Search Results for author: Weiqiang Wang

Found 53 papers, 20 papers with code

E-ANT: A Large-Scale Dataset for Efficient Automatic GUI NavigaTion

no code implementations20 Jun 2024 Ke Wang, Tianyu Xia, Zhangxuan Gu, Yi Zhao, Shuheng Shen, Changhua Meng, Weiqiang Wang, Ke Xu

Online GUI navigation on mobile devices has driven a lot of attention recent years since it contributes to many real-world applications.

Decision Making

Revisiting Modularity Maximization for Graph Clustering: A Contrastive Learning Perspective

1 code implementation20 Jun 2024 Yunfei Liu, Jintang Li, Yuehe Chen, Ruofan Wu, Ericbk Wang, Jing Zhou, Sheng Tian, Shuheng Shen, Xing Fu, Changhua Meng, Weiqiang Wang, Liang Chen

Another promising line of research involves the adoption of modularity maximization, a popular and effective measure for community detection, as the guiding principle for clustering tasks.

Clustering Community Detection +3

Supervised Contrastive Learning for Snapshot Spectral Imaging Face Anti-Spoofing

no code implementations29 May 2024 Chuanbiao Song, Yan Hong, Jun Lan, Huijia Zhu, Weiqiang Wang, Jianfu Zhang

This study reveals a cutting-edge re-balanced contrastive learning strategy aimed at strengthening face anti-spoofing capabilities within facial recognition systems, with a focus on countering the challenges posed by printed photos, and highly realistic silicone or latex masks.

Contrastive Learning Face Anti-Spoofing

Edge-guided and Class-balanced Active Learning for Semantic Segmentation of Aerial Images

no code implementations28 May 2024 Lianlei Shan, Weiqiang Wang, Ke Lv, Bin Luo

Due to the gap between aerial and natural images, the previous AL methods are not ideal, mainly caused by unreasonable labeling units and the neglect of class imbalance.

Active Learning Image Segmentation +2

Conditional Prototype Rectification Prompt Learning

1 code implementation15 Apr 2024 Haoxing Chen, Yaohui Li, Zizheng Huang, Yan Hong, Zhuoer Xu, Zhangxuan Gu, Jun Lan, Huijia Zhu, Weiqiang Wang

Recent advancements in efficient transfer learning (ETL) have shown remarkable success in fine-tuning VLMs within the scenario of limited data, introducing only a few parameters to harness task-specific insights from VLMs.

Few-Shot Learning Transfer Learning

Clean-image Backdoor Attacks

no code implementations22 Mar 2024 Dazhong Rong, Guoyao Yu, Shuheng Shen, Xinyi Fu, Peng Qian, Jianhai Chen, Qinming He, Xing Fu, Weiqiang Wang

To gather a significant quantity of annotated training data for high-performance image classification models, numerous companies opt to enlist third-party providers to label their unlabeled data.

Fairness Image Classification

PromptKD: Unsupervised Prompt Distillation for Vision-Language Models

1 code implementation CVPR 2024 Zheng Li, Xiang Li, Xinyi Fu, Xin Zhang, Weiqiang Wang, Shuo Chen, Jian Yang

To our best knowledge, we are the first to (1) perform unsupervised domain-specific prompt-driven knowledge distillation for CLIP, and (2) establish a practical pre-storing mechanism of text features as shared class vectors between teacher and student.

Knowledge Distillation Prompt Engineering +1

TroubleLLM: Align to Red Team Expert

no code implementations28 Feb 2024 Zhuoer Xu, Jianping Zhang, Shiwen Cui, Changhua Meng, Weiqiang Wang

Not only are these methods labor-intensive and require large budget costs, but the controllability of test prompt generation is lacking for the specific testing domain of LLM applications.

On provable privacy vulnerabilities of graph representations

no code implementations6 Feb 2024 Ruofan Wu, Guanhua Fang, Qiying Pan, Mingyang Zhang, Tengfei Liu, Weiqiang Wang

Our research primarily addresses the theoretical underpinnings of similarity-based edge reconstruction attacks (SERA), furnishing a non-asymptotic analysis of their reconstruction capacities.

Graph Representation Learning

LasTGL: An Industrial Framework for Large-Scale Temporal Graph Learning

no code implementations28 Nov 2023 Jintang Li, Jiawang Dan, Ruofan Wu, Jing Zhou, Sheng Tian, Yunfei Liu, Baokun Wang, Changhua Meng, Weiqiang Wang, Yuchang Zhu, Liang Chen, Zibin Zheng

Over the past few years, graph neural networks (GNNs) have become powerful and practical tools for learning on (static) graph-structure data.

Graph Learning

Boosting Audio-visual Zero-shot Learning with Large Language Models

1 code implementation21 Nov 2023 Haoxing Chen, Yaohui Li, Yan Hong, Zizheng Huang, Zhuoer Xu, Zhangxuan Gu, Jun Lan, Huijia Zhu, Weiqiang Wang

Recent methods mainly focus on learning multi-modal features aligned with class names to enhance the generalization ability to unseen categories.

audio-visual learning Descriptive +1

Privacy-preserving design of graph neural networks with applications to vertical federated learning

no code implementations31 Oct 2023 Ruofan Wu, Mingyang Zhang, Lingjuan Lyu, Xiaolong Xu, Xiuquan Hao, Xinyi Fu, Tengfei Liu, Tianyi Zhang, Weiqiang Wang

The paradigm of vertical federated learning (VFL), where institutions collaboratively train machine learning models via combining each other's local feature or label information, has achieved great success in applications to financial risk management (FRM).

Graph Representation Learning Management +2

Self-supervision meets kernel graph neural models: From architecture to augmentations

no code implementations17 Oct 2023 Jiawang Dan, Ruofan Wu, Yunpeng Liu, Baokun Wang, Changhua Meng, Tengfei Liu, Tianyi Zhang, Ningtao Wang, Xing Fu, Qi Li, Weiqiang Wang

Recently, the idea of designing neural models on graphs using the theory of graph kernels has emerged as a more transparent as well as sometimes more expressive alternative to MPNNs known as kernel graph neural networks (KGNNs).

Data Augmentation Graph Classification +2

FedGKD: Unleashing the Power of Collaboration in Federated Graph Neural Networks

no code implementations18 Sep 2023 Qiying Pan, Ruofan Wu, Tengfei Liu, Tianyi Zhang, Yifei Zhu, Weiqiang Wang

Federated training of Graph Neural Networks (GNN) has become popular in recent years due to its ability to perform graph-related tasks under data isolation scenarios while preserving data privacy.

ControlCom: Controllable Image Composition using Diffusion Model

1 code implementation19 Aug 2023 Bo Zhang, Yuxuan Duan, Jun Lan, Yan Hong, Huijia Zhu, Weiqiang Wang, Li Niu

To address these challenges, we propose a controllable image composition method that unifies four tasks in one diffusion model: image blending, image harmonization, view synthesis, and generative composition.

Image Harmonization

Joint Local Relational Augmentation and Global Nash Equilibrium for Federated Learning with Non-IID Data

no code implementations17 Aug 2023 Xinting Liao, Chaochao Chen, Weiming Liu, Pengyang Zhou, Huabin Zhu, Shuheng Shen, Weiqiang Wang, Mengling Hu, Yanchao Tan, Xiaolin Zheng

In server, GNE reaches an agreement among inconsistent and discrepant model deviations from clients to server, which encourages the global model to update in the direction of global optimum without breaking down the clients optimization toward their local optimums.

Federated Learning

Backpropagation Path Search On Adversarial Transferability

no code implementations ICCV 2023 Zhuoer Xu, Zhangxuan Gu, Jianping Zhang, Shiwen Cui, Changhua Meng, Weiqiang Wang

Transfer-based attackers craft adversarial examples against surrogate models and transfer them to victim models deployed in the black-box situation.

