基本信息
浏览量:338
职业迁徙
个人简介
Research: My research is in computer vision, machine learning, and computer graphics. I'm interested in the following areas:
Learning from video: What is a good representation of actions and events in a video? How can we best jointly model natural language and video? How can we efficiently scale up training for video datasets from small (~10K) to large (~10M)? Potential applications include large-scale search and retrieval for video and smart video editing.
3D scene understanding: How can we recover a detailed 3D semantic representation of a depicted scene from one or more images? How can we learn to scrape physics from video? How can we learn from real-world interactions in an environment? Potential applications include augmented reality, 2D-3D compositing and editing, and robotics.
Learning from video: What is a good representation of actions and events in a video? How can we best jointly model natural language and video? How can we efficiently scale up training for video datasets from small (~10K) to large (~10M)? Potential applications include large-scale search and retrieval for video and smart video editing.
3D scene understanding: How can we recover a detailed 3D semantic representation of a depicted scene from one or more images? How can we learn to scrape physics from video? How can we learn from real-world interactions in an environment? Potential applications include augmented reality, 2D-3D compositing and editing, and robotics.
研究兴趣
论文共 78 篇作者统计合作学者相似作者
按年份排序按引用量排序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
Reuben Tan,Ximeng Sun,Ping Hu, Jui-Hsien Wang, Hanieh Deilamsalehy,Bryan A. Plummer,Bryan Russell,Kate Saenko
CVPR 2024 (2024)
引用0浏览0引用
0
0
CVPR 2023 (2023): 19123-19132
CVPR 2023 (2023): 2426-2436
CVPR 2023 (2023): 10575-10584
CVPR 2023 (2023): 14784-14793
加载更多
作者统计
合作学者
合作机构
D-Core
- 合作者
- 学生
- 导师
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn