 |
秦景辉 QIN JINGHUI 讲师 职称：讲师 所属学院：信息工程学院 导师类别：硕导 职务：讲师 科研方向：自然语言处理，多模态人工智能, 计算机视觉 联系方式：qinjinghui@gdut.edu.cn 硕士招生学院：信息工程学院 |
个人简述：
本人本硕博均毕业于中山大学，于2022年12月加入广东工业大学信息工程学院，主要从事自然语言处理，多模态人工智能，计算机视觉等方向的研究，包括多模态情感分析，多模态推荐，AI生成内容检测，数学解题等方向。
学科领域：
科学学位：
专业学位：
教育背景：
2008.9~2012.6 中山大学 软件学院 本科
2012.9~2014.6 中山大学 软件学院 硕士研究生
2016.9~2020.6 中山大学 数据科学与计算机学院 博士研究生
工作经历：
2014.7-2016.8 广州云晫信息科技有限公司 工程师
2020.11-2022.10 中山大学 博士后
2022.12-至今 广东工业大学 讲师，青年百人
主要论文：
u Jinghui Qin, Changsong Liu, Tianchi Tang, Dahuang Liu, Minghao Wang, Qianying Huang, Rumin Zhang. “Mental-Perceiver: Audio-textual Multi-modal Learning for Estimating Mental Disorders”, The 39th Annual AAAI Conference on Artificial Intelligence, 2025.（CCF-A类会议, 人工智能顶级会议）
u Lei Tang, Jinghui Qin(通信作者), Wenxuan Ye, Hao Tan, Zhijing Yang. “Adaptive Few-shot Prompting for Machine Translation with Pre-trained Language Models”, The 39th Annual AAAI Conference on Artificial Intelligence, 2025. （CCF-A类会议, 人工智能顶级会议）
u Qingling Li, Wushao Wen(通信作者), Jinghui Qin(通信作者). “Boundary-Driven Table-Filling with Cross-Granularity Contrastive Learning for Aspect Sentiment Triplet Extraction”, 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing. （CCF-B类会议, 声学、语音与信号处理顶级会议）
u Qiangpu Chen, Wushao Wen, Jinghui Qin(通信作者). “GlobalSR: Global context network for single image super-resolution via deformable convolution attention and fast Fourier convolution”, Neural Networks, 2024.（中科院SCI一区TOP期刊）
u Tianshui Chen, Weihang Wang, Tao Pu, Jinghui Qin(通信作者), Zhijing Yang, Jie Liu, Liang Lin. “Dynamic correlation learning and regularization for multi-label confidence calibration”, IEEE Transactions on Image Processing, 2024.（中科院SCI一区TOP期刊, 图像处理顶级期刊）
u Qingling Li, Wushao Wen, Jinghui Qin(通信作者). “Improving span-based Aspect Sentiment Triplet Extraction with part-of-speech filtering and contrastive learning”, Neural Networks, 2024.（中科院SCI一区TOP期刊）
u Jinghui Qin, Zhongzhan Huang, Ying Zeng, Quanshi Zhang, Liang Lin. “An Introspective Data Augmentation Method for Training Math Word Problem Solvers”, IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2024.（中科院SCI二区TOP期刊，自然语言处理顶级期刊）
u Shanshan Zhong, Zhongzhan Huang, Daifeng Li, Wushao Wen, Jinghui Qin(通信作者), Liang Lin. “Mirror Gradient: Towards Robust Multimodal Recommender Systems via Exploring Flat Local Minima”, Proceedings of the ACM on Web Conference 2024, 2024.（CCF-A类会议, 计算机顶级会议）
u Qiangpu Chen, Jiahua Huang, Wushao Wen, Qingling Li, Rumin Zhang, Jinghui Qin(通信作者) . “CAT: Continual Adapter Tuning for aspect sentiment classification”, Neurocomputing, 2024. （中科院SCI二区TOP期刊）
u Qiangpu Chen, Jinghui Qin(通信作者), Wushao Wen. “RepECN: Making ConvNets Better Again for Efficient Image Super-Resolution”, Sensors, 2023.（中科院SCI三区期刊）
