基本信息
views: 14
![](https://originalfileserver.aminer.cn/sys/aminer/icon/show-trajectory.png)
Bio
Research Interests
I am broadly interested in the field of Computer Vision and Deep Learning. Particularly, I have mostly focused on Visual Scene Understanding (VSU) from images and videos, effective methods of Transfer Learning for VSU, building systems that learn with minimal or no supervision in real and diverse scenarios. I am currently working in Vision-Language Modeling, Few-Shot/Zero-Shot/Meta-Learning, Ego-Centric Video Understanding, Video Action Detection/Recognition, Object Detection, Semantic Segmentation, Depth Estimation. Recently, I have shifted my focus on Generative Modeling, 3D Human Digitization, Physics-guided Animation, 3D Human-Motion Synthesis and 3D Texture transfer .
I am broadly interested in the field of Computer Vision and Deep Learning. Particularly, I have mostly focused on Visual Scene Understanding (VSU) from images and videos, effective methods of Transfer Learning for VSU, building systems that learn with minimal or no supervision in real and diverse scenarios. I am currently working in Vision-Language Modeling, Few-Shot/Zero-Shot/Meta-Learning, Ego-Centric Video Understanding, Video Action Detection/Recognition, Object Detection, Semantic Segmentation, Depth Estimation. Recently, I have shifted my focus on Generative Modeling, 3D Human Digitization, Physics-guided Animation, 3D Human-Motion Synthesis and 3D Texture transfer .
Research Interests
Papers共 23 篇Author StatisticsCo-AuthorSimilar Experts
By YearBy Citation主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
CoRR (2024)
Cited0Views0EIBibtex
0
0
AAAI 2024no. 2 (2024): 792-800
CoRR (2023)
2023 IEEE/CVF International Conference on Computer Vision (ICCV) (2023): 10328-10340
CoRR (2023)
CVPR 2023 (2023): 18837-18845
CoRR (2023)
European Conference on Computer Vision (2022): 645-662
Load More
Author Statistics
Co-Author
Co-Institution
D-Core
- 合作者
- 学生
- 导师
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn