Search Results for author: Cong Wang

Found 46 papers, 8 papers with code

基于BiLSTM-CRF的社会突发事件研判方法(Social Emergency Event Judgement based on BiLSTM-CRF)

no code implementations CCL 2020 Huijun Hu, Cong Wang, Jianhua Dai, Maofu Liu

社会突发事件的分类和等级研判作为应急处置中的一环, 其重要性不言而喻。然而, 目前研究多数采用人工或规则的方法识别证据进行研判, 由于社会突发事件的构成的复杂性和语言描述的灵活性, 这对于研判证据识别有很大局限性。本文参考“事件抽取”思想, 事件类型和研判证据作为事件中元素, 以BiLSTM-CRF方法细粒度的识别, 并将二者结合, 分类结果作为等级研判的输入, 识别出研判证据。最终将识别结果结合注意力机制进行等级研判, 通过对研判证据的精准识别从而来增强等级研判的准确性。实验表明, 相比人工或规则识别研判证据, 本文提出的方法有着更好的鲁棒性, 社会突发事件研判时也达到了较好的效果。 关键词:事件分类 ;研判证据识别 ;等级研判 ;BiLSTM-CRF

Towards Robust 3D Object Recognition with Dense-to-Sparse Deep Domain Adaptation

no code implementations7 May 2022 Prajval Kumar Murali, Cong Wang, Ravinder Dahiya, Mohsen Kaboli

Three-dimensional (3D) object recognition is crucial for intelligent autonomous agents such as autonomous vehicles and robots alike to operate effectively in unstructured environments.

3D Object Recognition Autonomous Vehicles +1

Learning to Classify Open Intent via Soft Labeling and Manifold Mixup

1 code implementation16 Apr 2022 Zifeng Cheng, Zhiwei Jiang, Yafeng Yin, Cong Wang, Qing Gu

In our method, soft labeling is used to reshape the label distribution of the known intent samples, aiming at reducing model's overconfident on known intents.

Intent Classification Outlier Detection

Fault Detection and Isolation of Uncertain Nonlinear Parabolic PDE Systems

no code implementations29 Mar 2022 Jingting Zhang, Chengzhi Yuan, Wei Zeng, Cong Wang

This paper proposes a novel fault detection and isolation (FDI) scheme for distributed parameter systems modeled by a class of parabolic partial differential equations (PDEs) with nonlinear uncertain dynamics.

Decision Making Fault Detection

The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining

no code implementations14 Mar 2022 Yi Liu, Lei Xu, Xingliang Yuan, Cong Wang, Bo Li

Existing machine unlearning techniques focus on centralized training, where access to all holders' training data is a must for the server to conduct the unlearning process.

Federated Learning

Load-Flow Solvability under Security Constraints in DC Distribution Networks

no code implementations7 Mar 2022 Zhe Chen, Cong Wang

We present sufficient conditions for the load-flow solvability under security constraints in DC distribution networks.

A Transferable Legged Mobile Manipulation Framework Based on Disturbance Predictive Control

no code implementations2 Mar 2022 Qingfeng Yao, Jilong Wan, Shuyu Yang, Cong Wang, Linghan Meng, Qifeng Zhang, Donglin Wang

Due to their ability to adapt to different terrains, quadruped robots have drawn much attention in the research field of robot learning.

reinforcement-learning

Online-updated High-order Collaborative Networks for Single Image Deraining

no code implementations14 Feb 2022 Cong Wang, Jinshan Pan, Xiao-Ming Wu

Most of the existing deep-learning-based methods constrain the network to generate derained images but few of them explore features from intermediate layers, different levels, and different modules which are beneficial for rain streaks removal.

Single Image Deraining

Aggregation Service for Federated Learning: An Efficient, Secure, and More Resilient Realization

no code implementations4 Feb 2022 Yifeng Zheng, Shangqi Lai, Yi Liu, Xingliang Yuan, Xun Yi, Cong Wang

In this paper, we present a system design which offers efficient protection of individual model updates throughout the learning procedure, allowing clients to only provide obscured model updates while a cloud server can still perform the aggregation.

