Search Results for author: Wei Wang

Found 399 papers, 114 papers with code

PALM: Pre-training an Autoencoding\&Autoregressive Language Model for Context-conditioned Generation

no code implementations EMNLP 2020 Bin Bi, Chenliang Li, Chen Wu, Ming Yan, Wei Wang, Songfang Huang, Fei Huang, Luo Si

An extensive set of experiments show that PALM achieves new state-of-the-art results on a variety of language generation benchmarks covering generative question answering (Rank 1 on the official MARCO leaderboard), abstractive summarization on CNN/DailyMail as well as Gigaword, question generation on SQuAD, and conversational response generation on Cornell Movie Dialogues.

Abstractive Text Summarization Conversational Response Generation +7

HelixADMET: a robust and endpoint extensible ADMET system incorporating self-supervised knowledge transfer

no code implementations17 May 2022 Shanzhuo Zhang, Zhiyuan Yan, Yueyang Huang, Lihang Liu, Donglong He, Wei Wang, Xiaomin Fang, Xiaonan Zhang, Fan Wang, Hua Wu, Haifeng Wang

Additionally, the pre-trained model provided by H-ADMET can be fine-tuned to generate new and customised ADMET endpoints, meeting various demands of drug research and development requirements.

Drug Discovery Self-Supervised Learning +1

Intelligent Reflecting Surface Configurations for Smart Radio Using Deep Reinforcement Learning

1 code implementation11 May 2022 Wei Wang, Wei zhang

Intelligent reflecting surface (IRS) is envisioned to change the paradigm of wireless communications from "adapting to wireless channels" to "changing wireless channels".

Frame reinforcement-learning

COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personas

1 code implementation2 May 2022 Chen Xu, Piji Li, Wei Wang, Haoran Yang, Siyun Wang, Chuangbai Xiao

In this work, we propose COSPLAY(COncept Set guided PersonaLized dialogue generation Across both partY personas) that considers both parties as a "team": expressing self-persona while keeping curiosity toward the partner, leading responses around mutual personas, and finding the common ground.

Dialogue Generation

On the Equity of Nuclear Norm Maximization in Unsupervised Domain Adaptation

no code implementations12 Apr 2022 Wenju Zhang, Xiang Zhang, Qing Liao, Long Lan, Mengzhu Wang, Wei Wang, Baoyun Peng, Zhengming Ding

Nuclear norm maximization has shown the power to enhance the transferability of unsupervised domain adaptation model (UDA) in an empirical scheme.

Image Classification Unsupervised Domain Adaptation

Explicit and Implicit Pattern Relation Analysis for Discovering Actionable Negative Sequences

no code implementations4 Apr 2022 Wei Wang, Longbing Cao

A DPP-based NSP representation and actionable NSP discovery method EINSP introduces novel and significant contributions for NSA and sequence analysis: (1) it represents NSPs by a determinantal point process (DPP) based graph; (2) it quantifies actionable NSPs in terms of their statistical significance, diversity, and strength of explicit/implicit element/pattern relations; and (3) it models and measures both explicit and implicit element/pattern relations in the DPP-based NSP graph to represent direct and indirect couplings between NSP items, elements and patterns.

Decision Making

DNN-Driven Compressive Offloading for Edge-Assisted Semantic Video Segmentation

no code implementations28 Mar 2022 Xuedou Xiao, Juecheng Zhang, Wei Wang, Jianhua He, Qian Zhang

Existing compression algorithms are not fit for semantic segmentation, as the lack of obvious and concentrated regions of interest (RoIs) forces the adoption of uniform compression strategies, leading to low compression ratios or accuracy.

Optical Flow Estimation Semantic Segmentation +2

Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment

1 code implementation ACL 2022 Zijie Huang, Zheng Li, Haoming Jiang, Tianyu Cao, Hanqing Lu, Bing Yin, Karthik Subbian, Yizhou Sun, Wei Wang

In this paper, we explore multilingual KG completion, which leverages limited seed alignment as a bridge, to embrace the collective knowledge from multiple languages.

Knowledge Graph Completion

Physical Layer Security Assisted Computation Offloading in Intelligently Connected Vehicle Networks

no code implementations25 Mar 2022 Yiliang Liu, Wei Wang, Hsiao-Hwa Chen, Feng Lyu, Liangmin Wang, Weixiao Meng, Xuemin, Shen

In this paper, we propose a secure computation offloading scheme (SCOS) in intelligently connected vehicle (ICV) networks, aiming to minimize overall latency of computing via offloading part of computational tasks to nearby servers in small cell base stations (SBSs), while securing the information delivered during offloading and feedback phases via physical layer security.

On Supervised Feature Selection from High Dimensional Feature Spaces

no code implementations22 Mar 2022 Yijing Yang, Wei Wang, Hongyu Fu, C. -C. Jay Kuo

The application of machine learning to image and video data often yields a high dimensional feature space.

Efficient Training of the Memristive Deep Belief Net Immune to Non-Idealities of the Synaptic Devices

no code implementations15 Mar 2022 Wei Wang, Barak Hoffer, Tzofnat Greenberg-Toledo, Yang Li, Minhui Zou, Eric Herbelin, Ronny Ronen, Xiaoxin Xu, Yulin Zhao, Jianguo Yang, Shahar Kvatinsky

Nevertheless, the implementation of the VMM needs complex peripheral circuits and the complexity further increases since non-idealities of memristive devices prevent precise conductance tuning (especially for the online training) and largely degrade the performance of the deep neural networks (DNNs).

Deep Continuous Prompt for Contrastive Learning of Sentence Embeddings

1 code implementation14 Mar 2022 Yuxin Jiang, Wei Wang

To this end, we present a novel method which freezes the whole language model and only optimizes the prefix deep continuous prompts.

Contrastive Learning Language Modelling +2

Wasserstein Adversarial Transformer for Cloud Workload Prediction

1 code implementation12 Mar 2022 Shivani Arbat, Vinodh Kumaran Jayakumar, Jaewoo Lee, Wei Wang, In Kee Kim

Understanding the job arrival rate is crucial for accurately predicting future changes in cloud workloads and proactively provisioning and de-provisioning VMs for hosting the applications.

Time Series Time Series Forecasting

Amplitude-Constrained Constellation and Reflection Pattern Designs for Directional Backscatter Communications Using Programmable Metasurface

no code implementations8 Mar 2022 Wei Wang, Bincheng Zhu, Yongming Huang, Wei zhang

For constellation design, we adopt the amplitude and phase-shift keying (APSK) constellation and optimize the parameters of APSK such as ring number, ring radius, and inter-ring phase difference.

Sensing as A Service in 6G Perceptive Networks: A Unified Framework for ISAC Resource Allocation

no code implementations21 Feb 2022 Fuwang Dong, Fan Liu, Yuanhao Cui, Wei Wang, Kaifeng Han, Zhiqin Wang

Then, we establish a unified framework for ISAC resource allocation, where the fairness and the comprehensiveness optimization criteria are considered for the aforementioned sensing services.


