汪婧雅
助理教授、研究员、博导
博士毕业院校: 伦敦大学玛丽女王学院
电话: 021-20684854
办公室: 信息学院1C-303B室
专业方向:
单位:
所属课题组:
研究方向: 计算机视觉、机器学习、人工智能
招聘主页:
简介
团队
科研
教学
服务
成果
论文
影集
报道
主要岗位职责(A角)
兼任岗位职责(B角)
兼任岗位职业(C角)

汪婧雅博士现任上海科技大学信息科学与技术学院助理教授、研究员、博导。她于2019年在英国伦敦大学玛丽女王学院获得博士学位,随后在澳大利亚悉尼大学从事博士后研究工作,目前任职上海科技大学信息学院。她的研究方向包括计算机视觉、机器学习、人工智能,目前的研究兴趣侧重于以人为中心的视觉感知、推理与决策。她已发表了多篇计算机视觉顶级期刊和会议文章,包括CVPR、ICCV、 ECCV、NeurIPS、AAAI、IJCAI、ICLR等,担任CVPR、WACV等会议的领域主席。攻博期间入选 CVPR Doctoral Consortium Award,第一作者论文入选Computer Vision News Magazine 评比的 2018 Best of CVPR Paper,2023 年入选百度AI 华人女性青年学者榜。 

更多信息请参见她的个人主页:http://faculty.sist.shanghaitech.edu.cn/faculty/wangjingya/


  • 计算机视觉

  • 机器学习

  • 人工智能

CS172- 《计算机视觉I

CS272- 《计算机视觉II
  • 1. Guo, Song;Wang, Jingya;Wang, Xinchao;Tao, Dacheng#, Online Multiple Object Tracking with Cross-Task Synergy, 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021,
  • 2. Liu, Fang;Wang, Jingya;Tang, Xu;Liu, Jia;Zhang, Xiangrong;Xiao, Liang#, Adaptive Graph Convolutional Network for PolSAR Image Classification, IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022,
  • 3. Sun, Guoxing;Chen, Xin;Chen, Yizhang;Pang, Anqi;Lin, Pei;Jiang, Yuheng;Xu, Lan;Yu, Jingyi;Wang, Jingya#, Neural Free-Viewpoint Performance Rendering under Complex Human-object Interactions, MM 2021 - PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, 17 Oct 2021, 4651-4660
  • 4. Duan, Yiqun;Wang, Zhen;Wang, Jingya;Wang, Yu-Kai;Lin, Chin-Teng#, Position-aware image captioning with spatial relation, NEUROCOMPUTING, 01 Aug 2022, 497:28-38
  • 5. Chang, Wanxing;Shi, Ye;Hoang, Duong Tuan;Wang, Jingya#, Unified Optimal Transport Framework for Universal Domain Adaptation, ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS, Nov 2022,
  • 6. Qiu, Zesong;Li, Yuwei;He, Dongming;Zhang, Qixuan;Zhang, Longwen;Zhang, Yinghao;Wang, Jingya;Xu, Lan;Wang, Xudong;Zhang, Yuyao;Yu, Jingyi#, SCULPTOR: Skeleton-Consistent Face Creation Using a Learned Parametric Generator, ACM TRANSACTIONS ON GRAPHICS, 01 Dec 2022, 41(6)
  • 7. Duan, Yiqun;Wang, Zhen;Li, Yi;Wang, Jingya#, Cross-domain multi-style merge for image captioning, COMPUTER VISION AND IMAGE UNDERSTANDING, Feb 2023, 228
  • 8. Zhang, Juze;Wang, Jingya;Shi, Ye;Gao, Fei;Xu, Lan;Yu, Jingyi#, Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimations, ACM MULTIMEDIA, 2022,
  • 9. Zhang, Juze;Shi, Ye;Ma, Yuexin;Xu, Lan;Yu, Jingyi;Wang, Jingya#, IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation, AAAI, 2023,
  • 10. Liang, Han;He, Yannan;Zhao, Chengfeng;Li, Mutian;Wang, Jingya;Yu, Jingyi;Xu, Lan#, HybridCap: Inertia-aid Monocular Capture of Challenging Human Motions, AAAI, 2023,
  • 11. Sun, Haixiang;Wang, Jingya;Shi, Ye;Tuan, Hoang Duong;Poor, H Vincent;Tao, Dacheng#, Alternating Differentiation for Optimization Layers, THE INTERNATIONAL CONFERENCE ON LEARNING REPRESENTATIONS, 2023,
  • 12. Cong, Peishan;Xu, Yiteng;Ren, Yiming;Zhang, Juze;Xu, Lan;Wang, Jingya;Yu, Jingyi;Ma, Yuexin#, Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDAR, AAAI, 2023,
  • 13. Yu, chunlin;Shi, Ye;Liu, Zimo;Gao, Shenghua;Wang, Jingya#, Lifelong Person Re-identification via Knowledge Refreshing and Consolidation, AAAI, 2023,