u Qiangpu Chen, Jinghui Qin(通信作者), Wushao Wen. “ALAN: Self-Attention is Not All You Need for Image Super-Resolution”, IEEE Signal Processing Letters, 2023.（中科院SCI二区期刊）
u Shanshan Zhong, Zhongzhan Huang, Wushao Wen, Zhijing Yang, Jinghui Qin(通信作者). “ESA: Excitation-Switchable Attention for convolutional neural networks”, Neurocomputing, 2023.（中科院SCI二区TOP期刊）
u Shanshan Zhong, Zhongzhan Huang, Weushao Wen, Jinghui Qin(通信作者), Liang Lin. “Sur-adapter: Enhancing text-to-image pre-trained diffusion models with large language models”, Proceedings of the 31st ACM International Conference on Multimedia, 2023.（CCF-A类会议, 多媒体顶级会议）
u Jinghui Qin, Lihuang Fang, Ruitao Lu, Liang Lin, Yukai Shi. “ADASR: An adversarial auto-augmentation framework for hyperspectral and multispectral data fusion”, IEEE Geoscience and Remote Sensing Letters, 2023.（中科院SCI三区期刊）
u Shanshan Zhong, Wushao Wen, Jinghui Qin(通信作者), Qiangpu Chen, Zhongzhan Huang. “LSAS: Lightweight sub-attention strategy for alleviating attention bias problem”, 2023 IEEE International Conference on Multimedia and Expo (ICME), 2023. （CCF-B类会议，国际多媒体旗舰会议）
u Jinghui Qin, Zhicheng Yang, Jiaqi Chen, Xiaodan Liang, Liang Lin. “Template-Based Contrastive Distillation Pretraining for Math Word Problem Solving”, IEEE Transactions on Neural Networks and Learning Systems, 2023.（中科院SCI一区TOP期刊，人工智能顶级期刊）
u Jinghui Qin, Rumin Zhang. “Lightweight single image super-resolution with attentive residual refinement network” , Neurocomputing, 2022.（中科院SCI二区TOP期刊）
u Hao Li*, Jinghui Qin*(共同一作), Zhijing Yang, Pengxu Wei, Jinshan Pan, Liang Lin, Yukai Shi. Real-World Image Super-Resolution by Exclusionary Dual-Learning. IEEE Transactions on Multimedia. 2022.（中科院SCI一区期刊Top, 多媒体处理顶级期刊）
u Zhicheng Yang*, Jinghui Qin*(共同一作), Jiaqi Chen, Liang Lin, Xiaodan Liang. “LogicSolver: Towards Interpretable Math Word Problem Solving with Logical Prompt-enhanced Learning”, Findings of the Association for Computational Linguistics: EMNLP 2022. (自然语言处理顶级会议)
u Jinghui Qin, Xiaodan Liang, Yining Hong, Jianheng Tang, Liang Lin. “Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks”, The 59th Annual Meeting of the Association for Computational Linguistics(ACL) , 2021. （CCF-A类会议,自然语言处理顶级会议）
u Jinghui Qin, Lihui Lin, Xiaodan Liang, Rumin Zhang, Liang Lin. “Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems”, The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020. （CCF-B类会议, 自然语言处理顶级会议）
u Jinghui Qin, Zheng Ye, Jianheng Tang, Xiaodan Liang. “Dynamic Knowledge Routing Network For Target-Guided Open-Domain Conversation”, Thirty-Fourth AAAI Conference on Artificial Intelligence(AAAI), 2020.（大会焦点论文）（CCF-A类会议, 人工智能顶级会议）
u Jinghui Qin, Yongjie Huang, Wushao Wen. “Multi-scale feature fusion residual network for Single Image Super-Resolution”, Neurocomputing, 2019.（中科院SCI二区TOP期刊）