Disentangle Saliency Detection into Cascaded Detail Modeling and Body Filling

no code implementations8 Feb 2022 Yue Song, Hao Tang, Nicu Sebe, Wei Wang

Specifically, the detail modeling focuses on capturing the object edges by supervision of explicitly decomposed detail label that consists of the pixels that are nested on the edge and near the edge.

Object Detection Saliency Detection +1

Fast Differentiable Matrix Square Root and Inverse Square Root

1 code implementation29 Jan 2022 Yue Song, Nicu Sebe, Wei Wang

Computing the matrix square root and its inverse in a differentiable manner is important in a variety of computer vision tasks.

Style Transfer Video Recognition

Reinforcement Learning Based Query Vertex Ordering Model for Subgraph Matching

no code implementations25 Jan 2022 Hanchen Wang, Ying Zhang, Lu Qin, Wei Wang, Wenjie Zhang, Xuemin Lin

In recent years, many advanced techniques for query vertex ordering (i. e., matching order generation) have been proposed to reduce the unpromising intermediate results according to the preset heuristic rules.


Forgery Attack Detection in Surveillance Video Streams Using Wi-Fi Channel State Information

no code implementations24 Jan 2022 Yong Huang, Xiang Li, Wei Wang, Tao Jiang, Qian Zhang

The cybersecurity breaches expose surveillance video streams to forgery attacks, under which authentic streams are falsified to hide unauthorized activities.

Time Series Video Forensics

Fast Differentiable Matrix Square Root

1 code implementation ICLR 2022 Yue Song, Nicu Sebe, Wei Wang

Previous methods either adopt the Singular Value Decomposition (SVD) to explicitly factorize the matrix or use the Newton-Schulz iteration (NS iteration) to derive the approximate solution.

A three-dimensional dual-domain deep network for high-pitch and sparse helical CT reconstruction

no code implementations7 Jan 2022 Wei Wang, Xiang-Gen Xia, Chuanjiang He, Zemin Ren, Jian Lu

By embedding our implementation into the network, we propose an end-to-end deep network for the high pitch helical CT reconstruction with sparse detectors.

Computer Vision Based Parking Optimization System

no code implementations1 Jan 2022 Siddharth Chandrasekaran, Jeffrey Matthew Reginald, Wei Wang, Ting Zhu

One of these problems is the occupancy detection of the parking slots in a distributed parking ecosystem.

Machine Learning and Artificial Intelligence in Next-Generation Wireless Network

no code implementations30 Dec 2021 Wafeeq Iqbal, Wei Wang, Ting Zhu

The limited capability of the traditional tools will not allow the network providers to fulfill the demands of the network's subscribers in the future.

Chatbot for fitness management using IBM Watson

no code implementations30 Dec 2021 Sai Rugved Lola, Rahul Dhadvai, Wei Wang, Ting Zhu

Chatbots have revolutionized the way humans interact with computer systems and they have substituted the use of service agents, call-center representatives etc.

Chatbot Natural Language Understanding

3D-Aware Semantic-Guided Generative Model for Human Synthesis

no code implementations2 Dec 2021 Jichao Zhang, Enver Sangineto, Hao Tang, Aliaksandr Siarohin, Zhun Zhong, Nicu Sebe, Wei Wang

However, they usually struggle to generate high-quality images representing non-rigid objects, such as the human body, which is of a great interest for many computer graphics applications.

3D-Aware Image Synthesis

Weakly-Supervised Video Object Grounding via Causal Intervention

no code implementations1 Dec 2021 Wei Wang, Junyu Gao, Changsheng Xu

With this in mind, we design a unified causal framework to learn the deconfounded object-relevant association for more accurate and robust video object grounding.

Contrastive Learning

Structure-Aware Label Smoothing for Graph Neural Networks

no code implementations1 Dec 2021 Yiwei Wang, Yujun Cai, Yuxuan Liang, Wei Wang, Henghui Ding, Muhao Chen, Jing Tang, Bryan Hooi

Representing a label distribution as a one-hot vector is a common practice in training node classification models.

Classification Node Classification

KS-GNN: Keywords Search over Incomplete Graphs via Graphs Neural Network

no code implementations NeurIPS 2021 Yu Hao, Xin Cao, Yufan Sheng, Yixiang Fang, Wei Wang

Keyword search is a fundamental task to retrieve information that is the most relevant to the query keywords.

Measuring Vulnerabilities of Malware Detectors with Explainability-Guided Evasion Attacks

no code implementations19 Nov 2021 Ruoxi Sun, Wei Wang, Tian Dong, Shaofeng Li, Minhui Xue, Gareth Tyson, Haojin Zhu, Mingyu Guo, Surya Nepal

We find that (i) commercial antivirus engines are vulnerable to AMM-guided manipulated samples; (ii) the ability of a manipulated malware generated using one detector to evade detection by another detector (i. e., transferability) depends on the overlap of features with large AMM values between the different detectors; and (iii) AMM values effectively measure the importance of features and explain the ability to evade detection.

Online Meta Adaptation for Variable-Rate Learned Image Compression

no code implementations16 Nov 2021 Wei Jiang, Wei Wang, Songnan Li, Shan Liu

This work addresses two major issues of end-to-end learned image compression (LIC) based on deep neural networks: variable-rate learning where separate networks are required to generate compressed images with varying qualities, and the train-test mismatch between differentiable approximate quantization and true hard quantization.

Image Compression Meta-Learning +2

Boundary Distribution Estimation to Precise Object Detection

no code implementations2 Nov 2021 Haoran Zhou, Hang Huang, Rui Zhao, Wei Wang, Qingguo Zhou

In principal modern detectors, the task of object localization is implemented by the box subnet which concentrates on bounding box regression.

Object Detection Object Localization

TPSNet: Thin-Plate-Spline Representation for Arbitrary Shape Scene Text Detection

no code implementations25 Oct 2021 Wei Wang

The research focus of scene text detection has shifted to arbitrary shape text in recent years, in which text representation is a fundamental problem.

Scene Text Detection Scene Text Recognition

Bi-integrative analysis of two-dimensional heterogeneous panel data model

no code implementations20 Oct 2021 Wei Wang, Xiaodong Yan, Yanyan Ren, Zhijie Xiao

Heterogeneous panel data models that allow the coefficients to vary across individuals and/or change over time have received increasingly more attention in statistics and econometrics.

MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction

1 code implementation Findings (ACL) 2022 Linhan Zhang, Qian Chen, Wen Wang, Chong Deng, Shiliang Zhang, Bing Li, Wei Wang, Xin Cao

In this work, we propose a novel unsupervised embedding-based KPE approach, Masked Document Embedding Rank (MDERank), to address this problem by leveraging a mask strategy and ranking candidates by the similarity between embeddings of the source document and the masked document.

Contrastive Learning Document Embedding +3

Tao: A Learning Framework for Adaptive Nearest Neighbor Search using Static Features Only

no code implementations2 Oct 2021 Kaixiang Yang, Hongya Wang, Bo Xu, Wei Wang, Yingyuan Xiao, Ming Du, Junfeng Zhou

In the middle of query execution, AdaptNN collects a number of runtime features and predicts termination condition for each individual query, by which better end-to-end latency is attained.

