王铮
浙江工业大学计算机学院朝晖特聘副研究员,计算机视觉科研团队成员(Work with 白琮教授)
科研方向
Large Multimodal Modal
Reasoning with Agent, Embodied LMM, Long-tailed Knowledge Discovering & Debiasing
Long Video Understanding
Cache Compression, Instruction Tuning
AI4Science
Large-scale Pretraining, Precipational Forecasting, Physical Infused Model
科研项目
弱相关场景下视频文本语义对齐方法研究,国自然青年科学基金项目,主持,2024.1-2026.12
面向长视频理解的上下文扩展方法研究,省自然探索项目,主持,2025.1-2026.12
视频内容生成与鉴别方法研究,国自然重点项目,参与,2021.1-2025.12
数据安全与隐私保护下的机器学习技术,科技创新2030—“新一代人工智能”重大项目,参与,2021.1-2027.12
科研奖项
面向智能制造的跨域融合感知关键技术及应用,上海市科学技术奖技术发明奖,参与,2023
教育经历
博士,2022年,复旦大学FVL实验室 (Supervised by 姜育刚教授,陈静静教授)
学士,2017年,浙江工业大学计算机学院,健行荣誉生
指导学生
24硕士
陈良圆
胡凯琦
24硕士
陈浩然,视觉多模态Agent(Co-supervised with 白琮)
洪滔, 联合降雨估计与预测(Co-supervised with 白琮)
23硕士
黄堃, 多粒度视频语义检索 (Co-supervised with 白琮)
应楷, 降雨计算外扩(Co-supervised with 白琮)
22硕士
何波贤,异构数据降雨计算(Co-supervised with 白琮)
张晗奕,基于物理模型的临近降雨预测(Co-supervised with 白琮)
王磊, 临近降雨预测 (湖师范,Co-supervised with 白琮)
何贤康,语言引导的视觉跟踪(Co-supervised with 郭东岩)
田文韬,视频关系提取(复旦,Co-supervised with 陈静静)
23本科
秦浩轩、陈思洁、翁昊越、朱琪、蔡景翔、袁锦文
22本科
孔焓彬,长尾视觉知识挖掘
卢美伊,视频长上下文拓展
21本科
林曾荣,跨模态语义检索中的Hubness问题
教学授课
24春 《自然语言理解与处理》(大规模语言模型:从理论到实践)
23/24秋 《人机交互与界面设计》(智能界面+Figma实现的界面设计)
论文发表
2025
Zheng Wang, Kai Ying, Bin Xu, Chunjiao Wang, Cong Bai. From Swath to Full-Disc: Advancing Precipitation Retrieval with Multimodal Knowledge Expansion. KDD 2025. (数据挖掘顶会, CCF-A)
Hui Zhang, Zheng Wang, Zxuan Wu, and Yu-Gang Jiang. DiffusionAD: Denoising Diffusion for Anomaly Detection. TPAMI, 2025. (模式识别顶刊, CCF-A) [Project]
Zheng Wang, Kun Huang, Zenrong Lin, Cong Bai. Event-Driven Hybrid and Cross-Stage Guide for Video Corpus Moment Retrieval. ICMR, 2025. (多媒体会议, CCF-B) [Project]
Zengrong Lin*, Zheng Wang*, Tianwen Qian, Pan Mu, Sixian Chan, Cong Bai. NeighborRetr: Balancing Hub Centrality in Cross-Modal Retrieval. CVPR, 2025. (人工智能顶会, CCF-A) [Project]
Zheng Wang, Hanyi Zhang, Cong Bai. Physics-infused Convolution Network for Radar-Based Precipitation Nowcasting. ICASSP, 2025. (信号处理会议, CCF-B)
Lei Wang, Zheng Wang, Wenjun Hu, Cong Bai. RainHCNet: Hybrid High-Low Frequency and Cross-Scale Network for Precipitation Nowcasting. JSTAR, 2025. (地球观测遥感期刊)
Chao Wang, Luning Zhang, Zheng Wang, Yang Zhou. Can Large Language Models Unveil the Mysteries? An Exploration of Their Ability to Unlock Information in Complex Scenarios. arXiv preprint arxiv:2502.19973.
2024
Zheng Wang*, Xiankang He*, Kaiyang Lan, Ying Cui, Dongyan Guo. TDCL: Dense Semantic Contrastive Learning for Vision-Language Tracking. ECAI, 2024. (Full Talk, 人工智能会议,CCF-B)
Pengxiang Ouyang, Jianan Chen, Qing Ma, Zheng Wang, Cong Bai. Distinguishing Visually Similar Images: Triplet Contrastive Learning Framework for Image-text Retrieval. ICME, 2024. (Oral, 多媒体会议, CCF-B)
Wentao Tian, Zheng Wang, Yuqian Fu, Jingjing Chen, and Lechao Cheng. Open-Vocabulary Video Relation Extraction. AAAI, 2024. (人工智能顶会,CCF-A) [Project]
2023
Hui Zhang, Zuxuan Wu, Zheng Wang, Zhineng Chen, and Yu-Gang Jiang. Prototypical Residual Networks for Anomaly Detection and Localization. CVPR, 2023. (计算机视觉顶会,CCF-A)
2022
Jianggang Zhu*,Zheng Wang*, Jingjing Chen, Yi-Ping Phoebe Chen, Yu-Gang Jiang. Balanced Contrastive Learning for Long-Tailed Visual Recognition. CVPR, 2022. (计算机视觉顶会,CCF-A)
Jingmian Cai*, Zheng Wang*, Huazhu Fu, Jingjing Chen, Yu-Gang Jiang. Data-free Network Debiasing for Long-Tailed Visual Recognition. ICME, 2022. (多媒体会议,CCF-B)
2021
Zheng Wang, Jingjing Chen, and Yu-Gang Jiang. Visual Co-Occurrence Alignment Learning for Weakly- Supervised Video Moment Retrieval. ACM MM, 2021. (多媒体顶会,CCF-A)
ZhengWang, Jianguo Li, and Yu-Gang Jiang. Story-driven Video Editing. TMM, 2021.(多媒体顶刊, SCI TOP期刊)
2020, ..
王铮, 翁泽佳, 王锐, 陈静静, 姜育刚. 基于长短时预测一致性的大规模视频语义识别算法. 中国科学:信息科学,2020. (北大核心,CCF-A)
You Qiaoben, Zheng Wang, Jianguo Li, Yinpeng Dong, Yu-Gang Jiang, and Jun Zhu. Composite Binary Decomposition Networks. AAAI, 2019. (人工智能顶会,CCF-A)
学生竞赛
第十四届中国大学生服务外包创新创业大赛三等奖
社会服务
期刊审稿
TPAMI, TIP, TMM, TCSVT, TOMM, Neurocomputing, MVAP, DMKD
会议审稿
CVPR25/23,ICCV25,ACMMM25/24/23/22, ECCV24, CAI24, ACL23,AAAI23, BMVC22, ICME22/25