Yiming Dou 窦铱明
Hi! I am a senior student from Shanghai Jiao Tong University (SJTU).
Currently, I'm working with Dr. Ruohan Gao as a
research
intern at Stanford University, supervised by Prof. Jiajun Wu.
I also work with Prof. Yong-Lu Li as an undergraduate
researcher at SJTU, supervised by Prof. Cewu Lu.
My research interests mainly lie in computer vision, multimodal
and robotics.
I'm always happy to make friends with people from various backgrounds. Feel free to contact my WeChat: 18017112986.
I'm actively applying for a Ph.D. position in 2023 Fall!
Email  / 
Google Scholar  / 
Twitter  / 
Github
|
|
02/2023:
🎉
Our paper "The ObjectFolder Benchmark: Multisensory Learning
with Neural and Real Objects" is accepted by CVPR'23.
|
Humans perceive the world with multiple senses,
based on which we establish abstract concepts to understand it.
From the concepts we develop logical reasoning ability,
and thus creating brilliant achievements.
Inspired by the fascinating human intelligence,
my dream is to design human-like intelligent systems,
which can be divided into four specific problems:
Multimodal Perception:
how to effectively incorporate multiple modalities
(e.g., vision, touch, audio, language and even smell or taste)
into AI systems to make them extract
as much information from the surrounding world as possible.
Concept Learning:
how to abstract and summarize the perceived information into high-level concepts
(e.g., languages or symbols),
thus enabling generalizable cross-domain understanding.
Reasoning:
how to extract relations from complex scenes
and perform causal reasoning on the basis of concepts.
Robot Learning:
how to enable agents/robots to interact with the real-world environments and humans
by leveraging the intelligence learnt from the former three stages.
|
Publications
(* indicates equal contribution)
|
|
The ObjectFolder Benchmark: Multisensory Learning with Neural and Real
Objects
Ruohan Gao*,
Yiming Dou*,
Hao Li*,
Tanmay Agarwal,
Jeannette Bohg,
Yunzhu Li,
Li Fei-Fei,
Jiajun Wu
Conference on Computer Vision and Pattern Recognition (CVPR), 2023
arXiv
/ Project Page
/ Interactive Demo
|
|
Bridging The Isolated Islands in Human Action Understanding
Yong-Lu Li*,
Xiaoqian Wu*,
Xinpeng Liu,
Yiming Dou,
Yikun Ji,
Junyi Zhang,
Yixing Li,
Xudong Lu,
Jingru Tan,
Cewu Lu
Under review, 2022
arXiv
/ Project Page
|
|
ReSU: A Novel Interactive-Action Driven Benchmark for Embodied Visual Grounding
Yiming Dou*,
Yong-Lu Li*,
Cewu Lu
Under review, 2022
arXiv
|
|
Discovering A Variety of Objects in Spatio-Temporal Human-Object Interactions
Yong-Lu Li*,
Hongwei Fan*,
Zuoyu Qiu,
Yiming Dou,
Liang Xu,
Hao-Shu Fang,
Peiyang Guo,
Haisheng Su,
Dongliang Wang,
Wei Wu,
Cewu Lu
Technical report, 2022
arXiv
/ Project Page
|
|
Stanford University
2022.03 ~ present
California, U.S.A.
Visiting Research Intern
Supervisor: Prof. Jiajun Wu
|
|
Shanghai Jiao Tong University
2019.09 ~ present
Shanghai, China
B.Eng. in Computer Science and Technology (Honor), Zhiyuan
Honors Program
B.Ec. in Economics (Associate Degree)
Supervisor: Prof. Cewu Lu and Prof. Yong-Lu Li
|
SJTU Overseas Scholarship (two winners in SJTU), SJTU, 2022
|
Academic Excellence Scholarship (top 10%), SJTU, 2022
|
Zhanjiajun Scholarship (six winners in SJTU), SJTU, 2022
|
Meritorious Winner (top 7%), MCM, 2022
|
Merit Student Award (top 5%), SJTU, 2021
|
Zhiyuan Honors Scholarship
(top 5%), SJTU, 2019, 2020, 2021, 2022
|
|