Yipin Zhou

Email: yipinzhou"at"fb.com

I'm a Researcher at Facebook AI.

I received PhD from University of North Carolina at Chapel Hill, and my advisor was Prof. Tamara Berg. Before that, I got Sc.M from Brown University, working with Prof. James Hays, and B.Eng. in Software Engineering from Tongji University.

My research interests span Computer Vision, especially video and audio cross-modeling; Machine Learning and Computational Photography from time to time.

Publications


ROICtrl: Boosting Instance Control for Visual Generation
Yuchao Gu, Yipin Zhou, Yunfan Ye, Yixin Nie, Licheng Yu, Pingchuan Ma, Kevin Qinghong Lin and Mike Zheng Shou
IEEE Conference on Computer Vision and Pattern Recognition (CVPR2025)

VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondence
Yuchao Gu, Yipin Zhou, Bichen Wu, Licheng Yu, Jia-Wei Liu, Rui Zhao, Jay Zhangjie Wu, David Junhao Zhang, Mike Zheng Shou, Kevin Tang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR2024)

Universal Pyramid Adversarial Training for Improved ViT Performance
Ping-yeh Chiang, Yipin Zhou, Omid Poursaeed, Satya Narayan Shukla, Tom Goldstein, Ser-Nam Lim
Arxiv, 2023

VoxelFormer: Bird's-Eye-View Feature Generation based on Dual-view Attention for Multi-view 3D Object Detection
Zhuoling Li, Chuanrui Zhang, Wei-Chiu Ma, Yipin Zhou, Linyan Huang, Haoqian Wang, SerNam Lim, Hengshuang Zhao
Arxiv, 2023

Unifying Tracking and Image-Video Object Detection
Peirong Liu, Rui Wang, Pengchuan Zhang, Omid Poursaeed, Yipin Zhou, Xuefei Cao, Sreya Dutta Roy, Ashish Shah, Ser-Nam Lim
Arxiv, 2023

Few-Shot Fast-Adaptive Anomaly Detection
Ze Wang, Yipin Zhou, Rui Wang, Tsung-Yu Lin, Ashish Shah, Ser-Nam Lim
Conference on Neural Information Processing Systems (NeurIPS 2022)

Self-appearance-aided Differential Evolution for Motion Transfer
Peirong Liu, Rui Wang, Xuefei Cao, Yipin Zhou, Ashish Shah, Maxime Oquab, Camille Couprie, Ser-Nam Lim
Arxiv, 2022

Joint Audio-Visual Deepfake Detection
Yipin Zhou and Ser-Nam Lim
Proceedings of IEEE International Conference on Computer Vision (ICCV2021)

Dance Dance Generation: Motion Transfer for Internet Videos
Yipin Zhou, Zhaowen Wang, Chen Fang, Trung Bui and Tamara L. Berg
ICCV Human Behaviour Understanding Workshop (ICCVW2019, Oral)

Visual to Sound: Generating Natural Sound for Videos in the Wild
Yipin Zhou, Zhaowen Wang, Chen Fang, Trung Bui and Tamara L. Berg
IEEE Conference on Computer Vision and Pattern Recognition (CVPR2018)
The shorten version will appear in the Sight and Sound Workshop (CVPRW2018, Oral)
 

Image2GIF: Generating Cinemagraphs using Recurrent Deep Q-Networks
Yipin Zhou, Yale Song and Tamara L. Berg
IEEE Winter Conf. on Applications of Computer Vision (WACV2018)

Learning Temporal Transformations From Time-Lapse Videos
Yipin Zhou and Tamara L. Berg
Proceedings of the 14th European Conference on Computer Vision (ECCV2016)

Temporal Perception and Prediction in Ego-Centric Video
Yipin Zhou and Tamara L. Berg
Proceedings of 15th IEEE International Conference on Computer Vision (ICCV2015)

A MAP-estimation Framework for Blind Deblurring Using High-level Edge Priors
Yipin Zhou and Nikos Komodakis
Proceedings of the 13th European Conference on Computer Vision (ECCV2014)

Thesis


Learning Beyond-pixel Mappings from Internet Videos
Yipin Zhou
Doctoral Dissertation, UNC-Chapel Hill, 2019