Information Retrieval

Directional Domain Generalization

no code implementations29 Sep 2021 Wei Wang, Jiaqi Li, Ruizhi Pu, Gezheng Xu, Fan Zhou, Changjian Shui, Charles Ling, Boyu Wang

Domain generalization aims to learn a predictive model from multiple different but related source tasks that can generalize well to a target task without the need of accessing any target data.

Domain Generalization Meta-Learning

Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations

no code implementations29 Sep 2021 Wentao Chen, Zhang Zhang, Wei Wang, Liang Wang, Zilei Wang, Tieniu Tan

Few-shot learning (FSL) aims to recognize novel query examples with a small support set through leveraging prior knowledge learned from a large-scale training set.

Few-Shot Learning

The Report on China-Spain Joint Clinical Testing for Rapid COVID-19 Risk Screening by Eye-region Manifestations

no code implementations18 Sep 2021 Yanwei Fu, Feng Li, Paula boned Fustel, Lei Zhao, Lijie Jia, Haojie Zheng, Qiang Sun, Shisong Rong, Haicheng Tang, xiangyang xue, Li Yang, Hong Li, Jiao Xie Wenxuan Wang, Yuan Li, Wei Wang, Yantao Pei, Jianmin Wang, Xiuqi Wu, Yanhua Zheng, Hongxia Tian, Mengwei Gu

The image-level performance of COVID-19 prescreening model in the China-Spain multicenter study achieved an AUC of 0. 913 (95% CI, 0. 898-0. 927), with a sensitivity of 0. 695 (95% CI, 0. 643-0. 748), a specificity of 0. 904 (95% CI, 0. 891 -0. 919), an accuracy of 0. 875(0. 861-0. 889), and a F1 of 0. 611(0. 568-0. 655).

Dense Semantic Contrast for Self-Supervised Visual Representation Learning

no code implementations16 Sep 2021 Xiaoni Li, Yu Zhou, Yifei Zhang, Aoting Zhang, Wei Wang, Ning Jiang, Haiying Wu, Weiping Wang

Concretely, these downstream tasks require more accurate representation, in other words, the pixels from the same object must belong to a shared semantic category, which is lacking in the previous methods.

Contrastive Learning Instance Segmentation +3

Towards Fine-Grained Reasoning for Fake News Detection

1 code implementation13 Sep 2021 Yiqiao Jin, Xiting Wang, Ruichao Yang, Yizhou Sun, Wei Wang, Hao Liao, Xing Xie

The detection of fake news often requires sophisticated reasoning skills, such as logically combining information by considering word-level subtle clues.

Fake News Detection

SO-SLAM: Semantic Object SLAM with Scale Proportional and Symmetrical Texture Constraints

1 code implementation10 Sep 2021 Ziwei Liao, Yutong Hu, Jiadong Zhang, Xianyu Qi, XiaoYu Zhang, Wei Wang

Object SLAM introduces the concept of objects into Simultaneous Localization and Mapping (SLAM) and helps understand indoor scenes for mobile robots and object-level interactive applications.

Object SLAM

Towards Robust Cross-domain Image Understanding with Unsupervised Noise Removal

no code implementations9 Sep 2021 Lei Zhu, Zhaojing Luo, Wei Wang, Meihui Zhang, Gang Chen, Kaiping Zheng

In multimedia analysis, domain adaptation studies the problem of cross-domain knowledge transfer from a label rich source domain to a label scarce target domain, thus potentially alleviates the annotation requirement for deep learning models.

Domain Adaptation Transfer Learning

System Optimization in Synchronous Federated Training: A Survey

no code implementations9 Sep 2021 Zhifeng Jiang, Wei Wang

The unprecedented demand for collaborative machine learning in a privacy-preserving manner gives rise to a novel machine learning paradigm called federated learning (FL).

Federated Learning

PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition

1 code implementation9 Sep 2021 Zhi Qiao, Yu Zhou, Jin Wei, Wei Wang, Yuan Zhang, Ning Jiang, Hongbin Wang, Weiping Wang

In this paper, we propose a Parallel, Iterative and Mimicking Network (PIMNet) to balance accuracy and efficiency.

Scene Text Recognition

AppQ: Warm-starting App Recommendation Based on View Graphs

no code implementations8 Sep 2021 Dan Su, Jiqiang Liu, Sencun Zhu, Xiaoyang Wang, Wei Wang, Xiangliang Zhang

In this work, we propose AppQ, a novel app quality grading and recommendation system that extracts inborn features of apps based on app source code.

Recommendation Systems

Recommend for a Reason: Unlocking the Power of Unsupervised Aspect-Sentiment Co-Extraction

no code implementations Findings (EMNLP) 2021 Zeyu Li, Wei Cheng, Reema Kshetramade, John Houser, Haifeng Chen, Wei Wang

Compliments and concerns in reviews are valuable for understanding users' shopping interests and their opinions with respect to specific aspects of certain items.

Powering Comparative Classification with Sentiment Analysis via Domain Adaptive Knowledge Transfer

1 code implementation EMNLP 2021 Zeyu Li, Yilong Qin, Zihan Liu, Wei Wang

We study Comparative Preference Classification (CPC) which aims at predicting whether a preference comparison exists between two entities in a given sentence and, if so, which entity is preferred over the other.

Question Answering Sentiment Analysis +1

Sent2Span: Span Detection for PICO Extraction in the Biomedical Text without Span Annotations

1 code implementation Findings (EMNLP) 2021 Shifeng Liu, Yifang Sun, Bing Li, Wei Wang, Florence T. Bourgeois, Adam G. Dunn

The rapid growth in published clinical trials makes it difficult to maintain up-to-date systematic reviews, which requires finding all relevant trials.


RiWNet: A moving object instance segmentation Network being Robust in adverse Weather conditions

no code implementations4 Sep 2021 Chenjie Wang, Chengyuan Li, Bin Luo, Wei Wang, Jun Liu

Then we extend SOLOV2 to capture temporal information in video to learn motion information, and propose a moving object instance segmentation network with RiWFPN called RiWNet.

Instance Segmentation Semantic Segmentation

FLASHE: Additively Symmetric Homomorphic Encryption for Cross-Silo Federated Learning

no code implementations2 Sep 2021 Zhifeng Jiang, Wei Wang, Yang Liu

Homomorphic encryption (HE) is a promising privacy-preserving technique for cross-silo federated learning (FL), where organizations perform collaborative model training on decentralized data.

Federated Learning

Self-supervised Representation Learning for Trip Recommendation

no code implementations2 Sep 2021 Qiang Gao, Wei Wang, Kunpeng Zhang, Xin Yang, Congcong Miao

Although recent deep recursive models (e. g., RNN) are capable of alleviating these concerns, existing solutions hardly recognize the practical reality, such as the diversity of tourist demands, uncertainties in the trip generation, and the complex visiting preference.

Contrastive Learning Representation Learning

Grid-VLP: Revisiting Grid Features for Vision-Language Pre-training

no code implementations21 Aug 2021 Ming Yan, Haiyang Xu, Chenliang Li, Bin Bi, Junfeng Tian, Min Gui, Wei Wang

Existing approaches to vision-language pre-training (VLP) heavily rely on an object detector based on bounding boxes (regions), where salient objects are first detected from images and then a Transformer-based model is used for cross-modal fusion.

Object Detection

Online Evolutionary Batch Size Orchestration for Scheduling Deep Learning Workloads in GPU Clusters

no code implementations8 Aug 2021 Zhengda Bian, Shenggui Li, Wei Wang, Yang You

ONES automatically manages the elasticity of each job based on the training batch size, so as to maximize GPU utilization and improve scheduling efficiency.

A review on vision-based analysis for automatic dietary assessment

no code implementations6 Aug 2021 Wei Wang, Weiqing Min, TianHao Li, Xiaoxiao Dong, Haisheng Li, Shuqiang Jiang

We also provide the latest ideas for future development of VBDA, e. g., fine-grained food analysis and accurate volume estimation.

Food Recognition

Sentence Semantic Regression for Text Generation

no code implementations6 Aug 2021 Wei Wang, Piji Li, Hai-Tao Zheng

In the phase of surface realization, a mixed-granularity sentence decoder is designed to generate text with better consistency by jointly incorporating the predicted sentence-level main idea as well as the preceding contextual token-level information.

Dialogue Generation Language Modelling

Optimal Transport for Unsupervised Denoising Learning

1 code implementation4 Aug 2021 Wei Wang, Fei Wen, Zeyu Yan, Peilin Liu

Toward answering this question, this work proposes a criterion for unsupervised denoising learning based on the optimal transport theory.


SINGA-Easy: An Easy-to-Use Framework for MultiModal Analysis

no code implementations3 Aug 2021 Naili Xing, Sai Ho Yeung, ChengHao Cai, Teck Khim Ng, Wei Wang, Kaiyuan Yang, Nan Yang, Meihui Zhang, Gang Chen, Beng Chin Ooi

Specifically, in terms of usability, it is demanding for non-experts to implement deep learning models, obtain the right settings for the entire machine learning pipeline, manage models and datasets, and exploit external data sources all together.

Image Classification

Addressing Semantic Drift in Generative Question Answering with Auxiliary Extraction

no code implementations ACL 2021 Chenliang Li, Bin Bi, Ming Yan, Wei Wang, Songfang Huang

This work focuses on generative QA which aims to generate an abstractive answer to a given question instead of extracting an answer span from a provided passage.

Generative Question Answering Machine Reading Comprehension

Automatic Vocabulary and Graph Verification for Accurate Loop Closure Detection

no code implementations30 Jul 2021 Haosong Yue, Jinyu Miao, Weihai Chen, Wei Wang, Fanghong Guo, Zhengguo Li

Localizing pre-visited places during long-term simultaneous localization and mapping, i. e. loop closure detection (LCD), is a crucial technique to correct accumulated inconsistencies.

Loop Closure Detection Simultaneous Localization and Mapping

A Signal Detection Scheme Based on Deep Learning in OFDM Systems

no code implementations24 Jul 2021 Guangliang Pan, Zitong Liu, Wei Wang, Minglei Li

Simulation results show that the DDLSD scheme outperforms the existing traditional methods in terms of improving channel estimation and signal detection performance.

Time Series

A Systematical Solution for Face De-identification

no code implementations19 Jul 2021 Songlin Yang, Wei Wang, Yuehua Cheng, Jing Dong

Through this, we can construct unrestricted adversarial image to decrease ID similarity recognized by model.

De-identification Disentanglement +1

GuideBoot: Guided Bootstrap for Deep Contextual Bandits

no code implementations18 Jul 2021 Feiyang Pan, Haoming Li, Xiang Ao, Wei Wang, Yanrong Kang, Ao Tan, Qing He

The proposed method is efficient as it can make decisions on-the-fly by utilizing only one randomly chosen model, but is also effective as we show that it can be viewed as a non-Bayesian approximation of Thompson sampling.

Multi-Armed Bandits

Drug-Target Interaction Prediction with Graph Attention networks

1 code implementation10 Jul 2021 Haiyang Wang, Guangyu Zhou, SiQi Liu, Jyun-Yu Jiang, Wei Wang

For better learning and interpreting the DTI topological structure and the similarity, it is desirable to have methods specifically for predicting interactions from the graph structure.

Graph Attention

Transformer Network for Significant Stenosis Detection in CCTA of Coronary Arteries

1 code implementation7 Jul 2021 Xinghua Ma, Gongning Luo, Wei Wang, Kuanquan Wang

However, the complexity of coronary artery plaques that cause CAD makes the automatic detection of coronary artery stenosis in Coronary CT angiography (CCTA) a difficult task.

Clinical Named Entity Recognition using Contextualized Token Representations

no code implementations23 Jun 2021 Yichao Zhou, Chelsea Ju, J. Harry Caufield, Kevin Shih, Calvin Chen, Yizhou Sun, Kai-Wei Chang, Peipei Ping, Wei Wang

To facilitate various downstream applications using clinical case reports (CCRs), we pre-train two deep contextualized language models, Clinical Embeddings from Language Model (C-ELMo) and Clinical Contextual String Embeddings (C-Flair) using the clinical-related corpus from the PubMed Central.

Language Modelling Named Entity Recognition +1

Analyzing Adversarial Robustness of Deep Neural Networks in Pixel Space: a Semantic Perspective

no code implementations18 Jun 2021 Lina Wang, Xingshu Chen, Yulong Wang, Yawei Yue, Yi Zhu, Xuemei Zeng, Wei Wang

Previous works study the adversarial robustness of image classifiers on image level and use all the pixel information in an image indiscriminately, lacking of exploration of regions with different semantic meanings in the pixel space of an image.

Adversarial Robustness

Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterion

no code implementations17 Jun 2021 Xian-Jin Gui, Wei Wang, Zhang-Hao Tian

However, there are few theoretical analyses to explain why these methods could learn well from noisy labels.

Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation

no code implementations CVPR 2021 Yahui Liu, Enver Sangineto, Yajing Chen, Linchao Bao, Haoxian Zhang, Nicu Sebe, Bruno Lepri, Wei Wang, Marco De Nadai

In this paper, we propose a new training protocol based on three specific losses which help a translation network to learn a smooth and disentangled latent style space in which: 1) Both intra- and inter-domain interpolations correspond to gradual changes in the generated images and 2) The content of the source image is better preserved during the translation.

Translation Unsupervised Image-To-Image Translation

Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression

no code implementations15 Jun 2021 Sheng Lin, Wei Jiang, Wei Wang, Kaidi Xu, Yanzhi Wang, Shan Liu, Songnan Li

Compressing Deep Neural Network (DNN) models to alleviate the storage and computation requirements is essential for practical applications, especially for resource limited devices.

Neural Network Compression

Graphical Gaussian Process Regression Model for Aqueous Solvation Free Energy Prediction of Organic Molecules in Redox Flow Battery

no code implementations15 Jun 2021 Peiyuan Gao, Xiu Yang, Yu-Hang Tang, Muqing Zheng, Amity Anderson, Vijayakumar Murugesan, Aaron Hollas, Wei Wang

The solvation free energy of organic molecules is a critical parameter in determining emergent properties such as solubility, liquid-phase equilibrium constants, and pKa and redox potentials in an organic redox flow battery.

Dimensionality Reduction

Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition

1 code implementation13 Jun 2021 Mengmeng Cui, Wei Wang, Jinjin Zhang, Liang Wang

However, for the current state-of-the-art(SOTA) methods, there is room for improvement in terms of the efficient usage of local visual and global context information of the input text image, as well as the robust correlation between the scene processing module(encoder) and the text processing module(decoder).

Scene Text Recognition

Rapid COVID-19 Risk Screening by Eye-region Manifestations

no code implementations12 Jun 2021 Yanwei Fu, Lei Zhao, Haojie Zheng, Qiang Sun, Li Yang, Hong Li, Jiao Xie, xiangyang xue, Feng Li, Yuan Li, Wei Wang, Yantao Pei, Jianmin Wang, Xiuqi Wu, Yanhua Zheng, Hongxia Tian Mengwei Gu1

It is still nontrivial to develop a new fast COVID-19 screening method with the easier access and lower cost, due to the technical and cost limitations of the current testing methods in the medical resource-poor districts.

Self-supervised and Supervised Joint Training for Resource-rich Machine Translation

no code implementations8 Jun 2021 Yong Cheng, Wei Wang, Lu Jiang, Wolfgang Macherey

Self-supervised pre-training of text representations has been successfully applied to low-resource Neural Machine Translation (NMT).

Low-Resource Neural Machine Translation Translation

Language Scaling for Universal Suggested Replies Model

no code implementations NAACL 2021 Qianlan Ying, Payal Bajaj, Budhaditya Deb, Yu Yang, Wei Wang, Bojia Lin, Milad Shokouhi, Xia Song, Yang Yang, Daxin Jiang

Faced with increased compute requirements and low resources for language expansion, we build a single universal model for improving the quality and reducing run-time costs of our production system.

Continual Learning Cross-Lingual Transfer

Multi-Grained Knowledge Distillation for Named Entity Recognition

1 code implementation NAACL 2021 Xuan Zhou, Xiao Zhang, Chenyang Tao, Junya Chen, Bing Xu, Wei Wang, Jing Xiao

To maximally assimilate knowledge into the student model, we propose a multi-grained distillation scheme, which integrates cross entropy involved in conditional random field (CRF) and fuzzy learning. To validate the effectiveness of our proposal, we conducted a comprehensive evaluation on five NER benchmarks, reporting cross-the-board performance gains relative to competing prior-arts.

Knowledge Distillation Named Entity Recognition +1

Mixup for Node and Graph Classification

1 code implementation1 Jun 2021 Yiwei Wang, Wei Wang, Yuxuan Liang, Yujun Cai, Bryan Hooi

In this work, we propose the Mixup methods for two fundamental tasks in graph learning: node and graph classification.

Classification Data Augmentation +3

Transferable Sparse Adversarial Attack

1 code implementation31 May 2021 Ziwen He, Wei Wang, Jing Dong, Tieniu Tan

The experiment shows that our method has improved the transferability by a large margin under a similar sparsity setting compared with state-of-the-art methods.

Adversarial Attack Quantization

Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization

1 code implementation31 May 2021 Jichao Zhang, Aliaksandr Siarohin, Hao Tang, Jingjing Chen, Enver Sangineto, Wei Wang, Nicu Sebe

Controllable person image generation aims to produce realistic human images with desirable attributes (e. g., the given pose, cloth textures or hair style).

Image-to-Image Translation Pose Transfer +1

Predicting Aqueous Solubility of Organic Molecules Using Deep Learning Models with Varied Molecular Representations

1 code implementation26 May 2021 Gihan Panapitiya, Michael Girard, Aaron Hollas, Vijay Murugesan, Wei Wang, Emily Saldanha

Determining the aqueous solubility of molecules is a vital step in many pharmaceutical, environmental, and energy storage applications.

Transfer Learning

CFA-Net: Controllable Face Anonymization Network with Identity Representation Manipulation

no code implementations24 May 2021 Tianxiang Ma, Dongze Li, Wei Wang, Jing Dong

We propose a Controllable Face Anonymization Network (CFA-Net), a novel approach that can anonymize the identity of given faces in images and videos, based on a generator that can disentangle face identity from other image contents.

De-identification Face Anonymization

Substitutional Neural Image Compression

no code implementations16 May 2021 Xiao Wang, Wei Jiang, Wei Wang, Shan Liu, Brian Kulis, Peter Chin

The key idea is to replace the image to be compressed with a substitutional one that outperforms the original one in a desired way.

Image Compression

AnomalyHop: An SSL-based Image Anomaly Localization Method

1 code implementation8 May 2021 Kaitai Zhang, Bin Wang, Wei Wang, Fahad Sohrab, Moncef Gabbouj, C. -C. Jay Kuo

An image anomaly localization method based on the successive subspace learning (SSL) framework, called AnomalyHop, is proposed in this work.

Adapting by Pruning: A Case Study on BERT

1 code implementation7 May 2021 Yang Gao, Nicolo Colombo, Wei Wang

Adapting pre-trained neural models to downstream tasks has become the standard practice for obtaining high-quality models.

ER-IQA: Boosting Perceptual Quality Assessment Using External Reference Images

no code implementations6 May 2021 Jingyu Guo, Wei Wang, Wenming Yang, Qingmin Liao, Jie zhou

In this paper, we introduce a brand new scheme, namely external-reference image quality assessment (ER-IQA), by introducing external reference images to bridge the gap between FR and NR-IQA.

Image Quality Assessment

Citadel: Protecting Data Privacy and Model Confidentiality for Collaborative Learning with SGX

no code implementations4 May 2021 Chengliang Zhang, Junzhe Xia, Baichen Yang, Huancheng Puyang, Wei Wang, Ruichuan Chen, Istemi Ekin Akkus, Paarijaat Aditya, Feng Yan

This paper presents Citadel, a scalable collaborative ML system that protects the privacy of both data owner and model owner in untrusted infrastructures with the help of Intel SGX.

Federated Learning

Robust Face-Swap Detection Based on 3D Facial Shape Information

no code implementations28 Apr 2021 Weinan Guan, Wei Wang, Jing Dong, Bo Peng, Tieniu Tan

Maliciously-manipulated images or videos - so-called deep fakes - especially face-swap images and videos have attracted more and more malicious attackers to discredit some key figures.

Distributed Eco-Driving Algorithm of Vehicle Platoon Using Traffic Light and Road Slope Information

no code implementations26 Apr 2021 Yan Wang, Rong Su, Wei Wang, Xiaoxu Liu, Bohui Wang

This paper investigates the problem of ecological driving (eco-driving) of vehicle platoons.

Secure Artificial Intelligence of Things for Implicit Group Recommendations

no code implementations23 Apr 2021 Keping Yu, Zhiwei Guo, Yu Shen, Wei Wang, Jerry Chun-Wei Lin, Takuro Sato

The emergence of Artificial Intelligence of Things (AIoT) has provided novel insights for many social computing applications such as group recommender systems.

