I'm a Ph.D. candidate in Computer Science and Engineering at the University of Minnesota, Twin Cities, advised by Prof. Hyun Soo Park.

Currently, I'm working on single view human 3D reconstruction with a focus on predicting the high fidelity depth and surface normal from social media videos in a self-supervised framework.

My previous research area were keypoint tracking and detection of nonhuman beings such as monkeys and dogs and measuring the behaviors of them in three-dimensional space (3D) using multi-view cameras.

I have received the Best Paper Honorable Mention Award at CVPR 2021 for "Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos"


[Email | Google Scholar | LinkedIn | GitHub | CV]

Publications

Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos

Yasamin Jafarian, Hyun Soo Park

IEEE Computer Vision and Pattern Recognition (CVPR 2021),

[Oral presentation] [Best Paper Honorable Mention Award]

[Pdf | Video | Code | Dataset | Project Website | BibTeX]

MONET: Multiview Semi-supervised Keypoint via Epipolar Divergence

Yuan Yao, Yasamin Jafarian, Hyun Soo Park

International Conference on Computer Vision (ICCV 2019)

[Pdf | Video | Code | BibTex]

News

June 2021: The paper "Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos" won the Best Paper Honorable Mention.

June 2021: The TikTok dataset is published in the Kaggle.

June 2021: The paper "Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos" is chosen as a CVPR best paper candidate.

Mar 2021: The paper "Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos" is accepted for oral presentation in CVPR 2021.

Jul 2019: The paper "MONET: Multiview Semi-supervised Keypoint via Epipolar Divergence" Is accepted to ICCV 2019.