianfeng Zhan, Xu Wen, Lei Wang, Zheng Cao, Chuanxin Lan, Chunjie Luo, Xiaoli Liu, Zihan Jiang

We formalize a real-world application scenario as a Directed Acyclic Graph-based model and propose the rules to distill it into a permutation of essential AI and non-AI tasks, which we call a scenario benchmark.

Continuous matrix product operator approach to finite temperature quantum states

2 code implementations27 Apr 2020 Wei Tang, Hong-Hao Tu, Lei Wang

We present an algorithm for studying quantum systems at finite temperature using continuous matrix product operator representation.

Strongly Correlated Electrons Statistical Mechanics Computational Physics

Class Distribution Alignment for Adversarial Domain Adaptation

no code implementations20 Apr 2020 Wanqi Yang, Tong Ling, Chengmei Yang, Lei Wang, Yinghuan Shi, Luping Zhou, Ming Yang

To address this issue, we propose a novel approach called Conditional ADversarial Image Translation (CADIT) to explicitly align the class distributions given samples between the two domains.

General Classification Translation +1

Secret Sharing based Secure Regressions with Applications

no code implementations10 Apr 2020 Chaochao Chen, Liang Li, Wenjing Fang, Jun Zhou, Li Wang, Lei Wang, Shuang Yang, Alex Liu, Hao Wang

Nowadays, the utilization of the ever expanding amount of data has made a huge impact on web technologies while also causing various types of security concerns.


A Noise Filter for Dynamic Vision Sensors using Self-adjusting Threshold

no code implementations8 Apr 2020 Shasha Guo, Ziyang Kang, Lei Wang, Limeng Zhang, Xiaofan Chen, Shiming Li, Weixia Xu

Neuromorphic event-based dynamic vision sensors (DVS) have much faster sampling rates and a higher dynamic range than frame-based imagers.

Emerging Technologies Signal Processing

A Neural Architecture Search based Framework for Liquid State Machine Design

no code implementations7 Apr 2020 Shuo Tian, Lianhua Qu, Kai Hu, Nan Li, Lei Wang, Weixia Xu

By exploring the design space in network architectures and parameters, recent works have demonstrated great potential for improving the accuracy of LSM model with low complexity.

Neural Architecture Search

Exploration of Input Patterns for Enhancing the Performance of Liquid State Machines

no code implementations6 Apr 2020 Shasha Guo, Lianhua Qu, Lei Wang, Shuo Tian, Shiming Li, Weixia Xu

To mitigate the difficulty in effectively dealing with huge input spaces of LSM, and to find that whether input reduction can enhance LSM performance, we explore several input patterns, namely fullscale, scanline, chessboard, and patch.

Multi-AI competing and winning against humans in iterated Rock-Paper-Scissors game

no code implementations15 Mar 2020 Lei Wang, Wenbin Huang, Yuanpeng Li, Julian Evans, Sailing He

We model and predict human competition behavior by combining many Markov Models with different fixed memory lengths (abbreviated as "multi-AI"), and develop an architecture of multi-AI with changeable parameters to adapt to different competition strategies.

Decision Making

Extended Batch Normalization

no code implementations12 Mar 2020 Chunjie Luo, Jianfeng Zhan, Lei Wang, Wanling Gao

To alleviate the problem caused by small batch size, extended batch normalization computes the standard deviation along the (N, C, H, W) dimensions, thus enlarges the number of samples from which the standard deviation is computed.

Image Classification

Industrial Scale Privacy Preserving Deep Neural Network

no code implementations11 Mar 2020 Longfei Zheng, Chaochao Chen, Yingting Liu, Bingzhe Wu, Xibin Wu, Li Wang, Lei Wang, Jun Zhou, Shuang Yang

Deep Neural Network (DNN) has been showing great potential in kinds of real-world applications such as fraud detection and distress prediction.

Fraud Detection Privacy Preserving

Exploration of Surgeons' Natural Skills for Robotic Catheterization

no code implementations6 Mar 2020 Olatunji Mumini Omisore, Wenjing Du, Tao Zhou, Shipeng Han, Kamen Ivanov, Yousef Al-Handarish, Lei Wang

Despite having the robotic catheter systems which have recently emerged as safe way of performing cardiovascular interventions, a number of important challenges are yet to be investigated.

Asymmetric Distribution Measure for Few-shot Learning

no code implementations1 Feb 2020 Wenbin Li, Lei Wang, Jing Huo, Yinghuan Shi, Yang Gao, Jiebo Luo

Given the natural asymmetric relation between a query image and a support class, we argue that an asymmetric measure is more suitable for metric-based few-shot learning.

