卫志华

2026

FOSK: Fast Open-Vocabulary 3D Instance Segmentation via Consensus-Filtered Knowledge Distillation

IEEE International Conference on Acoustics Speech and Signal Processing

DOI

2026

Interpreting Accent Classification via Attribution-Based Analysis and Clustering of Time-Frequency Patterns

Communications in computer and information science

DOI

2026

Enhancing large language models for knowledge graph question answering via multi-granularity knowledge injection and structured reasoning path-augmented prompting

Information Processing & Management

DOI

2026

UD-Gaussian: Uncertainty-Driven Gaussian Modeling for Occluded Person Re-Identification

IEEE Transactions on Image Processing

DOI

2026

Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement

Underline Science Inc.

DOI

2026

Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement

Annual Meeting of the Association for Computational Linguistics (ACL)

DOI

2025

Salient Object Detection Based on Shadowed Sets and Illumination-Guided Network

IEEE Transactions on Fuzzy Systems

DOI

2025

COSMO: Combination of Selective Memorization for Low-Cost Vision-and-Language Navigation

IEEE/CVF International Conference on Computer Vision (ICCV)

DOI

2025

Leveraging Debiased Cross-Modal Attention Maps and Code-Based Reasoning for Zero-Shot Referring Expression Comprehension

IEEE/CVF International Conference on Computer Vision (ICCV)

DOI

2025

ProDet: Learning Prototype-Based Region-Word Alignment for Open-Vocabulary Object Detection

International Conference on Computer Vision and Data Mining (ICCVDM)

DOI

2025

Quantifying Fine-Grained Alignment Knowledge in Vision-Language Pre-trained Models via Interactions

International Conference on Computer Vision and Data Mining (ICCVDM)

DOI

2025

Improving Prediction Certainty Estimation for Reliable Early Exiting via Null Space Projection

International Joint Conference on Artificial Intelligence

DOI

2025

StyleCSR: Style-controllable Sequential Recommendation with Prompt Tuning

DOI

2025

A Unified Approach to Interpreting Self-supervised Pre-training Methods for 3D Point Clouds via Interactions

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI

2025

Binary mask tuning on gradient: Towards multi-data question answering

Knowledge-Based Systems

DOI

2025

LLM-enhanced representation learning for graph collaborative filtering recommendation models

Journal of Intelligent Information Systems

DOI

2025

Text2Bundle: Towards Personalized Query-based Bundle Generation

ACM Transactions on Recommender Systems

DOI

2025

Infusing Multi-Hop Medical Knowledge Into Smaller Language Models for Biomedical Question Answering

IEEE Journal of Biomedical and Health Informatics

DOI

2025

BRDIA: Bidirectional Reasoning with Dynamic Instruction Adjustment for Multi-hop KGQA

IEEE International Conference on Acoustics Speech and Signal Processing

DOI

2025

DeTAM: Defending LLMs Against Jailbreak Attacks via Targeted Attention Modification

DOI

2025

PhonePredictor: Bridging the Semantic Gap Between Neural Audio Codecs and Phonetic Sequences in Carefully Crafted Scenarios

International Conference on Electronic Information Engineering and Computer Communication (EIECC)

DOI

2025

CFMMD: A CLIP-based Frequency-Aware Metric for Robust Generative Image Evaluation

International Conference on Image Processing, Computer Vision and Machine Learning (ICICML)

DOI

2025

Interpreting Arithmetic Reasoning in Large Language Models using Game-Theoretic Interactions

neural information processing systems

DOI

2025

PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization

arXiv.org

DOI

2025

Degrading Voice: A Comprehensive Overview of Robust Voice Conversion Through Input Manipulation

arXiv.org

DOI

2025

MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models

Annual Meeting of the Association for Computational Linguistics

DOI

2024

Incorporating multi-perspective information into reinforcement learning to address multi-hop knowledge graph question answering

Expert Systems With Applications，Vol. 255

DOI

2024

Supplementing domain knowledge to BERT with semi-structured information of documents

Expert Systems With Applications，Vol. 235

DOI

2024

Occlusion-Aware Transformer With Second-Order Attention for Person Re-Identification