Bayesian Optimization

End-to-end Remote Sensing Change Detection of Unregistered Bi-temporal Images for Natural Disasters

no code implementations27 Jul 2023 Guiqin Zhao, Lianlei Shan, Weiqiang Wang

Deep networks have demonstrated significant success in detecting changes in bi-temporal remote sensing images and have found applications in various fields.

Change Detection

Compositional Prototypical Networks for Few-Shot Classification

1 code implementation11 Jun 2023 Qiang Lyu, Weiqiang Wang

We empirically demonstrate that the learned component prototypes have good class transferability and can be reused to construct compositional prototypes for novel classes.

Attribute Classification

DiffUTE: Universal Text Editing Diffusion Model

1 code implementation NeurIPS 2023 Haoxing Chen, Zhuoer Xu, Zhangxuan Gu, Jun Lan, Xing Zheng, Yaohui Li, Changhua Meng, Huijia Zhu, Weiqiang Wang

Specifically, we build our model on a diffusion model and carefully modify the network structure to enable the model for drawing multilingual characters with the help of glyph and position information.

Self-Supervised Learning

FlowText: Synthesizing Realistic Scene Text Video with Optical Flow Estimation

1 code implementation5 May 2023 Yuzhong Zhao, Weijia Wu, Zhuang Li, Jiahong Li, Weiqiang Wang

This paper introduces a novel video text synthesis technique called FlowText, which utilizes optical flow estimation to synthesize a large amount of text video data at a low cost for training robust video text spotters.

Optical Flow Estimation Text Spotting

Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embedding

no code implementations6 Apr 2023 Yuke Hu, Wei Liang, Ruofan Wu, Kai Xiao, Weiqiang Wang, Xiaochen Li, Jinfei Liu, Zhan Qin

Knowledge Graph Embedding (KGE) is a fundamental technique that extracts expressive representation from knowledge graph (KG) to facilitate diverse downstream tasks.

Knowledge Graph Embedding

DEDGAT: Dual Embedding of Directed Graph Attention Networks for Detecting Financial Risk

no code implementations6 Mar 2023 Jiafu Wu, Mufeng Yao, Dong Wu, Mingmin Chi, Baokun Wang, Ruofan Wu, Xin Fu, Changhua Meng, Weiqiang Wang

Graph representation plays an important role in the field of financial risk control, where the relationship among users can be constructed in a graph manner.

Graph Attention

GRANDE: a neural model over directed multigraphs with application to anti-money laundering

no code implementations4 Feb 2023 Ruofan Wu, Boqun Ma, Hong Jin, Wenlong Zhao, Weiqiang Wang, Tianyi Zhang

The application of graph representation learning techniques to the area of financial risk management (FRM) has attracted significant attention recently.

Edge Classification Graph Representation Learning +1

SplitGNN: Splitting GNN for Node Classification with Heterogeneous Attention

no code implementations27 Jan 2023 Xiaolong Xu, Lingjuan Lyu, Yihong Dong, Yicheng Lu, Weiqiang Wang, Hong Jin

With the frequent happening of privacy leakage and the enactment of privacy laws across different countries, data owners are reluctant to directly share their raw data and labels with any other party.

Classification Federated Learning +1

DiffusionInst: Diffusion Model for Instance Segmentation

2 code implementations6 Dec 2022 Zhangxuan Gu, Haoxing Chen, Zhuoer Xu, Jun Lan, Changhua Meng, Weiqiang Wang

Extensive experimental results on COCO and LVIS show that DiffusionInst achieves competitive performance compared to existing instance segmentation models with various backbones, such as ResNet and Swin Transformers.

Instance Segmentation Segmentation

Hierarchical Dynamic Image Harmonization

1 code implementation16 Nov 2022 Haoxing Chen, Zhangxuan Gu, Yaohui Li, Jun Lan, Changhua Meng, Weiqiang Wang, Huaxiong Li

The MGD effectively applies distinct convolution to the foreground and background, learning the representations of foreground and background regions as well as their correlations to the global harmonization, facilitating local visual consistency for the images much more efficiently.

