Search Results for author: Xinyu Wang

Found 102 papers, 45 papers with code

Correcting the Misuse: A Method for the Chinese Idiom Cloze Test

no code implementations EMNLP (DeeLIO) 2020 Xinyu Wang, Hongsheng Zhao, Tan Yang, Hongbo Wang

The cloze test for Chinese idioms is a new challenge in machine reading comprehension: given a sentence with a blank, choosing a candidate Chinese idiom which matches the context.

Attribute Cloze Test +3

VQLTI: Long-Term Tropical Cyclone Intensity Forecasting with Physical Constraints

1 code implementation30 Jan 2025 Xinyu Wang, Lei Liu, Kang Chen, Tao Han, Bin Li, Lei Bai

(2) Incorporating physical knowledge and physical constraints can help mitigate the accumulation of forecasting errors.

Tropical Cyclone Intensity Forecasting

Green Video Camouflaged Object Detection

no code implementations19 Jan 2025 Xinyu Wang, Hong-Shuo Chen, Zhiruo Zhou, Suya You, Azad M. Madni, C. -C. Jay Kuo

Camouflaged object detection (COD) aims to distinguish hidden objects embedded in an environment highly similar to the object.

Object object-detection +1

U-GIFT: Uncertainty-Guided Firewall for Toxic Speech in Few-Shot Scenario

no code implementations1 Jan 2025 Jiaxin Song, Xinyu Wang, Yihao Wang, Yifan Tang, Ru Zhang, Jianyi Liu, Gongshen Liu

While manual content moderation is still prevalent, the overwhelming volume of content and the psychological strain on human moderators underscore the need for automated toxic speech detection.

Active Learning

An End-to-End Smart Predict-then-Optimize Framework for Vehicle Relocation Problems in Large-Scale Vehicle Crowd Sensing

no code implementations27 Nov 2024 Xinyu Wang, Yiyang Peng, Wei Ma

Methodologically, we formulate the vehicle relocation problem by quadratic programming (QP) and incorporate a novel unrolling approach based on the Alternating Direction Method of Multipliers (ADMM) within the SPO framework to compute gradients of the QP layer, facilitating backpropagation and gradient-based optimization for end-to-end learning.

Decision Making

Exploring Knowledge Boundaries in Large Language Models for Retrieval Judgment

no code implementations9 Nov 2024 Zhen Zhang, Xinyu Wang, Yong Jiang, Zhuo Chen, Feiteng Mu, Mengting Hu, Pengjun Xie, Fei Huang

Actually, we find that the impact of RAG on the question answering capabilities of LLMs can be categorized into three groups: beneficial, neutral, and harmful.

Question Answering RAG +1

Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent

1 code implementation5 Nov 2024 Yangning Li, Yinghui Li, Xinyu Wang, Yong Jiang, Zhen Zhang, Xinran Zheng, Hui Wang, Hai-Tao Zheng, Pengjun Xie, Philip S. Yu, Fei Huang, Jingren Zhou

To bridge the dataset gap, we first construct Dyn-VQA dataset, consisting of three types of "dynamic" questions, which require complex knowledge retrieval strategies variable in query, tool, and time: (1) Questions with rapidly changing answers.

Benchmarking Hallucination +3

The Reopening of Pandora's Box: Analyzing the Role of LLMs in the Evolving Battle Against AI-Generated Fake News

no code implementations25 Oct 2024 Xinyu Wang, Wenbo Zhang, Sai Koneru, Hangzhi Guo, Bonam Mingole, S. Shyam Sundar, Sarah Rajtmajer, Amulya Yadav

To address this gap, this work presents the findings from a university-level competition which aimed to explore how LLMs can be used by humans to create fake news, and to assess the ability of human annotators and AI models to detect it.

Fake News Detection

Monolingual and Multilingual Misinformation Detection for Low-Resource Languages: A Comprehensive Survey

no code implementations24 Oct 2024 Xinyu Wang, Wenbo Zhang, Sarah Rajtmajer

In today's global digital landscape, misinformation transcends linguistic boundaries, posing a significant challenge for moderation systems.

Misinformation

GARLIC: LLM-Guided Dynamic Progress Control with Hierarchical Weighted Graph for Long Document QA

no code implementations7 Oct 2024 Xinyu Wang, Yanzheng Xiang, Lin Gui, Yulan He

In this paper, we propose a new retrieval method, called LLM-Guided Dynamic Progress Control with Hierarchical Weighted Graph (GARLIC), which outperforms previous state-of-the-art baselines, including Llama 3. 1, while retaining the computational efficiency of RAG methods.

Computational Efficiency RAG +1

Task-free Lifelong Robot Learning with Retrieval-based Weighted Local Adaptation

no code implementations3 Oct 2024 Pengzhi Yang, Xinyu Wang, Ruipeng Zhang, Cong Wang, Frans A. Oliehoek, Jens Kober

A fundamental objective in intelligent robotics is to move towards lifelong learning robot that can learn and adapt to unseen scenarios over time.

Retrieval

Are Heterophily-Specific GNNs and Homophily Metrics Really Effective? Evaluation Pitfalls and New Benchmarks

no code implementations9 Sep 2024 Sitao Luan, Qincheng Lu, Chenqing Hua, Xinyu Wang, Jiaqi Zhu, Xiao-Wen Chang, Guy Wolf, Jian Tang

To overcome these challenges, we first train and fine-tune baseline models on $27$ most widely used benchmark datasets, categorize them into three distinct groups: malignant, benign and ambiguous heterophilic datasets, and identify the real challenging subsets of tasks.

AnomalyCD: A benchmark for Earth anomaly change detection with high-resolution and time-series observations

no code implementations9 Sep 2024 Jingtao Li, Qian Zhu, Xinyu Wang, Hengwei Zhao, Yanfei Zhong

In this paper, to tackle this problem, we propose the anomaly change detection (AnomalyCD) technique, which accepts time-series observations and learns to identify anomalous changes by learning from the historical normal change pattern.

Change Detection Time Series

DCIM-AVSR : Efficient Audio-Visual Speech Recognition via Dual Conformer Interaction Module

no code implementations31 Aug 2024 Xinyu Wang, Haotian Jiang, Haolin Huang, Yu Fang, Mengjie Xu, Qian Wang

Speech recognition is the technology that enables machines to interpret and process human speech, converting spoken language into text or commands.

Audio-Visual Speech Recognition speech-recognition +1

EMDFNet: Efficient Multi-scale and Diverse Feature Network for Traffic Sign Detection

no code implementations26 Aug 2024 Pengyu Li, Chenhe Liu, Tengfei Li, Xinyu Wang, Shihui Zhang, Dongyang Yu

Motivated by these challenges, in this paper, we propose a novel object detection network named Efficient Multi-scale and Diverse Feature Network (EMDFNet) for traffic sign detection that integrates an Augmented Shortcut Module and an Efficient Hybrid Encoder to address the aforementioned issues simultaneously.

Autonomous Driving Novel Object Detection +3

LION: Linear Group RNN for 3D Object Detection in Point Clouds

1 code implementation25 Jul 2024 Zhe Liu, Jinghua Hou, Xinyu Wang, Xiaoqing Ye, Jingdong Wang, Hengshuang Zhao, Xiang Bai

To tackle this problem, we simply introduce a 3D spatial feature descriptor and integrate it into the linear group RNN operators to enhance their spatial features rather than blindly increasing the number of scanning orders for voxel features.

3D Object Detection Long-range modeling +2

The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challenges

no code implementations12 Jul 2024 Sitao Luan, Chenqing Hua, Qincheng Lu, Liheng Ma, Lirong Wu, Xinyu Wang, Minkai Xu, Xiao-Wen Chang, Doina Precup, Rex Ying, Stan Z. Li, Jian Tang, Guy Wolf, Stefanie Jegelka

In this survey, we provide a comprehensive review of the latest progress on heterophilic graph learning, including an extensive summary of benchmark datasets and evaluation of homophily metrics on synthetic graphs, meticulous classification of the most updated supervised and unsupervised learning methods, thorough digestion of the theoretical analysis on homophily/heterophily, and broad exploration of the heterophily-related applications.

Graph Learning Graph Representation Learning

Deciphering Oracle Bone Language with Diffusion Models

1 code implementation2 Jun 2024 Haisu Guan, Huanxin Yang, Xinyu Wang, Shengwei Han, Yongge Liu, Lianwen Jin, Xiang Bai, Yuliang Liu

Originating from China's Shang Dynasty approximately 3, 000 years ago, the Oracle Bone Script (OBS) is a cornerstone in the annals of linguistic history, predating many established writing systems.

Decipherment Image Generation

RaFe: Ranking Feedback Improves Query Rewriting for RAG

no code implementations23 May 2024 Shengyu Mao, Yong Jiang, Boli Chen, Xiao Li, Peng Wang, Xinyu Wang, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang

As Large Language Models (LLMs) and Retrieval Augmentation Generation (RAG) techniques have evolved, query rewriting has been widely incorporated into the RAG system for downstream tasks like open-domain QA.

RAG Retrieval

The Unappreciated Role of Intent in Algorithmic Moderation of Social Media Content

no code implementations17 May 2024 Xinyu Wang, Sai Koneru, Pranav Narayanan Venkit, Brett Frischmann, Sarah Rajtmajer

As social media has become a predominant mode of communication globally, the rise of abusive content threatens to undermine civil discourse.

Automatic question generation for propositional logical equivalences

no code implementations9 May 2024 Yicheng Yang, Xinyu Wang, Haoming Yu, Zhiyuan Li

Our experiments show that the difficulty level of questions generated by our AQG approach is similar to the questions presented to students in the textbook [1].

Attribute Question Generation +1

Multi-Label Out-of-Distribution Detection with Spectral Normalized Joint Energy

1 code implementation8 May 2024 Yihan Mei, Xinyu Wang, Dell Zhang, Xiaoling Wang

Our findings indicate that the application of spectral normalization to joint energy scores notably amplifies the model's capability for OOD detection.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Evaluating and Mitigating Linguistic Discrimination in Large Language Models

no code implementations29 Apr 2024 Guoliang Dong, Haoyu Wang, Jun Sun, Xinyu Wang

The results show that LLMs exhibit stronger human alignment capabilities with queries in English, French, Russian, and Spanish (only 1. 04\% of harmful queries successfully jailbreak on average) compared to queries in Bengali, Georgian, Nepali and Maithili (27. 7\% of harmful queries jailbreak successfully on average).

Inside the echo chamber: Linguistic underpinnings of misinformation on Twitter

1 code implementation24 Apr 2024 Xinyu Wang, Jiayi Li, Sarah Rajtmajer

Social media users drive the spread of misinformation online by sharing posts that include erroneous information or commenting on controversial topics with unsubstantiated arguments often in earnest.

Misinformation

Text in the Dark: Extremely Low-Light Text Image Enhancement

1 code implementation22 Apr 2024 Che-Tsung Lin, Chun Chet Ng, Zhi Qin Tan, Wan Jun Nah, Xinyu Wang, Jie Long Kew, PoHao Hsu, Shang Hong Lai, Chee Seng Chan, Christopher Zach

We also labeled texts in the extremely low-light See In the Dark (SID) and ordinary LOw-Light (LOL) datasets to allow for objective assessment of extremely low-light image enhancement through scene text tasks.

Low-Light Image Enhancement Scene Text Detection +1

Improving Retrieval Augmented Open-Domain Question-Answering with Vectorized Contexts

1 code implementation2 Apr 2024 Zhuo Chen, Xinyu Wang, Yong Jiang, Pengjun Xie, Fei Huang, Kewei Tu

With our method, the origin language models can cover several times longer contexts while keeping the computing requirements close to the baseline.

In-Context Learning Language Modeling +3

Let LLMs Take on the Latest Challenges! A Chinese Dynamic Question Answering Benchmark

1 code implementation29 Feb 2024 Zhikun Xu, Yinghui Li, Ruixue Ding, Xinyu Wang, Boli Chen, Yong Jiang, Hai-Tao Zheng, Wenlian Lu, Pengjun Xie, Fei Huang

To promote the improvement of Chinese LLMs' ability to answer dynamic questions, in this paper, we introduce CDQA, a Chinese Dynamic QA benchmark containing question-answer pairs related to the latest news on the Chinese Internet.

Question Answering

Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond

no code implementations22 Feb 2024 Xinyu Wang, Hainiu Xu, Lin Gui, Yulan He

Task embedding, a meta-learning technique that captures task-specific information, has gained popularity, especially in areas such as multi-task learning, model editing, and interpretability.

Meta-Learning Model Editing +1

Mirror: A Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning

1 code implementation22 Feb 2024 Hanqi Yan, Qinglin Zhu, Xinyu Wang, Lin Gui, Yulan He

While Large language models (LLMs) have the capability to iteratively reflect on their own outputs, recent studies have observed their struggles with knowledge-rich problems without access to external resources.

Diversity

An open dataset for oracle bone script recognition and decipherment

2 code implementations27 Jan 2024 Pengjie Wang, Kaile Zhang, Xinyu Wang, Shengwei Han, Yongge Liu, Jinpeng Wan, Haisu Guan, Zhebin Kuang, Lianwen Jin, Xiang Bai, Yuliang Liu

Oracle bone script, one of the earliest known forms of ancient Chinese writing, presents invaluable research materials for scholars studying the humanities and geography of the Shang Dynasty, dating back 3, 000 years.

Decipherment

An open dataset for the evolution of oracle bone characters: EVOBC

no code implementations23 Jan 2024 Haisu Guan, Jinpeng Wan, Yuliang Liu, Pengjie Wang, Kaile Zhang, Zhebin Kuang, Xinyu Wang, Xiang Bai, Lianwen Jin

We conducted validation and simulated deciphering on the constructed dataset, and the results demonstrate its high efficacy in aiding the study of oracle bone script.

Decipherment

ModaVerse: Efficiently Transforming Modalities with LLMs

1 code implementation CVPR 2024 Xinyu Wang, Bohan Zhuang, Qi Wu

This alignment process, which synchronizes a language model trained on textual data with encoders and decoders trained on multi-modal data, often necessitates extensive training of several projection layers in multiple stages.

Language Modeling Language Modelling +1

Enhancing Edge Intelligence with Highly Discriminant LNT Features

no code implementations19 Dec 2023 Xinyu Wang, Vinod K. Mishra, C. -C. Jay Kuo

Along this line, we present a novel supervised learning method to generate highly discriminant complementary features based on the least-squares normal transform (LNT).

Binary Classification Representation Learning

Simultaneous Synthesis and Verification of Neural Control Barrier Functions through Branch-and-Bound Verification-in-the-loop Training

no code implementations17 Nov 2023 Xinyu Wang, Luzia Knoedler, Frederik Baymler Mathiesen, Javier Alonso-Mora

In this work, we leverage bound propagation techniques and the Branch-and-Bound scheme to efficiently verify that a neural network satisfies the conditions to be a CBF over the continuous state space.

A Scalable Framework for Table of Contents Extraction from Complex ESG Annual Reports

no code implementations27 Oct 2023 Xinyu Wang, Lin Gui, Yulan He

Table of contents (ToC) extraction centres on structuring documents in a hierarchical manner.

Learning a Cross-modality Anomaly Detector for Remote Sensing Imagery

1 code implementation11 Oct 2023 Jingtao Li, Xinyu Wang, Hengwei Zhao, Liangpei Zhang, Yanfei Zhong

To satisfy this condition, two large margin losses for pixel-level and feature-level deviation ranking are proposed respectively.

Anomaly Detection Diversity +1

SwitchGPT: Adapting Large Language Models for Non-Text Outputs

no code implementations14 Sep 2023 Xinyu Wang, Bohan Zhuang, Qi Wu

To bridge this gap, we propose a novel approach, \methodname, from a modality conversion perspective that evolves a text-based LLM into a multi-modal one.

Exploiting Machine Unlearning for Backdoor Attacks in Deep Learning System

no code implementations12 Sep 2023 Peixin Zhang, Jun Sun, Mingtian Tan, Xinyu Wang

In recent years, the security issues of artificial intelligence have become increasingly prominent due to the rapid development of deep learning research and applications.

Backdoor Attack Deep Learning +1

Class Prior-Free Positive-Unlabeled Learning with Taylor Variational Loss for Hyperspectral Remote Sensing Imagery

1 code implementation ICCV 2023 Hengwei Zhao, Xinyu Wang, Jingtao Li, Yanfei Zhong

Positive-unlabeled learning (PU learning) in hyperspectral remote sensing imagery (HSI) is aimed at learning a binary classifier from positive and unlabeled data, which has broad prospects in various earth vision applications.

DiLogics: Creating Web Automation Programs With Diverse Logics

no code implementations10 Aug 2023 Kevin Pu, Jim Yang, Angel Yuan, Minyi Ma, Rui Dong, Xinyu Wang, Yan Chen, Tovi Grossman

Knowledge workers frequently encounter repetitive web data entry tasks, like updating records or placing orders.

New Interaction Paradigm for Complex EDA Software Leveraging GPT

1 code implementation27 Jul 2023 Boyu Han, Xinyu Wang, Yifan Wang, Junyu Yan, Yidong Tian

In the rapidly growing field of electronic design automation (EDA), professional software such as KiCad, Cadence , and Altium Designer provide increasingly extensive design functionalities.

Task Planning

A Badminton Recognition and Tracking System Based on Context Multi-feature Fusion

no code implementations26 Jun 2023 Xinyu Wang, Jianwei Li

Ball recognition and tracking have traditionally been the main focus of computer vision researchers as a crucial component of sports video analysis.

Green Steganalyzer: A Green Learning Approach to Image Steganalysis

no code implementations6 Jun 2023 Yao Zhu, Xinyu Wang, Hong-Shuo Chen, Ronald Salloum, C. -C. Jay Kuo

A novel learning solution to image steganalysis based on the green learning paradigm, called Green Steganalyzer (GS), is proposed in this work.

Self-Supervised Learning Steganalysis

Document-Level Multi-Event Extraction with Event Proxy Nodes and Hausdorff Distance Minimization

no code implementations30 May 2023 Xinyu Wang, Lin Gui, Yulan He

By directly minimizing Hausdorff distance, the model is trained towards the global optimum directly, which improves performance and reduces training time.

Event Extraction

Toward Evaluating Robustness of Reinforcement Learning with Adversarial Policy

1 code implementation4 May 2023 Xiang Zheng, Xingjun Ma, Shengjie Wang, Xinyu Wang, Chao Shen, Cong Wang

Our experiments validate the effectiveness of the four types of adversarial intrinsic regularizers and the bias-reduction method in enhancing black-box adversarial policy learning across a variety of environments.

reinforcement-learning Reinforcement Learning +1

Transition Propagation Graph Neural Networks for Temporal Networks

1 code implementation15 Apr 2023 Tongya Zheng, Zunlei Feng, Tianli Zhang, Yunzhi Hao, Mingli Song, Xingen Wang, Xinyu Wang, Ji Zhao, Chun Chen

The proposed TIP-GNN focuses on the bilevel graph structure in temporal networks: besides the explicit interaction graph, a node's sequential interactions can also be constructed as a transition graph.

Graph Mining Link Prediction +1

One-Step Detection Paradigm for Hyperspectral Anomaly Detection via Spectral Deviation Relationship Learning

1 code implementation22 Mar 2023 Jingtao Li, Xinyu Wang, Shaoyu Wang, Hengwei Zhao, Liangpei Zhang, Yanfei Zhong

In this paper, an unsupervised transferred direct detection (TDD) model is proposed, which is optimized directly for the anomaly detection task (one-step paradigm) and has transferability.

Anomaly Detection

Anomaly Segmentation for High-Resolution Remote Sensing Images Based on Pixel Descriptors

1 code implementation31 Jan 2023 Jingtao Li, Xinyu Wang, Hengwei Zhao, Shaoyu Wang, Yanfei Zhong

Anomaly segmentation in high spatial resolution (HSR) remote sensing imagery is aimed at segmenting anomaly patterns of the earth deviating from normal patterns, which plays an important role in various Earth vision applications.

Anomaly Segmentation One-Class Classification +1

SPTS v2: Single-Point Scene Text Spotting

3 code implementations4 Jan 2023 Yuliang Liu, Jiaxin Zhang, Dezhi Peng, Mingxin Huang, Xinyu Wang, Jingqun Tang, Can Huang, Dahua Lin, Chunhua Shen, Xiang Bai, Lianwen Jin

Within the context of our SPTS v2 framework, our experiments suggest a potential preference for single-point representation in scene text spotting when compared to other representations.

Decoder Text Detection +1

Named Entity and Relation Extraction with Multi-Modal Retrieval

1 code implementation3 Dec 2022 Xinyu Wang, Jiong Cai, Yong Jiang, Pengjun Xie, Kewei Tu, Wei Lu

MoRe contains a text retrieval module and an image-based retrieval module, which retrieve related knowledge of the input text and image in the knowledge corpus respectively.

Multi-modal Named Entity Recognition Named Entity Recognition +3

NeurIPS 2022 Competition: Driving SMARTS

no code implementations14 Nov 2022 Amir Rasouli, Randy Goebel, Matthew E. Taylor, Iuliia Kotseruba, Soheil Alizadeh, Tianpei Yang, Montgomery Alban, Florian Shkurti, Yuzheng Zhuang, Adam Scibior, Kasra Rezaee, Animesh Garg, David Meger, Jun Luo, Liam Paull, Weinan Zhang, Xinyu Wang, Xi Chen

The proposed competition supports methodologically diverse solutions, such as reinforcement learning (RL) and offline learning methods, trained on a combination of naturalistic AD data and open-source simulation platform SMARTS.

Autonomous Driving Reinforcement Learning (RL)

One-Class Risk Estimation for One-Class Hyperspectral Image Classification

no code implementations27 Oct 2022 Hengwei Zhao, Yanfei Zhong, Xinyu Wang, Hong Shu

Hyperspectral imagery (HSI) one-class classification is aimed at identifying a single target class from the HSI by using only knowing positive data, which can significantly reduce the requirements for annotation.

Classification Deep Learning +4

Statistical Attention Localization (SAL): Methodology and Application to Object Classification

no code implementations3 Aug 2022 Yijing Yang, Vasileios Magoulianitis, Xinyu Wang, C. -C. Jay Kuo

SAL consists of three steps: 1) preliminary attention window selection via decision statistics, 2) attention map refinement, and 3) rectangular attention region finalization.

Classification Object

Automated Evaluation for Student Argumentative Writing: A Survey

no code implementations9 May 2022 Xinyu Wang, Yohan Lee, Juneyoung Park

This paper surveys and organizes research works in an under-studied area, which we call automated evaluation for student argumentative writing.

Automated Writing Evaluation Survey

Stability of China's Stock Market: Measure and Forecast by Ricci Curvature on Network

no code implementations14 Apr 2022 Xinyu Wang, Liang Zhao, Ning Zhang, Liu Feng, Haibo Lin

As far as we know, this is the first paper to apply Ricci curvature to forecast the systemic stability of domestic stock market, and our results show that Ricci curvature has good explanatory power for the market stability and can be a good indicator to judge the future risk and volatility of the domestic market.

Time Series Time Series Analysis

Transfinite Modal Logic: a Semi-quantitative Explanation for Bayesian Reasoning

no code implementations2 Apr 2022 Xinyu Wang

Bayesian reasoning plays a significant role both in human rationality and in machine learning.

Repairing Adversarial Texts through Perturbation

no code implementations29 Dec 2021 Guoliang Dong, Jingyi Wang, Jun Sun, Sudipta Chattopadhyay, Xinyu Wang, Ting Dai, Jie Shi, Jin Song Dong

Furthermore, such attacks are impossible to eliminate, i. e., the adversarial perturbation is still possible after applying mitigation methods such as adversarial training.

Adversarial Text

SPTS: Single-Point Text Spotting

1 code implementation15 Dec 2021 Dezhi Peng, Xinyu Wang, Yuliang Liu, Jiaxin Zhang, Mingxin Huang, Songxuan Lai, Shenggao Zhu, Jing Li, Dahua Lin, Chunhua Shen, Xiang Bai, Lianwen Jin

For the first time, we demonstrate that training scene text spotting models can be achieved with an extremely low-cost annotation of a single-point for each instance.

Language Modelling Text Detection +1

ITA: Image-Text Alignments for Multi-Modal Named Entity Recognition

1 code implementation NAACL 2022 Xinyu Wang, Min Gui, Yong Jiang, Zixia Jia, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Kewei Tu

As text representations take the most important role in MNER, in this paper, we propose {\bf I}mage-{\bf t}ext {\bf A}lignments (ITA) to align image features into the textual space, so that the attention mechanism in transformer-based pretrained textual embeddings can be better utilized.

Multi-modal Named Entity Recognition named-entity-recognition +1

Learning Dynamic Preference Structure Embedding From Temporal Networks

1 code implementation23 Nov 2021 Tongya Zheng, Zunlei Feng, Yu Wang, Chengchao Shen, Mingli Song, Xingen Wang, Xinyu Wang, Chun Chen, Hao Xu

Our proposed Dynamic Preference Structure (DPS) framework consists of two stages: structure sampling and graph fusion.

Graph Sampling

Fairness Testing of Deep Image Classification with Adequacy Metrics

no code implementations17 Nov 2021 Peixin Zhang, Jingyi Wang, Jun Sun, Xinyu Wang

DeepFAIT consists of several important components enabling effective fairness testing of deep image classification applications: 1) a neuron selection strategy to identify the fairness-related neurons; 2) a set of multi-granularity adequacy metrics to evaluate the model's fairness; 3) a test selection algorithm for fixing the fairness issues efficiently.

Classification Face Recognition +2

A-PixelHop: A Green, Robust and Explainable Fake-Image Detector

no code implementations7 Nov 2021 Yao Zhu, Xinyu Wang, Hong-Shuo Chen, Ronald Salloum, C. -C. Jay Kuo

A novel method for detecting CNN-generated images, called Attentive PixelHop (or A-PixelHop), is proposed in this work.

Dependency Induction Through the Lens of Visual Perception

1 code implementation CoNLL (EMNLP) 2021 Ruisi Su, Shruti Rijhwani, Hao Zhu, Junxian He, Xinyu Wang, Yonatan Bisk, Graham Neubig

Our experiments find that concreteness is a strong indicator for learning dependency grammars, improving the direct attachment score (DAS) by over 50\% as compared to state-of-the-art models trained on pure text.

Constituency Grammar Induction Dependency Parsing

Automatic Fairness Testing of Neural Classifiers through Adversarial Sampling

no code implementations17 Jul 2021 Peixin Zhang, Jingyi Wang, Jun Sun, Xinyu Wang, Guoliang Dong, Xingen Wang, Ting Dai, Jin Song Dong

In this work, we bridge the gap by proposing a scalable and effective approach for systematically searching for discriminatory samples while extending existing fairness testing approaches to address a more challenging domain, i. e., text classification.

Deep Learning Fairness +2

ICDAR 2021 Competition on Integrated Circuit Text Spotting and Aesthetic Assessment

1 code implementation12 Jul 2021 Chun Chet Ng, Akmalul Khairi Bin Nazaruddin, Yeong Khang Lee, Xinyu Wang, Yuliang Liu, Chee Seng Chan, Lianwen Jin, Yipeng Sun, Lixin Fan

With hundreds of thousands of electronic chip components are being manufactured every day, chip manufacturers have seen an increasing demand in seeking a more efficient and effective way of inspecting the quality of printed texts on chip components.

Text Spotting

Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning

3 code implementations ACL 2021 Xinyu Wang, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Kewei Tu

We find empirically that the contextual representations computed on the retrieval-based input view, constructed through the concatenation of a sentence and its external contexts, can achieve significantly improved performance compared to the original input view based only on the sentence.