u Jinghui Qin, Ziwei Xie, Yukai Shi, Wushao Wen. “Difficulty-aware Image Super Resolution Via Deep Adaptive Dual-Network”, IEEE International Conference on Multimedia and Expo (ICME), 2019.（大会口头报告）（CCF B 类会议，国际多媒体旗舰会议）
u Wenkuan Zhao, Shanshan Zhong, Yifan Liu, Wushao Wen, Jinghui Qin, Mingfu Liang, Zhongzhan Huang. “DVIB: Towards Robust Multimodal Recommender Systems via Variational Information Bottleneck Distillation”, Proceedings of the ACM on Web Conference 2025, 2025.（CCF-A类会议, 计算机顶级会议）
u Zhongzhan Huang, Shanshan Zhong, Wushao Wen, Jinghui Qin, Liang Lin. “Stripe Observation Guided Inference Cost-Free Attention Mechanism”, European Conference on Computer Vision, 2024. （CCF-B类会议, 计算机视觉顶级会议）
u Haoxian Ruan, Zhihua Xu, Zhijing Yang, Yongyi Lu, Jinghui Qin, Tianshui Chen. “Learning Semantic-Aware Representation in Visual-Language Models for Multi-Label Recognition with Partial Labels”, ACM Transactions on Multimedia Computing, Communications and Applications, 2024. （中科院SCI三区期刊）
u Xiaoyu Xian, Jinghui Qin, Yukai Shi, Daxin Tian, Liang Lin. “Exploring Out-of-Distribution Scene Text Recognition for Driving Scenes with Hybrid Test-Time Adaptation”, Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2024.（CCF-C类会议）
u Shanshan Zhong, Wushao Wen, Jinghui Qin, Zhongzhan Huang. “DEEPAM: Toward Deeper Attention Module in Residual Convolutional Neural Networks”, International Conference on Artificial Neural Networks, 2024.（CCF-C类会议）
u Xiaoyu Xian, Qi Zhou, Jinghui Qin, Xiaojun Yang, Yin Tian, Yukai Shi, Daxin Tian. “CROSE: Low-light enhancement by CROss-SEnsor interaction for nighttime driving scenes”, Expert Systems with Applications, 2024.（中科院SCI一区TOP期刊）
u Yongsen Zheng, Ruilin Xu, Ziliang Chen, Guohua Wang, Mingjie Qian, Jinghui Qin, Liang Lin. “HyCoRec: Hypergraph-Enhanced Multi-Preference Learning for Alleviating Matthew Effect in Conversational Recommendation”, Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024.（CCF-A类会议,自然语言处理顶级会议）
u Zhaohuan Zhan, Jinghui Qin, Wei Zhuo, Guang Tan. “Enhancing Vision and Language Navigation with Prompt-based Scene Knowledge”, IEEE Transactions on Circuits and Systems for Video Technology, 2024.（中科院SCI一区TOP期刊）
u Qingyi Liu, Jinghui Qin, Wenxuan Ye, Hao Mou, Yuxuan He, Keze Wang. “Adaptive Prompt Routing for Arbitrary Text Style Transfer with Pre-trained Language Models”, Proceedings of the AAAI Conference on Artificial Intelligence, 2024.（CCF-A类会议,人工智能顶级会议）
u Yongsen Zheng, Ziliang Chen, Jinghui Qin, Liang Lin. “FacetCRS: Multi-Faceted Preference Learning for Pricking Filter Bubbles in Conversational Recommender System”, Proceedings of the AAAI Conference on Artificial Intelligence, 2024.（CCF-A类会议,人工智能顶级会议）
u Yongfeng Chen, Junpeng Tan, Zhijing Yang, Yukai Shi, Jinghui Qin. “Unsupervised multi-perspective fusing semantic alignment for cross-modal hashing retrieval”, Multimedia Tools and Applications, 2024. （中科院SCI四区期刊）
u Mingjie Qian, Yongsen Zheng, Jinghui Qin, Liang Lin. “HutCRS: Hierarchical User-Interest Tracking for Conversational Recommender System”, Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023. （CCF-B类会议,自然语言处理顶级会议）
u Liang Wang, Wushao Wen, Jinghui Qin. “Multi-view Graph Representation Learning via Mutual Learning for Drug Recommendation via Multi-view Graph Learning”, Proceedings of the 2023 5th International Conference on Internet of Things, Automation and Artificial Intelligence, 2023.（EI会议）
u Junpeng Tan, Zhijing Yang, Jielin Ye, Ruihan Chen, Yongqiang Cheng, Jinghui Qin, Yongfeng Chen. “Cross-modal hash retrieval based on semantic multiple similarity learning and interactive projection matrix learning”, Information Sciences, 2023. （中科院SCI一区TOP期刊）
u Liucun Lu, Jinghui Qin, Zequn Jie, Lin Ma, Liang Lin, Xiaodan Liang. “RecFormer: Recurrent Multi-modal Transformer with History-Aware Contrastive Learning for Visual Dialog”, Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2023.（CCF-C类会议）
u Yongsen Zheng, Jinghui Qin, Pengxu Wei, Ziliang Chen, Liang Lin. “Cipl: Counterfactual interactive policy learning to eliminate popularity bias for online recommendation”, IEEE Transactions on Neural Networks and Learning Systems, 2023.（中科院SCI一区TOP期刊）
u Shanshan Zhong, Wushao Wen, Jinghui Qin. “SPEM: Self-adaptive pooling enhanced attention module for image recognition”, International Conference on Multimedia Modeling, 2023. （CCF-C类会议）
u Zhongzhan Huang, Mingfu Liang, Jinghui Qin, Shanshan Zhong, Liang Lin. “Understanding self-attention mechanism via dynamical system perspective”, Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023. （CCF-A类会议, 计算机视觉顶级会议）
u Shanshan Zhong, Jinghui Qin, Zhongzhan Huang, Daifeng Li. “CEM: Machine-Human Chatting Handoff via Causal-Enhance Module”, The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022.（CCF-B类会议,自然语言处理顶级会议）
u Jiaqi Chen, Tong Li, Jinghui Qin, Pan Lu, Liang Lin, Chongyu Chen, Xiaodan Liang. “UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression”, The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022.（CCF-B类会议,自然语言处理顶级会议）
u Zhicheng Yang, Jinghui Qin, Jiaqi Chen, Xiaodan Liang. “Unbiased Math Word Problems Benchmark for Mitigating Solving Bias” , Findings of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: NAACL 2022. （CCF-C类会议,自然语言处理顶级会议）
u Jiaqi Chen, Jianheng Tang, Jinghui Qin, Xiaodan Liang, Lingbo Liu, Eric P Xing, Liang Lin. “GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning”, Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. （自然语言处理顶级会议）
