Dandan Shan (单丹丹)
PhD candidate, UMich CSE
Email: dandans AT umich.edu
Office: UMich BBBB 3929
Google Scholar
/ CV
/ Github
/ X
Biography
I am a final-year Ph.D. candidate of Computer Science and Engineering at the University of Michigan and a visiting student at New York University, working with Prof. David Fouhey on Computer Vision.
Previously, I received my M.S.E. in Electrical and Computer Engineering from the University of Michigan and B.Eng. in Software Engineering from Soochow University.
I am looking for industry jobs or postdoc positions in 2025. Please feel free to contact me if you think I’d be a good match!
News
[2025/02] Thrilled to co-organize “Agents in Interaction, from Humans to Robots” workshop at CVPR 2025.
[2024/04] Excited to be an intern at the Nvidia Seattle Robotics Lab this summer!
[2024/03] Gave a invited talk at Columbia University about "Understanding Human Hands and Interaction".
[2023/06] Gave a talk on "Towards A Richer 2D Understanding of Hands at Scale" at 4DHOI workshop at CVPR2023.
[2023/01] EPIC-KITCHENS HOS challenge is now open! Welcome to your participation and submit to Codalab.
[2022/10] Excited to be selected as an ECCV2022 Outstanding Reviewer.
[2022/04] I will intern at Adobe Research this summer!
[2021/12] I received the Rackham International Student Fellowship.
[2021/09] COHESIV is accepted at NeurIPS2021.
[2020.02] 100DOH is accepted at CVPR2020 as Oral.
Research Interests
My research interests are understanding human interaction with the world and human skill transfer learning (e.g. to robots) either from a single human video or large video data. My works have been focusing on hand-object interaction both in 2D and 3D, and we have released several important datasets in the field: 100DOH (100 Days of Hand), VISOR and Hands23. I am broadly interested in research on video understanding, 3D reconstruction, and vision for robotics.
Publications
Slot-Level Robotic Placement via Visual Imitation from Single Human Video
Dandan Shan, Kaichun Mo, Wei Yang, Yu-Wei Chao, David Fouhey, Dieter Fox, Arsalan Mousavian
In Submission, 2024
Teaching robots slot-level pick-place manipulation from a single human demonstration video; segmenting placement slot masks for pick-place videos using GenAI for training data augmentation.
Reconstructing Hands in 3D with Transformers
Georgios Pavlakos, Dandan Shan, Ilija Radosavovic, Angjoo Kanazawa, David Fouhey, Jitendra Malik
CVPR 2024
Project Webpage / Paper / Code (HaMeR) / Data (HInt)
Scaling up data and models for hand mesh recovery from images and video.
Towards A Richer 2D Understanding of Hands at Scale
Tianyi Cheng*, Dandan Shan*, Ayda Sultan Hassen, Richard Higgins, David Fouhey
NeurIPS 2023
Project&Dataset Webpage / Code repo / Data repo
New dataset (Hands23), tasks, and model for understanding more complex hand interactions, including bimanual manipulation and tool use (extend hand-object interaction to hand-tool-object interaction).
EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations
Ahmad Darkhalil*, Dandan Shan*, Bin Zhu*, Jian Ma*, Amlan Kar, Richard Higgins, Sanja Fidler, David Fouhey, Dima Damen
NeurIPS 2022 Datasets and Benchmarks
Paper&Review / Project Webpage / Download / Trailer
A new large-scale dataset of segments of people engaged in interaction with objects, including three new challenges and loads of data.
COHESIV: Contrastive Object and Hand Embedding Segmentation In Video
Dandan Shan*, Richard Higgins*, David Fouhey
NeurIPS 2021
Project Webpage / Paper
By applying the Gestalt principle of common fate at scale, we can learn how to segment hand-held objects with fairly minimal supervision.
Understanding Human Hands in Contact at Internet Scale
Dandan Shan, Jiaqi Geng*, Michelle Shu*, David Fouhey
CVPR 2020 (Oral)
Project Webpage (w/ 100DOH Dataset+Code) / Paper / Video
We built a new dataset (100DOH) and model that enables really accurate recognition of basic hand information. Since hands are key to interaction, this basic information unlocks tons of useful new problems.
Work Experience
Nvidia Seattle Robotics Lab
PhD Research Intern, Summer 2024
Mentor: Kaichun Mo, Yuwei-Chao, Wei Yang, Arsalan Mousavian, Dieter Fox
Adobe Research
PhD Research Intern, Summer 2022
Mentor: Jimei Yang, Oliver Wang
Teaching
AI4ALL
Project Instructor, Jul 2020 & Jul 2021
Michigan AI4ALL Director: David Fouhey
website