IEEE Transactions on Image Processing

DOI

2024

VL-MPFT: Multitask Parameter-Efficient Fine-Tuning for Visual-Language Pre-trained Models via Task-Adaptive Masking

Lecture notes in computer science

DOI

2024

MKEAH： Multimodal knowledge extraction and accumulation based on hyperplane embedding for knowledge-based visual question answering

Virtual Reality & Intelligent Hardware

DOI

2024

Subgraph-Based Attention Network for Multi-Hop Question Answering

DOI

2024

SamCap: Energy-based Controllable Image Captioning by Gradient-Based Sampling

International Conference on Multimedia Retrieval

DOI

2024

Extending Implicit Neural Representations for Text-to-Image Generation

IEEE International Conference on Acoustics Speech and Signal Processing

DOI

2024

Interpretable Rotation-Equivariant Quaternion Neural Networks for 3D Point Cloud Processing

IEEE Transactions on Pattern Analysis and Machine Intelligence

DOI

2024

DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination

Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI

2024

Towards Multi-subsession Conversational Recommendation

Lecture notes in computer science

DOI

2024

Controlling Attention Map Better for Text-Guided Image Editing Diffusion Models

Lecture notes in computer science

DOI

2024

On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models

International Joint Conference on Artificial Intelligence

DOI

2023

基于大数据专业贯通的数据采集与集成课程实验体系设计

《计算机教育》

2023

From Pixels to Explanations: Uncovering the Reasoning Process in Visual Question Answering

ACM Multimedia Asia (MMAsia)

DOI

2023

Multi-Interest Multi-Round Conversational Recommendation System with Fuzzy Feedback Based User Simulator

ACM Transactions on Recommender Systems

DOI

2023

Graph Learning Augmented Heterogeneous Graph Neural Network for Social Recommendation

ACM Transactions on Recommender Systems

DOI

2023

ToViLaG: Your Visual-Language Generative Model is Also An Evildoer

Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI

2023

Data-Augmented Counterfactual Learning for Bundle Recommendation

Lecture notes in computer science

DOI

2023

Large-Scale and Multi-Perspective Opinion Summarization with Diverse Review Subsets

DOI

2022

机器学习课程中递进式实验案例设计

《计算机教育》

2022

Multi-View Self-Attention Based Transformer for Speaker Recognition

IEEE International Conference on Acoustics Speech and Signal Processing

DOI

2022

LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT

Interspeech (USB)

DOI

2022

Multiple Choice Questions based Multi-Interest Policy Learning for Conversational Recommendation

ACM Web Conference (WWW)

DOI

2022

Neural Data-to-Text Generation Guided by Predicted Plan

DOI

2022

Heterogeneous Global Graph Neural Networks for Personalized Session-based Recommendation

ACM International Conference on Web Search and Data Mining (WSDM)

DOI

2022

SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing

Annual Meeting of the Association for Computational Linguistics (ACL)

DOI

2022

EfficientTDNN: Efficient Architecture Search for Speaker Recognition

IEEE/ACM Transactions on Audio Speech and Language Processing

DOI

2022

Intention Adaptive Graph Neural Network for Category-Aware Session-Based Recommendation

Lecture notes in computer science

DOI

2022

Graph-augmented Learning to Rank for Querying Large-scale Knowledge Graph

Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing (AACL-IJCNLP)

DOI

2022

SAKE: A Graph-Based Keyphrase Extraction Method Using Self-attention

Lecture notes in computer science

DOI

2022

Searching Efficient Dynamic Graph CNN for Point Cloud Processing

2021

面向学科交叉的数据采集与集成课程教学设计

《计算机教育》

DOI

2021

Temporal aware Multi-Interest Graph Neural Network For Session-based Recommendation

Asian Conference on Machine Learning

2021

Dual Path Residual Network for Speaker Verification

International Conference on Computer, Internet of Things and Control Engineering (CITCE)

DOI

2021

Multi-behavior Graph Contextual Aware Network for Session-based Recommendation

arXiv.org

2021

Interpretable Compositional Convolutional Neural Networks

DOI

2021

A Feature Fusion Based Dense Estimation Model for 3D Human Pose

International Conference on Image, Vision and Computing (ICIVC)