Recommendation Systems

SOGAN: 3D-Aware Shadow and Occlusion Robust GAN for Makeup Transfer

no code implementations21 Apr 2021 Yueming Lyu, Jing Dong, Bo Peng, Wei Wang, Tieniu Tan

Since human faces are symmetrical in the UV space, we can conveniently remove the undesired shadow and occlusion from the reference image by carefully designing a Flip Attention Module (FAM).

Face Model Facial Makeup Transfer

Jittering Effects Analysis and Beam Training Design for UAV Millimeter Wave Communications

no code implementations13 Apr 2021 Wei Wang, Wei zhang

In beam training design, with the relationship between attitude angles and AoA/AoD, we propose to generate a rough estimate of AoA and AoD from UAV navigation information.

Robust Differentiable SVD

2 code implementations8 Apr 2021 Wei Wang, Zheng Dang, Yinlin Hu, Pascal Fua, Mathieu Salzmann

Eigendecomposition of symmetric matrices is at the heart of many computer vision algorithms.

Image Classification Style Transfer

Conditional Hyper-Network for Blind Super-Resolution with Multiple Degradations

1 code implementation8 Apr 2021 Guanghao Yin, Wei Wang, Zehuan Yuan, Wei Ji, Dongdong Yu, Shouqian Sun, Tat-Seng Chua, Changhu Wang

We extract degradation prior at task-level with the proposed ConditionNet, which will be used to adapt the parameters of the basic SR network (BaseNet).

Image Super-Resolution

Machine Learning-Driven Virtual Bidding with Electricity Market Efficiency Analysis

no code implementations6 Apr 2021 Yinglun Li, Nanpeng Yu, Wei Wang

We leverage the proposed algorithmic virtual bid trading strategy to evaluate both the profitability of the virtual bid portfolio and the efficiency of U. S. wholesale electricity markets.

Algorithmic Trading Portfolio Optimization

Reduced Dynamics and Control for an Autonomous Bicycle

no code implementations30 Mar 2021 Jiaming Xiong, Bo Li, Ruihan Yu, Daolin Ma, Wei Wang, Caishan Liu

In this paper, we propose the reduced model for the full dynamics of a bicycle and analyze its nonlinear behavior under a proportional control law for steering.

AlphaEvolve: A Learning Framework to Discover Novel Alphas in Quantitative Investment

no code implementations30 Mar 2021 Can Cui, Wei Wang, Meihui Zhang, Gang Chen, Zhaojing Luo, Beng Chin Ooi

In this paper, we introduce a new class of alphas to model scalar, vector, and matrix features which possess the strengths of these two existing classes.

AutoML Stock Prediction

RadarLoc: Learning to Relocalize in FMCW Radar

no code implementations22 Mar 2021 Wei Wang, Pedro P. B. de Gusmo, Bo Yang, Andrew Markham, Niki Trigoni

There is considerable work in the field of deep camera relocalization, which directly estimates poses from raw images.

Camera Relocalization

Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Concepts

1 code implementation15 Mar 2021 Junheng Hao, Muhao Chen, Wenchao Yu, Yizhou Sun, Wei Wang

The cross-view association model is learned to bridge the embeddings of ontological concepts and their corresponding instance-view entities.

Entity Typing Knowledge Graphs +1

SemVLP: Vision-Language Pre-training by Aligning Semantics at Multiple Levels

no code implementations14 Mar 2021 Chenliang Li, Ming Yan, Haiyang Xu, Fuli Luo, Wei Wang, Bin Bi, Songfang Huang

Vision-language pre-training (VLP) on large-scale image-text pairs has recently witnessed rapid progress for learning cross-modal representations.

Bio-JOIE: Joint Representation Learning of Biological Knowledge Bases

1 code implementation7 Mar 2021 Junheng Hao, Chelsea Ju, Muhao Chen, Yizhou Sun, Carlo Zaniolo, Wei Wang

Leveraging a wide-range of biological knowledge, such as gene ontology and protein-protein interaction (PPI) networks from other closely related species presents a vital approach to infer the molecular impact of a new species.

Representation Learning Type prediction

Self-Renormalization of Quasi-Light-Front Correlators on the Lattice

no code implementations4 Mar 2021 Yi-Kai Huo, Yushan Su, Long-Cheng Gui, Xiangdong Ji, Yuan-Yuan Li, Yizhuang Liu, Andreas Schäfer, Maximilian Schlemmer, Peng Sun, Wei Wang, Yi-Bo Yang, Jian-Hui Zhang, Kuan Zhang

In applying large-momentum effective theory, renormalization of the Euclidean correlators in lattice regularization is a challenge due to linear divergences in the self-energy of Wilson lines.

High Energy Physics - Lattice High Energy Physics - Phenomenology

CREATe: Clinical Report Extraction and Annotation Technology

no code implementations28 Feb 2021 Yichao Zhou, Wei-Ting Chen, BoWen Zhang, David Lee, J. Harry Caufield, Kai-Wei Chang, Yizhou Sun, Peipei Ping, Wei Wang

Clinical case reports are written descriptions of the unique aspects of a particular clinical case, playing an essential role in sharing clinical experiences about atypical disease phenotypes and new therapies.

Robust Survivability-Oriented Scheduling of Separable Mobile Energy Storage and Demand Response for Isolated Distribution Systems

no code implementations26 Feb 2021 Wei Wang, Yufei He, Xiaofu Xiong, Hongzhou Chen

Extreme circumstances in which a local distribution system is electrically isolated from the main power supply may not always be avoidable.

Signal identification with Kalman Filter towards background-free neutrinoless double beta decay searches in gaseous detectors

no code implementations16 Feb 2021 Tao Li, Shaobo Wang, Yu Chen, Ke Han, Heng Lin, Kaixiang Ni, Wei Wang, Yiliu Xu, Anni Zou

Particle tracks and differential energy loss measured in high pressure gaseous detectors can be exploited for event identification in neutrinoless double beta decay~($0\nu \beta \beta$) searches.

Instrumentation and Detectors High Energy Physics - Experiment

Generating Diversified Comments via Reader-Aware Topic Modeling and Saliency Detection

no code implementations13 Feb 2021 Wei Wang, Piji Li, Hai-Tao Zheng

Automatic comment generation is a special and challenging task to verify the model ability on news content comprehension and language generation.

Saliency Detection Text Generation

BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction

2 code implementations ICLR 2021 Yuhang Li, Ruihao Gong, Xu Tan, Yang Yang, Peng Hu, Qi Zhang, Fengwei Yu, Wei Wang, Shi Gu

To further employ the power of quantization, the mixed precision technique is incorporated in our framework by approximating the inter-layer and intra-layer sensitivity.

Image Classification Object Detection +1

Using Hyperbolic Geometry for FG-NET over Distantly Supervised data

no code implementations27 Jan 2021 Muhammad Asif Ali, Yifang Sun, Bing Li, Wei Wang

Fine-Grained Named Entity Typing (\FGNET{}) classifies an entity mention into a fine range of entity types.

