个人简介
吉斌,华东理工大学计算机系讲师。主要研究方向包括生成式数字人、角色动画、具身交互行为建模等。在TVCG/CVPR/ICCV/ECCV等国际顶级期刊与会议上发表论文10余篇,其中2篇获选口头报告或亮点论文,并于ICCV 2025荣获最佳论文奖Finalist。更多代表成果详见个人主页: https://bin-ji.github.io/ 。
学术成果
- 1.FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases,International Conference on Computer Vision (ICCV),2025-10
- 2.POMP: Physics-constrainable Motion Generative Model through Phase Manifolds,IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),2025-02
- 3.SPORT: From Zero-shot {P}rompts to Real-time Motion Generation,IEEE Transactions on Visualization and Computer Graphics (TVCG),2025-02
- 4.EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis,European Conference on Computer Vision (ECCV),2024-07
- 5.FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization,IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR),2024-02
- 6.Say Anything with Any Style,AAAI Conference on Artificial Intelligence (AAAI),2023-12
- 7.Style2Talker: High-Resolution Talking Head Generation with Emotion Style and Art Style,AAAI Conference on Artificial Intelligence (AAAI) ,2023-12
- 8.StyleVR: Stylizing Character Animations with Normalizing Flows,IEEE Transactions on Visualization and Computer Graphics (TVCG),2023-03
- 9.EMMN: Emotional Motion Memory Network for Audio-driven Emotional Talking Face Generation,International Conference on Computer Vision (ICCV) ,2023-07
教育经历
- 2014-08 至 2018-06,西安电子科技大学,大学本科
- 2018-09 至 2021-06,上海交通大学,硕士研究生
- 2021-09 至 2025-06,上海交通大学,博士研究生
|