u Lishan Huang, Zheng Ye, Jinghui Qin, Liang Lin, Xiaodan Liang. “GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems” , The 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020. （CCF-B类会议, 自然语言处理顶级会议）
u Yukai Shi, Jinghui Qin, Pengxu Wei, Wanli Ouyang, Liang Lin. “Perceptual Image Enhancement by Relativistic Discriminant Learning With Cross-Scale Aggregated Representation”, IEEE ACCESS, 2019. （中科院二区期刊）
u Yongjie Huang, Qiping Yang, Jinghui Qin, Wushao Wen. “Phishing URL Detection via CNN and Attention-Based Hierarchical RNN”, 18th IEEE International Conference On Trust, Security And Privacy In Computing And Communications(TrustCom), 2019.（CCF C类会议）
u Xi Chen, Chongwu Dong, Jinghui Qin, Long Yin, Wushao Wen .“Label-Attentive Hierarchical Network for Document Classification”, 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence(ACAI), 2020. （EI检索）
u Yongjie Huang, Jinghui Qin, Wushao Wen. “Phishing URL Detection Via Capsule-Based Neural Network”, IEEE 13th International Conference on Anti-counterfeiting, Security, and Identification (ASID), 2019. (EI检索)
u Chang Wang, Chongwu Dong, Jinghui Qin, Xiaoxing Yang, Wushao Wen. “Energy-efficient Offloading Policy for Resource Allocation in Distributed Mobile Edge Computing”. IEEE Symposium on Computers and Communications (ISCC), 2018.（CCF C类会议）
知识产权：
u CN201510701751 一种外网客户端接入私有云云桌面方法，第二发明人，授权
u CN201610805160 基于虚拟桌面和虚拟操作系统的自适应云桌面服务系统，第四发明人，授权
u CN201710128026 一种多CDN辅助的多层云的直播分发系统，第五发明人，授权
u CN201910886251 一种基于深度学习的层次化钓鱼网站检测方法，第三发明人，授权
u CN201910073607 基于知识网络精准在线教育系统的多维度信息学情分析方法，第三发明人，授权
u 202411664912.9 一种基于大语言模型的机器翻译方法及系统，第一发明人，申请
u 202411602543.0 一种基于提示学习和对齐策略的对话推荐模型训练方法及对话推荐方法，第二发明人，申请
u 202411588223.4 基于频域解耦和交叉注意力的光伏发电预测方法与系统，第一发明人，申请
u 202410576404.9 一种提升大模型特定话题回答效果的方法和系统，第二发明人，申请
u 202410466556.3 一种基于结构重参数化的图像超分辨率增强方法及系统，第一发明人，申请
u 202411788172.X 运动伤病风险检测方法、系统及运动伤病风险部位定位方法、系统，第一发明人，申请
u 202411494117.X 一种利用对齐的多模态特征进行几何问题推理方法及系统，第一发明人，申请
u 202411798679.3 一种基于空间交互特征的跨被试脑电信号情绪识别模型训练方法、模型训练系统及情绪识别方法，第一发明人，申请
科研项目：
u 国家自然科学基金-青年科学基金，知识增强的表示学习模型及其在应用题求解中的应用，2023.01-2025.12，广东工业大学，项目负责人，在研
u 中国博士后科学基金-面上项目(第70批)，融合知识和图推理的初等数学应用题求解关键技术研究，2021.11.15-2022.10.31，中山大学，项目负责人，已结题
u 广东省自然科学基金-面上项目，初等数学应用题求解关键技术研究，2022.01.01-2024.12.31，广东工业大学，项目负责人，已结题
u 广州市2024年度基础与应用基础研究青年博士“启航”项目，融合大语言模型的弱监督数学应用题自动求解研究，2024.01.01-2025.12.31，广东工业大学，项目负责人，在研
u 科技创新2030-“新一代人工智能”重大项目，复杂版面手写图文识别及理解关键技术研究（子课题：理科解题步骤分析评分和抄袭检测），2021.01.01-2024.12.31，暗物智能科技（广州）有限公司，参与人，已结题
u 国家自然科学基金-面上项目，多模态环境下认知推理驱动的知识表达学习及可信赖智能问答关键技术研究，2023.01-2026.12，中山大学，主要参与人，在研
u 企业合作项目，智能数字内容生成与编辑平台，广东工业大学，项目负责人，已结题
u 企业合作项目，教材编写专项技术服务，广东工业大学，项目负责人，已结题
u 企业合作项目，视频压缩还原算法优化评估及样机测试，广东工业大学，项目负责人，已结题
u 企业合作项目，视频画质评估指标模型及视频质量评估工具，广东工业大学，项目负责人，已结题
教学活动：
数据挖掘、高级程序语言设计、python网页爬虫、知识图谱，自然语言处理