Federated Learning

Towards Private Learning on Decentralized Graphs with Local Differential Privacy

no code implementations23 Jan 2022 WanYu Lin, Baochun Li, Cong Wang

It is typical to collect these local views of social graphs and conduct graph learning tasks.

Graph Learning

ED2: An Environment Dynamics Decomposition Framework for World Model Construction

1 code implementation6 Dec 2021 Cong Wang, Tianpei Yang, Jianye Hao, Yan Zheng, Hongyao Tang, Fazl Barez, Jinyi Liu, Jiajie Peng, Haiyin Piao, Zhixiao Sun

To reduce the model error, previous works use a single well-designed network to fit the entire environment dynamics, which treats the environment dynamics as a black box.

Model-based Reinforcement Learning

On the complexity of Dark Chinese Chess

no code implementations6 Dec 2021 Cong Wang, Tongwei Lu

This paper provides a complexity analysis for the game of dark Chinese chess (a. k. a.

Card Games Decision Making

TransBoost: A Boosting-Tree Kernel Transfer Learning Algorithm for Improving Financial Inclusion

1 code implementation4 Dec 2021 Yiheng Sun, Tian Lu, Cong Wang, Yuan Li, Huaiyu Fu, Jingran Dong, Yunjie Xu

The prosperity of mobile and financial technologies has bred and expanded various kinds of financial products to a broader scope of people, which contributes to advocating financial inclusion.

Transfer Learning

Black-box Adversarial Attacks on Commercial Speech Platforms with Minimal Information

no code implementations19 Oct 2021 Baolin Zheng, Peipei Jiang, Qian Wang, Qi Li, Chao Shen, Cong Wang, Yunjie Ge, Qingyang Teng, Shenyi Zhang

For commercial cloud speech APIs, we propose Occam, a decision-only black-box adversarial attack, where only final decisions are available to the adversary.

Adversarial Attack Speaker Recognition

Influence of the Binomial Crossover on Performance of Evolutionary Algorithms

no code implementations29 Sep 2021 Cong Wang, Jun He, Yu Chen, Xiufen Zou

In differential Evolution (DE) algorithms, a crossover operation filtering variables to be mutated is employed to search the feasible region flexibly, which leads to its successful applications in a variety of complicated optimization problems.

MotionHint: Self-Supervised Monocular Visual Odometry with Motion Constraints

no code implementations14 Sep 2021 Cong Wang, Yu-Ping Wang, Dinesh Manocha

A key aspect of our approach is to use an appropriate motion model that can help existing self-supervised monocular VO (SSM-VO) algorithms to overcome issues related to the local minima within their self-supervised loss functions.

Monocular Visual Odometry

Fully Non-Homogeneous Atmospheric Scattering Modeling with Convolutional Neural Networks for Single Image Dehazing

no code implementations25 Aug 2021 Cong Wang, Yan Huang, Yuexian Zou, Yong Xu

However, it is noted that ASM-based SIDM degrades its performance in dehazing real world hazy images due to the limited modelling ability of ASM where the atmospheric light factor (ALF) and the angular scattering coefficient (ASC) are assumed as constants for one image.

Image Dehazing Single Image Dehazing

TDLS: A Top-Down Layer Searching Algorithm for Generating Counterfactual Visual Explanation

no code implementations8 Aug 2021 Cong Wang, Haocheng Han, Caleb Chen Cao

Explanation of AI, as well as fairness of algorithms' decisions and the transparency of the decision model, are becoming more and more important.

Counterfactual Explanation Fairness +1

Teacher Model Fingerprinting Attacks Against Transfer Learning

no code implementations23 Jun 2021 Yufei Chen, Chao Shen, Cong Wang, Yang Zhang

To this end, we propose a teacher model fingerprinting attack to infer the origin of a student model, i. e., the teacher model it transfers from.

