基本信息
浏览量:0
职业迁徙
个人简介
My research primarily centers around the domains of visual intelligence and vision-language learning. Presently, visual representations exhibit complexity and intermingling. Conversely, human perception apprehends the world by organizing objects or visual concepts as fundamental units, known as an object-centric approach. Moreover, humans tend to segment objects prior to recognizing their labels. Therefore, my current research endeavors involve developing a novel visual modeling methodology that can autonomously segment objects and acquire object-centric representations in an unsupervised manner. Subsequently, I aim to establish connections between this architecture and language to construct a robust model endowed with compositional understanding capabilities.
研究兴趣
论文共 8 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
CoRR (2024)
引用0浏览0EI引用
0
0
CoRR (2023)
引用0浏览0EI引用
0
0
arXiv (Cornell University) (2023)
CoRR (2023): 1195-1210
引用0浏览0EI引用
0
0
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