Image Harmonization

A2: Efficient Automated Attacker for Boosting Adversarial Training

1 code implementation7 Oct 2022 Zhuoer Xu, Guanghui Zhu, Changhua Meng, Shiwen Cui, ZhenZhe Ying, Weiqiang Wang, Ming Gu, Yihua Huang

In this paper, we propose an efficient automated attacker called A2 to boost AT by generating the optimal perturbations on-the-fly during training.

Adversarial Defense

NEURAL MARIONETTE: A Transformer-based Multi-action Human Motion Synthesis System

no code implementations27 Sep 2022 Weiqiang Wang, Xuefei Zhe, Qiuhong Ke, Di Kang, Tingguang Li, Ruizhi Chen, Linchao Bao

Along with the novel system, we also present a new dataset dedicated to the multi-action motion synthesis task, which contains both action tags and their contextual information.

Motion Synthesis Rolling Shutter Correction +1

K-Order Graph-oriented Transformer with GraAttention for 3D Pose and Shape Estimation

no code implementations24 Aug 2022 Weixi Zhao, Weiqiang Wang

We propose a novel attention-based 2D-to-3D pose estimation network for graph-structured data, named KOG-Transformer, and a 3D pose-to-shape estimation network for hand data, named GASE-Net.

3D Pose Estimation

Explore Faster Localization Learning For Scene Text Detection

no code implementations4 Jul 2022 Yuzhong Zhao, Yuanqiang Cai, Weijia Wu, Weiqiang Wang

Generally pre-training and long-time training computation are necessary for obtaining a good-performance text detector based on deep networks.

Scene Text Detection Text Detection

GUARD: Graph Universal Adversarial Defense

1 code implementation20 Apr 2022 Jintang Li, Jie Liao, Ruofan Wu, Liang Chen, Zibin Zheng, Jiawang Dan, Changhua Meng, Weiqiang Wang

To mitigate such a threat, considerable research efforts have been devoted to increasing the robustness of GCNs against adversarial attacks.

Adversarial Defense

XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding

1 code implementation CVPR 2022 Zhangxuan Gu, Changhua Meng, Ke Wang, Jun Lan, Weiqiang Wang, Ming Gu, Liqing Zhang

Recently, various multimodal networks for Visually-Rich Document Understanding(VRDU) have been proposed, showing the promotion of transformers by integrating visual and layout information with the text embeddings.

document understanding Optical Character Recognition (OCR) +1

MT-GBM: A Multi-Task Gradient Boosting Machine with Shared Decision Trees

1 code implementation17 Jan 2022 ZhenZhe Ying, Zhuoer Xu, Zhifeng Li, Weiqiang Wang, Changhua Meng

Despite the success of deep learning in computer vision and natural language processing, Gradient Boosted Decision Tree (GBDT) is yet one of the most powerful tools for applications with tabular data such as e-commerce and FinTech.

Multi-Task Learning

GraFormer: Graph-Oriented Transformer for 3D Pose Estimation

no code implementations CVPR 2022 Weixi Zhao, Weiqiang Wang, Yunjie Tian

In 2D-to-3D pose estimation, it is important to exploit the spatial constraints of 2D joints, but it is not yet well modeled.

3D Pose Estimation

GraFormer: Graph Convolution Transformer for 3D Pose Estimation

1 code implementation17 Sep 2021 Weixi Zhao, Yunjie Tian, Qixiang Ye, Jianbin Jiao, Weiqiang Wang

Exploiting relations among 2D joints plays a crucial role yet remains semi-developed in 2D-to-3D pose estimation.

3D Pose Estimation Implicit Relations

How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data

no code implementations ICLR 2022 Zhiyuan Zhang, Lingjuan Lyu, Weiqiang Wang, Lichao Sun, Xu sun

In this work, we observe an interesting phenomenon that the variations of parameters are always AWPs when tuning the trained clean model to inject backdoors.

SHORING: Design Provable Conditional High-Order Interaction Network via Symbolic Testing

no code implementations3 Jul 2021 Hui Li, Xing Fu, Ruofan Wu, Jinyu Xu, Kai Xiao, xiaofu Chang, Weiqiang Wang, Shuai Chen, Leilei Shi, Tao Xiong, Yuan Qi

Deep learning provides a promising way to extract effective representations from raw data in an end-to-end fashion and has proven its effectiveness in various domains such as computer vision, natural language processing, etc.

Management Product Recommendation +1

A Vertical Federated Learning Framework for Graph Convolutional Network

no code implementations22 Jun 2021 Xiang Ni, Xiaolong Xu, Lingjuan Lyu, Changhua Meng, Weiqiang Wang

Recently, Graph Neural Network (GNN) has achieved remarkable success in various real-world problems on graph data.

Graph Neural Network Node Classification +2

Towards Spatio-Temporal Video Scene Text Detection via Temporal Clustering

no code implementations19 Nov 2020 Yuanqiang Cai, Chang Liu, Weiqiang Wang, Qixiang Ye

With only bounding-box annotations in the spatial domain, existing video scene text detection (VSTD) benchmarks lack temporal relation of text instances among video frames, which hinders the development of video text-related applications.

Clustering Scene Text Detection +1

Characters as Graphs: Recognizing Online Handwritten Chinese Characters via Spatial Graph Convolutional Network

no code implementations20 Apr 2020 Ji Gan, Weiqiang Wang, Ke Lu

Chinese is one of the most widely used languages in the world, yet online handwritten Chinese character recognition (OLHCCR) remains challenging.

Time Series Time Series Analysis

Variational Policy Propagation for Multi-agent Reinforcement Learning

no code implementations19 Apr 2020 Chao Qu, Hui Li, Chang Liu, Junwu Xiong, James Zhang, Wei Chu, Weiqiang Wang, Yuan Qi, Le Song

We propose a \emph{collaborative} multi-agent reinforcement learning algorithm named variational policy propagation (VPP) to learn a \emph{joint} policy through the interactions over agents.

Multi-agent Reinforcement Learning reinforcement-learning +2

Rethinking Object Detection in Retail Stores

1 code implementation18 Mar 2020 Yuan-Qiang Cai, Longyin Wen, Libo Zhang, Dawei Du, Weiqiang Wang

In this paper, we propose a new task, ie, simultaneously object localization and counting, abbreviated as Locount, which requires algorithms to localize groups of objects of interest with the number of instances.

Object object-detection +2

Guided Attention Network for Object Detection and Counting on Drones

no code implementations25 Sep 2019 Yuan-Qiang Cai, Dawei Du, Libo Zhang, Longyin Wen, Weiqiang Wang, Yanjun Wu, Siwei Lyu

Object detection and counting are related but challenging problems, especially for drone based scenes with small objects and cluttered background.

Object object-detection +1

Reinterpreting CTC training as iterative fitting

2 code implementations24 Apr 2019 Hongzhu Li, Weiqiang Wang

The outputs of a CTC-trained model tend to form a series of spikes separated by strongly predicted blanks, know as the spiky problem.

General Classification

Egocentric Hand Detection Via Dynamic Region Growing

no code implementations10 Nov 2017 Shao Huang, Weiqiang Wang, Shengfeng He, Rynson W. H. Lau

Egocentric videos, which mainly record the activities carried out by the users of the wearable cameras, have drawn much research attentions in recent years.

Action Recognition Gesture Recognition +3

A New Hybrid-parameter Recurrent Neural Networks for Online Handwritten Chinese Character Recognition

no code implementations8 Nov 2017 Haiqing Ren, Weiqiang Wang

And the proposed Memory Pool Unit is proved to be a simple hidden layer function and obtains a competitive recognition results.

Temporal Sequences

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