Transfer Learning

You See What I Want You To See: Exploring Targeted Black-Box Transferability Attack for Hash-Based Image Retrieval Systems

no code implementations CVPR 2021 Yanru Xiao, Cong Wang

In this paper, we start from an adversarial standpoint to explore and enhance the capacity of targeted black-box transferability attack for deep hashing.

Image Retrieval

CARTL: Cooperative Adversarially-Robust Transfer Learning

1 code implementation12 Jun 2021 Dian Chen, Hongxin Hu, Qian Wang, Yinli Li, Cong Wang, Chao Shen, Qi Li

In deep learning, a typical strategy for transfer learning is to freeze the early layers of a pre-trained model and fine-tune the rest of its layers on the target domain.

Adversarial Robustness Transfer Learning

FWB-Net:Front White Balance Network for Color Shift Correction in Single Image Dehazing via Atmospheric Light Estimation

no code implementations21 Jan 2021 Cong Wang, Yan Huang, Yuexian Zou, Yong Xu

However, for images taken in real-world, the illumination is not uniformly distributed over whole image which brings model mismatch and possibly results in color shift of the deep models using ASM.

Image Dehazing Single Image Dehazing

Poisoning Semi-supervised Federated Learning via Unlabeled Data: Attacks and Defenses

no code implementations8 Dec 2020 Yi Liu, Xingliang Yuan, Ruihui Zhao, Cong Wang, Dusit Niyato, Yefeng Zheng

Extensive case studies have shown that our attacks are effective on different datasets and common semi-supervised learning methods.

Federated Learning Quantization

Logical peering for interdomain networking on testbeds

1 code implementation9 Oct 2020 Yuanjun Yao, Qiang Cao, Paul Ruth, Mert Cevik, Cong Wang, Jeff Chase

Research testbed fabrics have potential to support long-lived, evolving, interdomain experiments, including opt-in application traffic across multiple campuses and edge sites.

Networking and Internet Architecture

Joint Self-Attention and Scale-Aggregation for Self-Calibrated Deraining Network

1 code implementation6 Aug 2020 Cong Wang, Yutong Wu, Zhixun Su, Junyang Chen

In the field of multimedia, single image deraining is a basic pre-processing work, which can greatly improve the visual effect of subsequent high-level tasks in rainy conditions.

Single Image Deraining

DCSFN: Deep Cross-scale Fusion Network for Single Image Rain Removal

no code implementations3 Aug 2020 Cong Wang, Xiaoying Xing, Zhixun Su, Junyang Chen

Further, we design an inner-scale connection block to utilize the multi-scale information and features fusion way between different scales to improve rain representation ability and we introduce the dense block with skip connection to inner-connect these blocks.

Rain Removal

A Framework for Behavioral Biometric Authentication using Deep Metric Learning on Mobile Devices

no code implementations26 May 2020 Cong Wang, Yanru Xiao, Xing Gao, Li Li, Jun Wang

We show the feasibility of training with mobile CPUs, where training 100 epochs takes less than 10 mins and can be boosted 3-5 times with feature transfer.

Metric Learning Multi-class Classification

Towards Efficient Scheduling of Federated Mobile Devices under Computational and Statistical Heterogeneity

no code implementations25 May 2020 Cong Wang, Yuanyuan Yang, Pengzhan Zhou

While the current research mainly focuses on optimizing learning algorithms and minimizing communication overhead left by distributed learning, there is still a considerable gap when it comes to the real implementation on mobile devices.

Federated Learning

Residual-driven Fuzzy C-Means Clustering for Image Segmentation

no code implementations15 Apr 2020 Cong Wang, Witold Pedrycz, Zhiwu Li, Mengchu Zhou

Due to its inferior characteristics, an observed (noisy) image's direct use gives rise to poor segmentation results.

Semantic Segmentation

Physical Model Guided Deep Image Deraining

no code implementations30 Mar 2020 Honghe Zhu, Cong Wang, Ya-Jie Zhang, Zhixun Su, Guohui Zhao

Single image deraining is an urgent task because the degraded rainy image makes many computer vision systems fail to work, such as video surveillance and autonomous driving.

Autonomous Driving Single Image Deraining

SUOD: Accelerating Large-Scale Unsupervised Heterogeneous Outlier Detection

1 code implementation11 Mar 2020 Yue Zhao, Xiyang Hu, Cheng Cheng, Cong Wang, Changlin Wan, Wen Wang, Jianing Yang, Haoping Bai, Zheng Li, Cao Xiao, Yunlong Wang, Zhi Qiao, Jimeng Sun, Leman Akoglu

Outlier detection (OD) is a key machine learning (ML) task for identifying abnormal objects from general samples with numerous high-stake applications including fraud detection and intrusion detection.

Dimensionality Reduction Fraud Detection +2

Kullback-Leibler Divergence-Based Fuzzy $C$-Means Clustering Incorporating Morphological Reconstruction and Wavelet Frames for Image Segmentation

no code implementations21 Feb 2020 Cong Wang, Witold Pedrycz, Zhiwu Li, Mengchu Zhou

Considering these feature sets as data of clustering, an modified FCM algorithm is proposed, which introduces a KL divergence term in the partition matrix into its objective function.

Frame Semantic Segmentation

Residual-Sparse Fuzzy $C$-Means Clustering Incorporating Morphological Reconstruction and Wavelet frames

no code implementations14 Feb 2020 Cong Wang, Witold Pedrycz, Zhiwu Li, Mengchu Zhou, Jun Zhao

To further enhance the segmentation effects of the improved FCM algorithm, we also employ the morphological reconstruction to smoothen the labels generated by clustering.

Frame Semantic Segmentation

Error Analysis of Elitist Randomized Search Heuristics

no code implementations3 Sep 2019 Cong Wang, Yu Chen, Jun He, Chengwang Xie

When globally optimal solutions of complicated optimization problems cannot be located by evolutionary algorithms (EAs) in polynomial expected running time, the hitting time/running time analysis is not flexible enough to accommodate the requirement of theoretical study, because sometimes we have no idea on what approximation ratio is available in polynomial expected running time.

Defeating Misclassification Attacks Against Transfer Learning

no code implementations29 Aug 2019 Bang Wu, Shuo Wang, Xingliang Yuan, Cong Wang, Carsten Rudolph, Xiangwen Yang

To avoid the bloated ensemble size during inference, we propose a two-phase defence, in which inference from the Student model is firstly performed to narrow down the candidate differentiators to be assembled, and later only a small, fixed number of them can be chosen to validate clean or reject adversarial inputs effectively.

Network Pruning Transfer Learning

Hierarchical Clustering Supported by Reciprocal Nearest Neighbors

no code implementations9 Jul 2019 Wen-Bo Xie, Yan-Li Lee, Cong Wang, Duan-Bing Chen, Tao Zhou

Clustering is a fundamental analysis tool aiming at classifying data points into groups based on their similarity or distance.

Community Detection

Exploring Stereovision-Based 3-D Scene Reconstruction for Augmented Reality

no code implementations17 Feb 2019 Guang-Yu Nie, Yun Liu, Cong Wang, Yue Liu, Yongtian Wang

Three-dimensional (3-D) scene reconstruction is one of the key techniques in Augmented Reality (AR), which is related to the integration of image processing and display systems of complex information.

Stereo Matching Stereo Matching Hand

Identifying the Mislabeled Training Samples of ECG Signals using Machine Learning

no code implementations11 Dec 2017 Yaoguang Li, Wei Cui, Cong Wang

The classification accuracy of electrocardiogram signal is often affected by diverse factors in which mislabeled training samples issue is one of the most influential problems.

Classification General Classification

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