王卫宁

王卫宁  /  博士

  • 职  称: 副研究员
  • 邮  编: 100190
  • 电子邮件: weining.wang@nlpr.ia.ac.cn
  • 部门/实验室: 紫东太初大模型研究中心
  • 通讯地址: 北京市海淀区中关村东路95号智能化大厦

个人简历

1. 2023.08-今     中国科学院自动化研究所 紫东太初大模型研究中心 副研究员
2. 2022.10-2023.07   中国科学院自动化研究所 紫东太初大模型研究中心 助理研究员
3. 2020.10-2022.09  中国科学院自动化研究所 模式识别国家重点实验室 助理研究员
4. 2015.09-2020.09   中国科学院自动化研究所 模式识别国家重点实验室 博士
5. 2011.09-2015.06  华北电力大学 学士

研究方向

视频内容理解、视频内容生成、多模态分析

承担科研项目情况

1. 基于低成本标注样本的长视频行为分析,国家自然科学基金青年基金项目,2022.01-2024.12,项目负责人

2. 受限环境的跨模态目标识别与行为理解,国家自然科学基金重点项目, 2022.01-2025.12,主要完成人

3. 基于结构化深度学习的场景理解,国家自然科学基金面上项目,2019.01-2022.12,主要完成人

4. 多模态知识驱动的图文匹配,国家自然科学基金面上项目,2023.01-2026.12,项目骨干


代表论著

1.  Weining Wang, Tianwei Lin, Dongliang He, Fu Li, Shilei Wen, Liang Wang, and Jing Liu. "Semi-supervised temporal action proposal generation via exploiting 2-d proposal map." IEEE Transactions on Multimedia (TMM), 2021. (JCR一区,IF: 8.182)

2.  Weining Wang, Yan Huang, and Liang Wang. "Language-driven temporal activity localization: A semantic matching reinforcement learning model." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), 2019. (口头报告, CCF-A类会议)

3.  Weining Wang, Yan Huang, and Liang Wang. "Long video question answering: A Matching-guided Attention Model." Pattern Recognition (PR), 2020. (JCR一区,IF: 8.518)

4.  Weining Wang, Qi Li, and Liang Wang. "Robust Object Tracking via Information Theoretic Measures." International Journal of Automation and Computing (IJAC), 2020.

5.  Jing Liu, Sihan Chen, Xingjian He, Longteng Guo, Xinxin Zhu, Weining Wang, Jinhui Tang. "VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset." IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024. (JCR一区,IF:24.314)

6.  Mingzhen Sun, Weining Wang, Yanyuan Qiao, Jiahui Sun, Zihan Qin, Longteng Guo, Xinxin Zhu, Jing Liu. "MM-LDM: Multi-Modal Latent Diffusion Model for Sounding Video Generation." ACM International Conference on Multimedia (ACM MM), 2024. (CCF-A类会议)

7.  Mingzhen Sun, Weining Wang, Zihan Qin, Jiahui Sun, Sihan Chen, Jing Liu. "GLOBER: Coherent Non-autoregressive Video Generation via GLOBal Guided Video DecodER", Annual Conference on Neural Information Processing Systems (NeurIPS), 2023. (CCF-A类会议)

8.  Mingzhen Sun, Weining Wang, Xinxin Zhu, Jing Liu. "MOSO: Decomposing MOtion, Scene and Object for Video Prediction. " In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), 2023.  (CCF-A类会议)

9.   Jiawei Liu, Weining Wang, Sihan Chen, Xinxin Zhu, Jing Liu. "Sounding Video Generator: A Unified Framework for Text-guided Sounding Video Generation. " IEEE Transactions on Multimedia (TMM), 2023.(JCR一区,IF: 8.182)

10.Yepeng Tang, Weining Wang, Chunjie Zhang, Jing Liu, Yao Zhao. "Temporal Action Proposal Generation With Action Frequency Adaptive Network." IEEE Transactions on Multimedia (TMM), 2023.(JCR一区,IF: 8.182)

11.Mingzhen Sun, Weining Wang, Xinxin Zhu, Jing Liu. "Reparameterizing and dynamically quantizing image features for image generation" Pattern Recognition (PR), 2023.(JCR一区,IF: 8.518)

12.Qi Li, Weining Wang, Yuanyan Tang, Chengzhong Xu, Zhenan Sun. "Semantic-based conditional generative adversarial hashing with pairwise labels. " Pattern Recognition (PR), 2023. (JCR一区,IF: 8.518)

13.Yepeng Tang, Weining Wang, Yanwu Yang, Chunjie Zhang, and Jing Liu. "Anchor-free temporal action localization via Progressive Boundary-aware Boosting." Information Processing & Management (IPM), 2023. (JCR一区,IF:7.466)

14.Jiawei Liu, Weining Wang, Wei Liu, Qian He, Jing Liu. "ED-T2V: An Efficient Training Framework for Diffusion-Based Text-To-Video Generation." In Proceedings of the International Joint Conference on Neural Networks (IJCNN), 2023.

15. Chunfeng Song, Yongzhen Huang, Weining Wang, and Liang Wang. "CASIA-E: a large comprehensive dataset for gait recognition." IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022. (JCR一区,IF:24.314)


获奖及荣誉

2023年中国科学院科苑名匠团队

2022年世界人工智能大会最高奖项-SAIL 奖

2022年欧洲计算机视觉国际会议(ECCV)细粒度视频行为检测竞赛第一名

2022年国际模式识别会议(ICPR)多模态视频字幕识别竞赛第二名

2021年计算机视觉国际大会(ICCV) 大规模视频场景理解竞赛第一名

2020年北京图象图形学学会优秀博士论文提名奖


专利成果

1. 视频量化编解码方法、装置、设备及存储介质, 第1作者,专利号:ZL202210068433.5

2. 图像生成方法、装置、设备及存储介质,第1作者,专利号:ZL202210114595.8

3. 一种视频生成方法、装置、电子设备及存储介质,第1作者,专利号:ZL202210068441.X

4. 视频问答的交互方法及系统,第2作者,专利号:ZL202110069976.4


社会任职

中国人工智能学会模式识别专委会 委员 中国图象图形学学会女科技工作者专委会 委员