DOI

2021

Verifiability and Predictability: Interpreting Utilities of Network Architectures for Point Cloud Processing

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI

2021

Improved Instance Discrimination and Feature Compactness for End-to-End Person Search

IEEE Transactions on Circuits and Systems for Video Technology

DOI

2021

Boundary Information Aggregation and Adaptive Keypoint Combination Enhanced Object Detection

Lecture notes in computer science

DOI

2021

Slice Sequential Network: A Lightweight Unsupervised Point Cloud Completion Network

Lecture notes in computer science

DOI

2021

An Opinion Summarization-Evaluation System Based on Pre-trained Models

Lecture notes in computer science

DOI

2021

RDF-to-Text Generation with Reinforcement Learning Based Graph-augmented Structural Neural Encoders

arXiv.org

2020

Non-numerical nearest neighbor classifiers with value-object hierarchical embedding

Expert Systems With Applications，Vol. 150

DOI

2020

面向人工智能专业课程的棋类博弈教学辅助平台

《计算机与现代化》

2020

基于多粒度特征的行人跟踪检测结合算法

《计算机研究与发展》

2020

新工科背景下数据挖掘课程综合性实验设计

《计算机教育》

DOI

2020

立足能力建设，持续推进实验贯通

《实验技术与管理》

DOI

2020

Tongji University Undergraduate Team for the VoxCeleb Speaker Recognition Challenge2020

arXiv.org

2020

An Automatic Image Segmentation Algorithm Based on Three-Way Decisions

International Conference on Advanced Computational Intelligence (ICACI)

DOI

2020

Improved general attribute reduction algorithms

Information Sciences

DOI

2020

RepeatPadding: Balancing words and sentence length for language comprehension in visual question answering

Information Sciences

DOI

2020

DACNN

International Conference on Mathematics and Artificial Intelligence (ICMAI)

DOI

2020

Three-way decisions based blocking reduction models in hierarchical classification

Information Sciences

DOI

2020

3D-Rotation-Equivariant Quaternion Neural Networks

Lecture notes in computer science

DOI

2020

Time-Aware Attentive Neural Network for News Recommendation with Long- and Short-Term User Representation

Lecture notes in computer science

DOI

2020

Quick Maximum Distribution Reduction in Inconsistent Decision Tables

Lecture notes in computer science

DOI

2020

Tongji University Team for the VoxCeleb Speaker Recognition Challenge 2020

arXiv.org

2019

基于多源特征后融合的分层目标检测算法

《计算机科学》

2019

Attentional Transformer Networks for Target-Oriented Sentiment Classification

Communications in computer and information science

DOI

2019

Explaining the PointNet: What Has Been Learned Inside the PointNet?

CVPR Workshops

2019

Multi-Scale Receptive Field Detection Network

IEEE Access

DOI

2019

A Robust Long-Term Pedestrian Tracking-by-Detection Algorithm Based on Three-Way Decision

Lecture notes in computer science

DOI

2019

A Dustbin Category Based Feedback Incremental Learning Strategy for Hierarchical Image Classification

Lecture notes in computer science

DOI

2019

基于多源特征后融合的分层目标检测算法 (Multi-layer Object Detection Algorithm Based on Multi-source Feature Late Fusion)

《计算机科学》

DOI

2019

Traffic Flow Data Prediction Using Residual Deconvolution Based Deep Generative Network

IEEE Access

DOI

2018

基于Lasso算法的中文情感混合特征选择方法研究

《计算机科学》

2018

Multi-granularity principal curves extraction based on improved spectral clustering of complex distribution data

International Journal of Approximate Reasoning

DOI

2018

Long-Term Traffic Speed Prediction Based on Multiscale Spatio-Temporal Feature Learning Network

IEEE Transactions on Intelligent Transportation Systems

DOI

2018

A C-GRU Neural Network for Rumors Detection

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

DOI

2018

Selective Feature Fusion Based Adaptive Image Segmentation Algorithm

Advances in Multimedia

DOI

2018

A self-adaptive cascade ConvNets model based on label relation mining

Neurocomputing

DOI

2018

Multilevel triplet deep learning model for person re-identification

Pattern Recognition Letters

DOI

2018

QRKISS: A Two-Stage Metric Learning via QR-Decomposition and KISS for Person Re-Identification

