Yuan-Ting Hu

I am a research scientist at FAIR, Meta AI since 2022. I completed my Ph.D. in Electrical and Computer Engineering at the Univeristy of Illinois Urbana Champaign, advised by Alex Schwing.

I am interested in computer vision and machine learning, with a focus on videos.

[Google Scholar] [email]

Selected Publications

Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles

Chaitanya Ryali, Yuan-Ting Hu, Daniel Bolya, Chen Wei, Haoqi Fan, Po-Yao Huang, Vaibhav Aggarwal, Arkabandhu Chowdhury, Omid Poursaeed, Judy Hoffman, Jitendra Malik, Yanghao Li, Christoph Feichtenhofer

International Conference on Machine Learning (ICML) 2023

paper project page 

Surface Snapping Optimization Layer for Single Image Object Shape Reconstruction

Yuan-Ting Hu, Alexander G. Schwing and Raymond A. Yeh 

International Conference on Machine Learning (ICML) 2023

paper github 

Occupancy Planes for Single-View RGB-D Human Reconstruction

Xiaoming Zhao, Yuan-Ting Hu, Zongzheng Ren, and Alexander G. Schwing  

AAAI Conference on Artificial Intelligence (AAAI) 2023

paper github 

Equivariance Discovery by Learned Parameter-Sharing 

Raymond A. Yeh, Yuan-Ting Hu, Mark Hasegawa-Johnson and Alexander G. Schwing


International Conference on Artificial Intelligence and Statistics (AISTATS) 2022

paper project page 

Total Variation Optimization Layers for Computer Vision

Raymond A. Yeh, Yuan-Ting Hu and Alexander G. Schwing

International Conference on Computer Vision and Pattern Recognition (CVPR) 2022

paper project page 

SAIL-VOS 3D: A Synthetic Dataset and Baseline for Object Detection and 3D Mesh Reconstruction from Video Data

Yuan-Ting Hu, Jiahong Wang, Raymond A. Yeh and Alexander G. Schwing

International Conference on Computer Vision and Pattern Recognition (CVPR) 2021

paper project page download dataset

Proposal-based Video Completion

Yuan-Ting Hu, Heng Wang, Nicolas Ballas, Kristen Grauman and Alexander G. Schwing

European Conference on Computer Vision (ECCV) 2020

paper

Chirality Nets for Human Pose Regression

Raymond A. Yeh*, Yuan-Ting Hu*, and Alexander G. Schwing

(Equal contribution)

Neural Information Processing Systems (NeurIPS) 2019

paper project website code

SAIL-VOS: Semantic Amodal Instance Level Video Object Segmentation -- A Synthetic Dataset and Baselines

Yuan-Ting Hu, Hong-Shuo Chen, Kexin Hui, Jia-Bin Huang and Alexander G. Schwing

International Conference on Computer Vision and Pattern Recognition (CVPR) 2019

paper project website download dataset

Max-Sliced Wasserstein Distance and its use for GANs

Ishan Deshpande, Yuan-Ting Hu, Ruoyu Sun, Ruoyu Sun, Ayis Pyrros, Nasir Siddiqui, Sanmi Koyejo, Zhizhen Zhao, David Forsyth and Alexander G. Schwing

International Conference on Computer Vision and Pattern Recognition (CVPR) 2019

paper

VideoMatch: Matching based Video Object Segmentation 

Yuan-Ting Hu, Jia-Bin Huang and Alexander G. Schwing

European Conference on Computer Vision (ECCV) 2018

paper   project website  poster

Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation 

Yuan-Ting Hu, Jia-Bin Huang and Alexander G. Schwing

European Conference on Computer Vision (ECCV) 2018

paper   project website  poster

Mask-RNN: Instance Level Video Object Segmentation 

Yuan-Ting Hu, Jia-Bin Huang and Alexander G. Schwing

Neural Information Processing Systems (NeurIPS) 2017

paper  poster bibtex