Entity Typing

A Unified Joint Maximum Mean Discrepancy for Domain Adaptation

no code implementations25 Jan 2021 Wei Wang, Baopu Li, Shuhui Yang, Jing Sun, Zhengming Ding, Junyang Chen, Xiao Dong, Zhihui Wang, Haojie Li

From the revealed unified JMMD, we illustrate that JMMD degrades the feature-label dependence (discriminability) that benefits to classification, and it is sensitive to the label distribution shift when the label kernel is the weighted class conditional one.

Domain Adaptation

A Spike Learning System for Event-driven Object Recognition

no code implementations21 Jan 2021 Shibo Zhou, Wei Wang, Xiaohua LI, Zhanpeng Jin

The proposed temporal coding scheme maps each event's arrival time and data into SNN spike time so that asynchronously-arrived events are processed immediately without delay.

Object Recognition

Abnormal topological refraction into free medium at sub-wavelength scale in valley phononic crystal plates

no code implementations18 Jan 2021 Linyun Yang, Kaiping Yu, Bernard Bonello, Wei Wang, Ying Wu

In this work we propose a topological valley phononic crystal plate and we extensively investigate the refraction of valley modes into the surrounding homogeneous medium.

Applied Physics

Exploring Adversarial Fake Images on Face Manifold

no code implementations CVPR 2021 Dongze Li, Wei Wang, Hongxing Fan, Jing Dong

Then, the generated fake images driven by the adversarial latent vectors with the help of GANs can defeat main-stream forensic models.

Adversarial Attack DeepFake Detection +1

A New Weighting Scheme for Fan-beam and Circle Cone-beam CT Reconstructions

no code implementations6 Jan 2021 Wei Wang, Xiang-Gen Xia, Chuanjiang He, Zemin Ren, Jian Lu, Tianfu Wang, Baiying Lei

In this paper, we first present an arc based algorithm for fan-beam computed tomography (CT) reconstruction via applying Katsevich's helical CT formula to 2D fan-beam CT reconstruction.

Computed Tomography (CT) SSIM

Towards Cross-Modal Forgery Detection and Localization on Live Surveillance Videos

no code implementations4 Jan 2021 Yong Huang, Xiang Li, Wei Wang, Tao Jiang, Qian Zhang

Traditional video forensics approaches can detect and localize forgery traces in each video frame using computationally-expensive spatial-temporal analysis, while falling short in real-time verification of live video feeds.

Time Series Video Forensics Cryptography and Security

Certified Distributional Robustness via Smoothed Classifiers

no code implementations1 Jan 2021 Jungang Yang, Liyao Xiang, Ruidong Chen, Yukun Wang, Wei Wang, Xinbing Wang

We focus on certified robustness of smoothed classifiers in this work, and propose to use the worst-case population loss over noisy inputs as a robustness metric.

Learning to Search for Fast Maximum Common Subgraph Detection

no code implementations1 Jan 2021 Yunsheng Bai, Derek Qiang Xu, Yizhou Sun, Wei Wang

Detecting the Maximum Common Subgraph (MCS) between two input graphs is fundamental for applications in biomedical analysis, malware detection, cloud computing, etc.

Graph Matching Imitation Learning +1

A self-explanatory method for the black problem on discrimination part of CNN

no code implementations1 Jan 2021 Jinwei Zhao, Qizhou Wang, Wanli Qiu, Guo Xie, Wei Wang, Xinhong Hei, Deyu Meng

However, it is hard for the interpretable models to approximate the discrimination part because of the tradeoff problem between interpretability performance and generalization performance of the discrimination part.

Unsupervised Real-World Super-Resolution: A Domain Adaptation Perspective

no code implementations ICCV 2021 Wei Wang, Haochen Zhang, Zehuan Yuan, Changhu Wang

A popular attempts towards the challenge is unpaired generative adversarial networks, which generate "real" LR counterparts from real HR images using image-to-image translation and then perform super-resolution from "real" LR->SR.

Domain Adaptation Image-to-Image Translation +1

Improving Unsupervised Domain Adaptation by Reducing Bi-level Feature Redundancy

no code implementations28 Dec 2020 Mengzhu Wang, Xiang Zhang, Long Lan, Wei Wang, Huibin Tan, Zhigang Luo

In this paper, we emphasize the significance of reducing feature redundancy for improving UDA in a bi-level way.

Unsupervised Domain Adaptation

A liquid scintillator for a neutrino Detector working at -50 degree

no code implementations22 Dec 2020 Zhangquan Xie, Jun Cao, Yayun Ding, Mengchao Liu, Xilei Sun, Wei Wang, Yuguang Xie

A liquid scintillator (LS) is developed for the Taishan Antineutrino Observatory (TAO), a ton-level neutrino detector to measure the reactor antineutrino spectrum with sub-percent energy resolution by adopting Silicon Photomultipliers (SiPMs) as photosensor.

Instrumentation and Detectors High Energy Physics - Experiment

Tetraquark Interpretation and Production Mechanism of the Belle $Y_b (10750)$-Resonance

no code implementations14 Dec 2020 Ahmed Ali, Luciano Maiani, Alexander Parkhomenko, Wei Wang

Recently, the Belle Collaboration has updated the analysis of the cross sections for the processes $e^+ e^- \to \Upsilon(nS)\, \pi^+ \pi^-$ ($n = 1,\, 2,\, 3$) in the $e^+ e^-$ center-of-mass energy range from 10. 52 to 11. 02~GeV.

High Energy Physics - Phenomenology High Energy Physics - Experiment

Peer-to-Peer Localization for Single-Antenna Devices

no code implementations10 Dec 2020 Xianan Zhang, Wei Wang, Xuedou Xiao, Hang Yang, Xinyu Zhang, Tao Jiang

In this paper, we present P2PLocate, a peer-to-peer localization system that enables a single-antenna device co-located with a batteryless backscatter tag to localize another single-antenna device with decimeter-level accuracy.

Indoor Localization TAG

Long Term Motion Prediction Using Keyposes

1 code implementation8 Dec 2020 Sena Kiciroglu, Wei Wang, Mathieu Salzmann, Pascal Fua

Long term human motion prediction is essential in safety-critical applications such as human-robot interaction and autonomous driving.

Autonomous Driving Human motion prediction +1

Sequential Resource Access: Theory and Algorithm

no code implementations7 Dec 2020 Lin Chen, Anastasios Giovanidis, Wei Wang, Lin Shan

We formulate and analyze a generic sequential resource access problem arising in a variety of engineering fields, where a user disposes a number of heterogeneous computing, communication, or storage resources, each characterized by the probability of successfully executing the user's task and the related access delay and cost, and seeks an optimal access strategy to maximize her utility within a given time horizon, defined as the expected reward minus the access cost.

Networking and Internet Architecture

Semi-Supervised Partial Label Learning via Confidence-Rated Margin Maximization

no code implementations NeurIPS 2020 Wei Wang, Min-Ling Zhang

After that, maximum margin formulation is introduced to jointly enable the induction of predictive model and the estimation of labeling confidence over unlabeled data.

Partial Label Learning

Deep Discriminative Feature Learning for Accent Recognition

1 code implementation25 Nov 2020 Wei Wang, Chao Zhang, Xiaopei Wu

Accent recognition with deep learning framework is a similar work to deep speaker identification, they're both expected to give the input speech an identifiable representation.

Face Recognition Speaker Identification +2

MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation

1 code implementation CVPR 2021 Tianxiang Ma, Bo Peng, Wei Wang, Jing Dong

To deal with this problem, we propose a novel multi-level statistics transfer model, which disentangles and transfers multi-level appearance features from person images and merges them with pose features to reconstruct the source person images themselves.

Pose Transfer Style Transfer

Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations

1 code implementation NeurIPS 2020 Zijie Huang, Yizhou Sun, Wei Wang

In this paper, we propose to learn system dynamics from irregularly-sampled partial observations with underlying graph structure for the first time.

VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation

1 code implementation ACL 2021 Fuli Luo, Wei Wang, Jiahao Liu, Yijia Liu, Bin Bi, Songfang Huang, Fei Huang, Luo Si

Existing work in multilingual pretraining has demonstrated the potential of cross-lingual transferability by training a unified Transformer encoder for multiple languages.

Language Modelling Question Answering +1

Restrained Generative Adversarial Network against Overfitting in Numeric Data Augmentation

no code implementations26 Oct 2020 Wei Wang, Yimeng Chai, Tao Cui, Chuang Wang, Baohua Zhang, Yue Li, Yi An

In recent studies, Generative Adversarial Network (GAN) is one of the popular schemes to augment the image dataset.

Data Augmentation

Certified Distributional Robustness on Smoothed Classifiers

no code implementations21 Oct 2020 Jungang Yang, Liyao Xiang, Ruidong Chen, Yukun Wang, Wei Wang, Xinbing Wang

For smoothed classifiers, we propose the worst-case adversarial loss over input distributions as a robustness certificate.

Ulixes: Facial Recognition Privacy with Adversarial Machine Learning

no code implementations20 Oct 2020 Thomas Cilloni, Wei Wang, Charles Walter, Charles Fleming

In this paper we propose Ulixes, a strategy to generate visually non-invasive facial noise masks that yield adversarial examples, preventing the formation of identifiable user clusters in the embedding space of facial encoders.

From Distributed Machine Learning To Federated Learning: In The View Of Data Privacy And Security

no code implementations19 Oct 2020 Sheng Shen, Tianqing Zhu, Di wu, Wei Wang, Wanlei Zhou

Federated learning is an improved version of distributed machine learning that further offloads operations which would usually be performed by a central server.

Distributed, Parallel, and Cluster Computing

Consistency and Coherency Enhanced Story Generation

no code implementations17 Oct 2020 Wei Wang, Piji Li, Hai-Tao Zheng

In terms of consistency, on one hand, GPT2 cannot guarantee the consistency of the plots explicitly.

Language Modelling Story Generation

Multivariate Time Series Classification with Hierarchical Variational Graph Pooling

no code implementations12 Oct 2020 Ziheng Duan, Haoyan Xu, Yueyang Wang, Yida Huang, Anni Ren, Zhongbin Xu, Yizhou Sun, Wei Wang

Then we combine GNNs and our proposed variational graph pooling layers for joint graph representation learning and graph coarsening, after which the graph is progressively coarsened to one node.

Classification General Classification +5

Cloud Cover and Aurora Contamination at Dome A in 2017 from KLCAM

no code implementations7 Oct 2020 Xu Yang, Zhaohui Shang, Keliang Hu, Yi Hu, Bin Ma, Yongjiang Wang, Zihuang Cao, Michael C. B. Ashley, Wei Wang

Dome A in Antarctica has many characteristics that make it an excellent site for astronomical observations, from the optical to the terahertz.

Instrumentation and Methods for Astrophysics

Motion Prediction Using Temporal Inception Module

1 code implementation6 Oct 2020 Tim Lebailly, Sena Kiciroglu, Mathieu Salzmann, Pascal Fua, Wei Wang

We argue that the diverse temporal scales are important as they allow us to look at the past frames with different receptive fields, which can lead to better predictions.

Autonomous Driving Human motion prediction +1

StyleDGPT: Stylized Response Generation with Pre-trained Language Models

1 code implementation Findings of the Association for Computational Linguistics 2020 Ze Yang, Wei Wu, Can Xu, Xinnian Liang, Jiaqi Bai, Liran Wang, Wei Wang, Zhoujun Li

Generating responses following a desired style has great potentials to extend applications of open-domain dialogue systems, yet is refrained by lacking of parallel data for training.

Response Generation

Distributed ADMM with Synergetic Communication and Computation

no code implementations29 Sep 2020 Zhuojun Tian, Zhaoyang Zhang, Jue Wang, Xiaoming Chen, Wei Wang, Huaiyu Dai

In this paper, we propose a novel distributed alternating direction method of multipliers (ADMM) algorithm with synergetic communication and computation, called SCCD-ADMM, to reduce the total communication and computation cost of the system.

VECO: Variable Encoder-decoder Pre-training for Cross-lingual Understanding and Generation

no code implementations28 Sep 2020 Fuli Luo, Wei Wang, Jiahao Liu, Yijia Liu, Bin Bi, Songfang Huang, Fei Huang, Luo Si

Recent studies about learning multilingual representations have achieved significant performance gains across a wide range of downstream cross-lingual tasks.

Language Modelling Masked Language Modeling +2

GraphCrop: Subgraph Cropping for Graph Classification

no code implementations22 Sep 2020 Yiwei Wang, Wei Wang, Yuxuan Liang, Yujun Cai, Bryan Hooi

We present a new method to regularize graph neural networks (GNNs) for better generalization in graph classification.

Classification Data Augmentation +2

Is Each Layer Non-trivial in CNN?

no code implementations9 Sep 2020 Wei Wang, Yanjie Zhu, Zhuoxu Cui, Dong Liang

Convolutional neural network (CNN) models have achieved great success in many fields.

Stereo Plane SLAM Based on Intersecting Lines

1 code implementation19 Aug 2020 Xiao-Yu Zhang, Wei Wang, Xianyu Qi, Ziwei Liao

Adding such plane features in stereo SLAM system reduces the drift error and refines the performance.

Frame Stereo Matching

Improving adversarial robustness of deep neural networks by using semantic information

no code implementations18 Aug 2020 Li-Na Wang, Rui Tang, Yawei Yue, Xingshu Chen, Wei Wang, Yi Zhu, Xuemei Zeng

The vulnerability of deep neural networks (DNNs) to adversarial attack, which is an attack that can mislead state-of-the-art classifiers into making an incorrect classification with high confidence by deliberately perturbing the original inputs, raises concerns about the robustness of DNNs to such attacks.

Adversarial Attack Adversarial Robustness

Learning to Create Better Ads: Generation and Ranking Approaches for Ad Creative Refinement

no code implementations17 Aug 2020 Shaunak Mishra, Manisha Verma, Yichao Zhou, Kapil Thadani, Wei Wang

Since major ad platforms typically run A/B tests for multiple advertisers in parallel, we explore the possibility of collaboratively learning ad creative refinement via A/B tests of multiple advertisers.

TAG Text Generation