Neural Processing Letters

DOI

2018

Deep learning–based traffic sign recognition for unmanned autonomous vehicles

Proceedings of the Institution of Mechanical Engineers Part I Journal of Systems and Control Engineering

DOI

2018

Long Term Traffic Flow Prediction Using Residual Net and Deconvolutional Neural Network

Lecture notes in computer science

DOI

2018

Travel pattern modelling and future travel behaviour prediction based on GMM and GPR

International Journal of Simulation and Process Modelling

DOI

2018

An Improved Convolutional Neural Network Algorithm for Multi-Label Classification

International Conferences on Audio, Language and Image Processing

DOI

2017

面向计算机专业的软件开发技术课程集成发现教学法探索

《计算机应用与软件》

2017

过程可视化类C编译器的教学辅助软件

《计算机与现代化》

2017

基于卷积神经网络的谣言检测

《计算机应用》

2017

编译原理教学方法研讨与实践考核改革

《计算机教育》

2017

Optimized Automatic Seeded Region Growing Algorithm with Application to ROI Extraction

International Journal of Image and Graphics

DOI

2017

Improved Candidate Answers Ranking for QA

International Conference on Advanced Cloud and Big Data

DOI

2017

Empirical Study of Pedestrian Detection Algorithm Based on Ensemble Learning

IEEE International Symposium on Autonomous Decentralized Systems (ISADS)

DOI

2017

Automatic Image Annotation Based on Multi-Auxiliary Information

IEEE Access

DOI

2017

A Self-adaptive Cascade ConvNets Model Based on Three-Way Decision Theory

Communications in computer and information science

DOI

2017

Mining Mobile Phone Base Station Data Based on Clustering Algorithms with Application to Public Traffic Route Design

Lecture notes in computer science

DOI

2017

Discriminative Transfer Learning Siamese CNN for Person Re-identification

Asian Conference on Pattern Recognition

DOI

2016

“人机交互导论”课程双语教学实践与探索

《教育教学论坛》

2016

基于特征融合与多元关系一致性的社会标签精化模型

《南京大学学报(自然科学)》

2016

Bayesian rule based fast TU depth decision algorithm for high efficiency video coding

Visual Communications and Image Processing

DOI

2016

Fusion of multiple channel features for person re-identification

Neurocomputing

DOI

2016

Multiple granularity fused mobile forensics algorithm

Simulation Modelling Practice and Theory

DOI

2016

Biomedical Named Entity Recognition Based on Multistage Three-Way Decisions

Communications in computer and information science

DOI

2016

Optimal stopping theory based fast coding tree unit decision for high efficiency video coding

Visual Communications and Image Processing

DOI

2015

Lane Detection Method Based on Improved RANSAC Algorithm

IEEE International Symposium on Autonomous Decentralized Systems (ISADS)

DOI

2015

A Hybrid Feature Based Mobile Forensics System

IEEE International Symposium on Autonomous Decentralized Systems (ISADS)

DOI

2014

Early detection of all-zero 4×4 blocks in High Efficiency Video Coding

Journal of Visual Communication and Image Representation

DOI

2014

A multi-segment lane-switch algorithm for efficient real-time lane detection

IEEE International Conference on Information and Automation (ICIA)

DOI

2014

A Framework of Video Coding for Compressing Near-Duplicate Videos

Lecture notes in computer science

DOI

2014

Bayes Network Based Collaborating Control Algorithm in Active Multicamera Network with Applications to Object Tracking

Mathematical Problems in Engineering

DOI

2014

Online Object Tracking via Collaborative Model within the Cascaded Feedback Framework

Lecture notes in computer science

DOI

2014

A Robust Online Tracking-Detection Co-training Algorithm with Applications to Vehicle Recognition

Rough Sets and Knowledge Technology

DOI

2014

Mixed Pooling for Convolutional Neural Networks

Rough Sets and Knowledge Technology

DOI

2013

基于属性层次的规则挖掘方法研究

《计算机科学》

2013

From Principal Curves to Granular Principal Curves

IEEE Transactions on Cybernetics

DOI

2013

Semi-supervised multi-label image classification based on nearest neighbor editing

Neurocomputing

DOI

2013

Graph embedding discriminant analysis for face recognition

Neural Computing and Applications

DOI

2012

Document-Level Sentiment Classification Based on Behavior-Knowledge Space Method

Lecture notes in computer science

DOI

2012

Semi-supervised Vehicle Recognition: An Approximate Region Constrained Approach

Lecture notes in computer science

DOI

2011

Efficient vehicle identification using MPEG-7 Color Layout Descriptor

DOI

2011

A smoothed Latent Dirichlet Allocation model with application to Business Intelligence

DOI

2011

A Naive Bayesian Multi-label Classication Algorithm With Application to Visualize Text Search Results

2010

基于阻塞先验知识的文本层次分类模型

《模式识别与人工智能》

2010

基于粗糙集的快速KNN文本分类算法

《计算机工程》

2010

“中文信息处理”实践教学探索

《计算机教育》

2010

Visualizing search results based on multi-label classification

IEEE International Conference on Progress in Informatics and Computing

DOI

2010

The research on chinese text multi-label classification

DOI

2010

Chapter 2 Text Representation and Classification Methods 2.1 Text Representation

2010

Classification Framework Based on Variable Precision Rough Set

2010

Chapter 4 Chinese Text Multi-label Classification Algorithm Based on Latent Dirichlet Allocation Model

2010

Chapter 5 A Smoothing Latent Dirichlet Allocation Model for Text Classification Based on Tolerance Rough Set

2010

Fast KNN Algorithm for Text Classification Based on Rough Set

2010

Two-step Feature Selection Algorithm Based on N-gram Representation in Chinese Text Classification

2009

N-grams based feature selection and text representation for Chinese Text Classification

International Journal of Computational Intelligence Systems

DOI

2008

Feature Selection on Chinese Text Classification Using Character N-Grams

Rough Sets and Knowledge Technology

DOI

2008

Comparing different text representation and feature selection methods on Chinese text classification using Character n-grams

2007

A Reasonable Rough Approximation for Clustering Web Users

Springer eBooks

DOI

2021

Improved non-autoregressive dialog state tracking model

Proceedings of 2021 2nd International Conference on Control, Robotics and Intelligent System

DOI

2020

HSCKE: A Hybrid Supervised Method for Chinese Keywords Extraction

Conference Proceeding of 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence (ACAI 2020)

DOI

2019

A CLAIM Approach to Understanding the PointNet

Proceedings of 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence (ACAI 2019)

DOI

2018

A Multiple Granular Cascaded Model of Object Tracking Under Surveillance Videos

Proceedings of 2018 International Conference on Algorithms, Computing and Artificial Intelligence (ACAI 2018)

DOI

2014

融合反义关系的词语语义相似度计算

《第十五届汉语词汇语义学国际研讨会》

2026

HLL: Can Agents Cross Humanity's Last Line of Verification?

arXiv (Cornell University)

DOI

2026

Authorization Closure Graph: Minimal Repair for LLM Agents with Evolving User Instructions

arXiv (Cornell University)

DOI

2026

A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions

arXiv (Cornell University)

DOI

2026

Multilingual Safety Alignment via Self-Distillation

arXiv (Cornell University)

DOI

2026

TME-PSR: Time-aware, Multi-interest, and Explanation Personalization for Sequential Recommendation

arXiv (Cornell University)

DOI

2026

Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift

arXiv (Cornell University)

DOI

2025

CliniChat: A Multi-Source Knowledge-Driven Framework for Clinical Interview Dialogue Reconstruction and Evaluation

arXiv (Cornell University)

DOI

2024

Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing

arXiv (Cornell University)

DOI

2024

DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion

arXiv (Cornell University)

DOI

2022

CHAE: Fine-Grained Controllable Story Generation with Characters, Actions and Emotions

arXiv (Cornell University)

DOI

2011

Smoothing Text Representation Models Based on Rough Set

IGI Global eBooks

DOI