About Dandan Shan (单丹丹)

I am a Ph.D. candidate (4th-year) 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.

Email: dandans AT umich.edu      Google Scholor / CV / Github / Twitter

News

[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 with Jimei Yang this summer!
[2021/12] I received the Rackham International Student Fellowship.
[2021/09] I passed Prelim.
[2021/09] COHESIV is accepted at NeurIPS2021.
[2020.04] I will join UMich CS as a PhD student in Fall 2020.
[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) from 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 (upcoming). I am broadly interested in research on video, 3D, summarization and generating creative content.

Publications


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)

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
We explore hand-tool-object interactions, hand grasps and different bimanual hand manipulation configurations!

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

COHESIV: Contrastive Object and Hand Embedding Segmentation In Video
Dandan Shan*, Richard Higgins*, David Fouhey
NeurIPS 2021
Project Webpage / Paper

Understanding Human Hands in Contact at Internet Scale
Dandan Shan, Jiaqi Geng*, Michelle Shu*, David Fouhey
CVPR 2020 (Oral)
Project&Dataset Webpage / Paper / Video

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

Polaroids



Charcoal Drawings



Portfolio: Studio 2D


Hi/你好/Namaste/Hola/Bonjour...
So glad you come to this secret land.
I like drawing, taking photos and design.
I always want to find a way to better memorize days.
I enjoy biking🚴‍♀️ to office while listening to audio books.
I like playing ball games🏸🎾🏓 with friends.
I like 🐶🐱🦜.



(Life-size self-portrait, Dec 2021)