Chinese Named Entity Recognition Chunking +3

WHU-Hi: UAV-borne hyperspectral with high spatial resolution (H2) benchmark datasets for hyperspectral image classification

no code implementations27 Dec 2020 Xin Hu, Yanfei Zhong, Chang Luo, Xinyu Wang

Some start-of-art hyperspectral image classification methods benchmarked the WHU-Hi dataset, and the experimental results show that WHU-Hi is a challenging dataset.

Classification General Classification +1

Towards Repairing Neural Networks Correctly

no code implementations3 Dec 2020 Guoliang Dong, Jun Sun, Jingyi Wang, Xinyu Wang, Ting Dai

Neural networks are increasingly applied to support decision making in safety-critical applications (like autonomous cars, unmanned aerial vehicles and face recognition based authentication).

Decision Making Face Recognition

Syndrome-aware Herb Recommendation with Multi-Graph Convolution Network

no code implementations20 Feb 2020 Yuanyuan Jin, Wei zhang, Xiangnan He, Xinyu Wang, Xiaoling Wang

Given a set of symptoms to treat, we aim to generate an overall syndrome representation by effectively fusing the embeddings of all the symptoms in the set, to mimic how a doctor induces the syndromes.

Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection

1 code implementation20 Dec 2019 Yuliang Liu, Tong He, Hao Chen, Xinyu Wang, Canjie Luo, Shuaitao Zhang, Chunhua Shen, Lianwen Jin

More importantly, based on OBD, we provide a detailed analysis of the impact of a collection of refinements, which may inspire others to build state-of-the-art text detectors.

Scene Text Detection Text Detection

There is Limited Correlation between Coverage and Robustness for Deep Neural Networks

no code implementations14 Nov 2019 Yizhen Dong, Peixin Zhang, Jingyi Wang, Shuang Liu, Jun Sun, Jianye Hao, Xinyu Wang, Li Wang, Jin Song Dong, Dai Ting

In this work, we conduct an empirical study to evaluate the relationship between coverage, robustness and attack/defense metrics for DNN.

Face Recognition Malware Detection

Personality-Aware Probabilistic Map for Trajectory Prediction of Pedestrians

no code implementations1 Nov 2019 Chaochao Li, Pei Lv, Mingliang Xu, Xinyu Wang, Dinesh Manocha, Bing Zhou, Meng Wang

We update this map dynamically based on the agents in the environment and prior trajectory of a pedestrian.

Trajectory Prediction

Towards Interpreting Recurrent Neural Networks through Probabilistic Abstraction

1 code implementation22 Sep 2019 Guoliang Dong, Jingyi Wang, Jun Sun, Yang Zhang, Xinyu Wang, Ting Dai, Jin Song Dong, Xingen Wang

In this work, we propose an approach to extract probabilistic automata for interpreting an important class of neural networks, i. e., recurrent neural networks.

Machine Translation Object Recognition

Sketch-Driven Regular Expression Generation from Natural Language and Examples

1 code implementation16 Aug 2019 Xi Ye, Qiaochu Chen, Xinyu Wang, Isil Dillig, Greg Durrett

Our system achieves state-of-the-art performance on the prior datasets and solves 57% of the real-world dataset, which existing neural systems completely fail on.

Adversarial Sample Detection for Deep Neural Network through Model Mutation Testing

5 code implementations14 Dec 2018 Jingyi Wang, Guoliang Dong, Jun Sun, Xinyu Wang, Peixin Zhang

We thus first propose a measure of `sensitivity' and show empirically that normal samples and adversarial samples have distinguishable sensitivity.

Two-sample testing

Detecting Adversarial Samples for Deep Neural Networks through Mutation Testing

no code implementations14 May 2018 Jingyi Wang, Jun Sun, Peixin Zhang, Xinyu Wang

Recently, it has been shown that deep neural networks (DNN) are subject to attacks through adversarial samples.

Event Representations for Automated Story Generation with Deep Neural Nets

1 code implementation5 Jun 2017 Lara J. Martin, Prithviraj Ammanabrolu, Xinyu Wang, William Hancock, Shruti Singh, Brent Harrison, Mark O. Riedl

We then present a technique for automated story generation whereby we decompose the problem into the generation of successive events (event2event) and the generation of natural language sentences from events (event2sentence).

Event Expansion Sentence +2

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