Few-Shot Image Classification

How Distance Transform Maps Boost Segmentation CNNs: An Empirical Study

2 code implementations MIDL 2019 Jun Ma, Zhan Wei, Yiwen Zhang, Yixin Wang, Rongfei Lv, Cheng Zhu, Gaoxiang Chen, Jianan Liu, Chao Peng, Lei Wang, Yunpeng Wang, Jianan Chen

The \emph{second contribution} is that we systematically evaluated five benchmark methods on two representative public datasets.

Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors

no code implementations14 Jan 2020 Lei Wang, Piotr Koniusz

In this paper, we build on a concept of self-supervision by taking RGB frames as input to learn to predict both action concepts and auxiliary descriptors e. g., object descriptors.

 Ranked #1 on Scene Recognition on YUP++ (using extra training data)

Action Classification Action Recognition +3

Solving Quantum Statistical Mechanics with Variational Autoregressive Networks and Quantum Circuits

1 code implementation24 Dec 2019 Jin-Guo Liu, Liang Mao, Pan Zhang, Lei Wang

We extend the ability of unitary quantum circuits by interfacing it with classical autoregressive neural networks.

Quantum Physics

Yao.jl: Extensible, Efficient Framework for Quantum Algorithm Design

1 code implementation23 Dec 2019 Xiu-Zhe Luo, Jin-Guo Liu, Pan Zhang, Lei Wang

We introduce Yao, an extensible, efficient open-source framework for quantum algorithm design.

Quantum Physics Strongly Correlated Electrons Computational Physics

ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard

no code implementations20 Dec 2019 Xi Liu, Rui Zhang, Yongsheng Zhou, Qianyi Jiang, Qi Song, Nan Li, Kai Zhou, Lei Wang, Dong Wang, Minghui Liao, Mingkun Yang, Xiang Bai, Baoguang Shi, Dimosthenis Karatzas, Shijian Lu, C. V. Jawahar

21 teams submit results for Task 1, 23 teams submit results for Task 2, 24 teams submit results for Task 3, and 13 teams submit results for Task 4.

Line Detection

Application of Word2vec in Phoneme Recognition

1 code implementation17 Dec 2019 Xin Feng, Lei Wang

At the same time, in order to solve the problem of overfitting in the 61 phoneme recognition model on TIMIT dataset, we propose a new training method.

speech-recognition Speech Recognition

BenchCouncil's View on Benchmarking AI and Other Emerging Workloads

no code implementations2 Dec 2019 Jianfeng Zhan, Lei Wang, Wanling Gao, Rui Ren

This paper outlines BenchCouncil's view on the challenges, rules, and vision of benchmarking modern workloads like Big Data, AI or machine learning, and Internet Services.

Differentiable Meta-learning Model for Few-shot Semantic Segmentation

no code implementations23 Nov 2019 Pinzhuo Tian, Zhangkai Wu, Lei Qi, Lei Wang, Yinghuan Shi, Yang Gao

To address the annotation scarcity issue in some cases of semantic segmentation, there have been a few attempts to develop the segmentation model in the few-shot learning paradigm.

Few-Shot Semantic Segmentation Semantic Segmentation

Chemical-protein Interaction Extraction via Gaussian Probability Distribution and External Biomedical Knowledge

1 code implementation21 Nov 2019 Cong Sun, Zhihao Yang, Leilei Su, Lei Wang, Yin Zhang, Hongfei Lin, Jian Wang

Furthermore, the Gaussian probability distribution can effectively improve the extraction performance of sentences with overlapping relations in biomedical relation extraction tasks.

Drug Discovery Relation Extraction

Deep Learning based HEp-2 Image Classification: A Comprehensive Review

no code implementations20 Nov 2019 Saimunur Rahman, Lei Wang, Changming Sun, Luping Zhou

This paper provides a comprehensive review of the existing deep learning based HEp-2 cell image classification methods.

Classification General Classification +1

Defensive Few-shot Adversarial Learning

no code implementations16 Nov 2019 Wenbin Li, Lei Wang, Xingxing Zhang, Jing Huo, Yang Gao, Jiebo Luo

In this paper, instead of assuming such a distribution consistency, we propose to make this assumption at a task-level in the episodic training paradigm in order to better transfer the defense knowledge.

Adversarial Defense Few-Shot Learning

End-to-end speech enhancement based on discrete cosine transform

3 code implementations IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019 Chuang Geng, Lei Wang

Previous speech enhancement methods focus on estimating the short-time spectrum of speech signals due to its short-term stability.

Sound Audio and Speech Processing