个人资料
- 学院： 数据科学与人工智能研究院
- 性别： 男
- 出生年月：
- 职称： 副教授
- 学位： 博士
- 学历： 博士
- 毕业院校：
- 联系电话：
- 电子邮箱： xiangyu.song@chd.edu.cn
- 通讯地址： 长安大学南校区数智院
- 邮编：
- 传真：
- 办公地址： 长安大学南校区数智院
- 教育经历：
个人简介
副教授，博士生导师。主要研究方向为图结构数据中复杂关系挖掘、交通异常事件视频语言大模型、多模态学习应用等。发表学术论文30余篇，编写英文著作章节3篇，谷歌引用1000+，包括CCF A类学术期刊/会议或中科院一区期刊论文10余篇。近5年所发表学术论文获得高被引论文4篇，热点论文2篇。2023年入选深圳市高层次人才，荣获2023年APWeb-WAIM 联合国际会议最佳学生论文奖，2018年澳大利亚创新创业大赛三等奖，指导学生荣获中国研究生智慧城市技术与创意设计大赛一等奖。曾作为核心骨干成员参与澳大利亚国家级、州政府级科研项目4项、中国科技部重大专项课题2项。受邀担任SCI检索期刊Array Journal客座编委，CCF-C类国际会议APWeb-WAIM发表联合主席、NSE本地联合主席、CIKM、DASFAA、ADMA等国际会议委员会委员及TKDE、AAAI、CVPR、KBS等10多个高水平期刊/会议的审稿人等职务。
硕士招生专业为计算机科学与技术（学术型硕士研究生）和电子信息（专业型硕士研究生），25年名额已满，非常欢迎本科生（包括校内外26年保研同学）加入团队一起学习。
社会职务
u 会议论文集主席：APWeb-WAIM 2023 Proceeding Co-chair (APWeb) u 会议地方主席：International Conference on Network Simulation and Evaluation (NSE) u 会议程序委员会委员：Conference on Information and Knowledge Management (CIKM)
Conference on Database Systems for Advanced Applications (DASFAA)
Conference on Advanced Data Mining and Applications (ADMA)
Conference on Behavioral and Social Computing (BESC) u 客座编辑：Array Journal
u 会议审稿人：Association for the Advancement of Artificial Intelligence (AAAI) Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD) u 期刊审稿人：IEEE Transactions on Knowledge and Data Engineering (TKDE) Knowledge-Based Systems (KBS） Expert Systems with Applications (ESWA） World Wide Web: Internet and Web Information Systems (WWW) IEEE Signal Processing Letters (SPL) International Journal of Machine Learning and Cybernetics (JMLC) International Journal of Knowledge Science and Engineering (IJKSE)
研究领域
1.基于深度学习的图结构数据挖掘应用
2.交通异常事件视频语言大模型 3.多模态学习应用（交通、教育）
科研项目
1. 国家科技部重大攻关项目研发子课题 2022-2024 分布协同****关键技术及系统 项目骨干
论文
论文列表： https://scholar.google.com.au/citations?hl=en&user=XVFB7GcAAAAJ 2025A novel pipeline for tunnel multi-object tracking integrating cross-modality and motion model, Expert Systems with Applications （中科院一区Top） YCFA-Net: A unified framework for vehicle detection and fire anomaly recognition in tunnel scenarios, Expert Systems with Applications（中科院一区Top） SmartTrack: Sparse multiple objects association with selective re-identification tracking, Computers and Electrical Engineering MDATA Knowledge Representation and Management, MDATA Cognitive Model: Theory and Applications Bootstrapping vision–language transformer for monocular 3D visual grounding, IET Image Processing
2024CDGM: Controllable Dataset Generation Method for Cybersecurity, International Conference on Advanced Data Mining and Applications Dynamic evidence decoupling for trusted multi-view learning, ACM Multimedia (MM)（CCF-A） Generating Adversarial Texts by the Universal Tail Word Addition Attack, APWeb-WAIM Joint Conference Yolo-3DMM for simultaneous multiple object detection and tracking in traffic scenarios, IEEE Transactions on Intelligent Transportation Systems（中科院一区Top） A Nonoverlapping Sampling Approach With Peak Data Utilization for Hyperspectral Classification, IEEE Geoscience and Remote Sensing Letters Web and Big Data. APWeb-WAIM 2023 International Workshops: KGMA 2023 and SemiBDMA 2023, Springer (Workshop Proceedings) Web and Big Data: 7th International Joint Conference, Part IV, Springer (Main Conference Proceedings)
2023Unbalanced Multi-view Deep Learning, ACM Multimedia (MM)（CCF-A） YOLO-SA: An Efficient Object Detection Model Based on Self-attention Mechanism, APWeb-WAIM Joint Conference Efficient Multi-object Detection for Complexity Spatio-Temporal Scenes, APWeb-WAIM Joint Conference（CCF-C Best Student Paper） ECS-STPM: An Efficient Model for Tunnel Fire Anomaly Detection, APWeb-WAIM Joint Conference STTR-3D: Stereo Transformer 3D Network for Video-Based Disparity Change Estimation, APWeb-WAIM Joint Conference Research on question retrieval method for community question answering, Multimedia Tools and Applications Progressive deep multi-view comprehensive representation learning, AAAI Conference on Artificial Intelligence（CCF-A） Dynamic correlation adjacency-matrix-based graph neural networks for traffic flow prediction, Sensors Distributed optimization of graph convolutional network using subgraph variance, IEEE Transactions on Neural Networks and Learning Systems（中科院一区Top）
2022A survey on deep learning based knowledge tracing, Knowledge-Based Systems（中科院一区Top） Robust cross-network node classification via constrained graph mutual information, Knowledge-Based Systems（中科院一区Top） Parallelized nonlinear target detection for asbestos identification in large-scale remote sensing data, IEEE Geoscience and Remote Sensing Letters Simultaneous multiple object detection and pose estimation using 3d model infusion with monocular vision, arXiv Preprint Uncertainty-aware multiview deep learning for internet of things applications, IEEE Transactions on Industrial Informatics（中科院一区Top） Sentiment analysis and topic modeling for COVID-19 vaccine discussions, World Wide Web A survey on location-driven influence maximization, arXiv Preprint Bi-CLKT: Bi-Graph Contrastive Learning based Knowledge Tracing, Knowledge-Based Systems（中科院一区Top）
2021Effective sequential learning for student performance prediction, Deakin University (PhD Thesis) Jkt: A joint graph convolutional network based deep knowledge tracing, Information Sciences（中科院一区Top） Deep fusion of multimodal features for social media retweet time prediction, World Wide Web Representation learning for short text clustering, WISE 2021: Web Information Systems Engineering Sequential engagement-based online learning analytics and prediction, Intelligent Systems and Learning Data Analytics in Online Education (Book Chapter)
2020SEPN: A Sequential Engagement Based Academic Performance Prediction Model, IEEE Intelligent Systems Simultaneous detection and tracking with motion modelling for multiple object tracking, ECCV (European Conference on Computer Vision)
20182017
论著： 2025 2024 2023 2021
荣誉奖励
1. 2024 中国研究生智慧城市技术与创意设计大赛一等奖（指导老师） 2. 2023 深圳市高层次人才计划 3. 2023 APWeb 最佳学生论文（Best Student Paper，当年唯一，CCF-C） 4. 2018 澳大利亚国家创新创业大赛-三等奖
|
