Zhenheng Yang (杨振恒)

Welcome to my personal webpage.


I am now working on CV, multi-modality and recommendation at ByteDance (we are hiring!). Between 2019 and 2021, I worked as a research scientist at Facebook AI. I obtained my Ph.D. degree from University of Southern California (USC) under advisement of Prof. Ram Nevatia. My research interests include computer vision and machine learning, specifically weakly supervised learning, 3D perception and activity reasoning. I received B.E. degree from Tsinghua University in 2014.

More about me: Google scholar, Github, Resume (very outdated),

Email: zhenheny at gmail.com

Education

University of Southern California, Los Angeles, CA (Aug. 2014 - Dec. 2018)
  • Doctor of Philosophy (Ph.D)
  • Advisor: Ram Nevatia
Tsinghua University, Beijing, China (Aug. 2010 - Jul. 2014)
  • Bachelor of Engineering (B.E.)

Work Experience

Facebook AI, Menlo Park, CA (Mar. 2019 - Mar. 2021)
  • Position: Research Scientist
  • Work on: object detection / segmentation, person segmentation, foresics detection, content integrity
Facebook AI, Menlo Park, CA (May. 2018 - Aug. 2018)
Baidu Research, Sunnyvale, CA (May. 2017 - Aug. 2017)
University of Southern California, CA (Aug. 2014 - Current)

Publications

Qing Liu, Vignesh Ramanathan, Dhruv Mahajan, Alan Yuille and Zhenheng Yang. “Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistency, CVPR 2021. [paper], [ArXiv], [poster]

Xuefeng Hu, Zhihan Zhang, Zhenye Jiang, Syomantak Chaudhuri, Zhenheng Yang, and Ram Nevatia. “SPAN: Spatial pyramid attention network for image manipulation localization”, ECCV 2020. [paper], [ArXiv], [code]

Chenxu Luo*, Zhenheng Yang*, Peng Wang, Yang Wang, Wei Xu, Ram Nevatia, and Alan Yuille. “Every pixel counts++: Joint learning of geometry and motion with 3d holistic understanding.”, TPAMI 2019. [paper], [ArXiv], [code]

Zhenheng Yang, Vignesh Ramanathan, Deepti Ghadiyaram, Ram Nevatia, Dhruv Mahajan. “Activity Driven Weakly Supervised Object Detection”. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.[paper]

Yang Wang, Peng Wang, Zhenheng Yang, Chenxu Luo, Yi Yang, and Wei Xu. “UnOS: Unified Unsupervised Optical-flow and Stereo-depth Estimation by Watching Videos”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [paper][code]

Zhenheng Yang, Peng Wang, Yang Wang, Wei Xu and Ram Nevatia, “Every Pixel Counts: Unsupervised Geometry Learning with Holistic 3D Motion Understanding”, European Conference on Computer Vision VNAD workshop (ECCVW), 2018. [paper]

Zhenheng Yang, Peng Wang, Yang Wang, Wei Xu and Ram Nevatia, “LEGO: Learning Edge with Geometry all at Once by Watching Videos”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, Spotlight. [paper], [code], [demo], [presentation]

Yang Wang, Yi Yang, Zhenheng Yang, Liang Zhao, Peng Wang and Wei Xu, “Occlusion Aware Unsupervised Learning of Optical Flow”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [paper]

Zhenheng Yang, Peng Wang, Wei Xu, Liang Zhao and Ram Nevatia, “Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistency”, AAAI Conference on Artificial Intelligence (AAAI), 2018, Oral. [paper]

KangGeon Kim*, Zhenheng Yang*, Iacopo Masi, Ram Nevatia and Gerard Medioni, “Face and Body Association for Video-Based Face Recognition”, IEEE Winter Conference on Applications of Computer Vision (WACV), 2018. [paper] [model]

Jiyang Gao*, Zhenheng Yang*, Kan Chen, Chen Sun and Ram Nevatia, “TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals”, in International Conference on Computer Vision (ICCV), 2017. [paper], [code]

Zhenheng Yang, Jiyang Gao and Ram Nevatia, “Spatio-Temporal Action Detection with Cascade Proposal and Location Anticipation”, British Machine Vision Conference (BMVC), 2017 Oral. [paper], [presentation]

Jiyang Gao, Chen Sun, Zhenheng Yang and Ram Nevatia, “TALL: Temporal Activity Localization via Language Query”, in International Conference on Computer Vision (ICCV), 2017, Spotlight. [paper], [code], [presentation]

Jiyang Gao, Zhenheng Yang and Ram Nevatia, “Cascaded Boundary Regression for Temporal Action Detection”, British Machine Vision Conference (BMVC), 2017. [paper], [code], [Results]

Jiyang Gao, Zhenheng Yang and Ram Nevatia, “RED: Reinforced Encoder-Decoder Network for Action Anticipation”, British Machine Vision Conference (BMVC), 2017 Oral. [paper], [presentation]

Zhenheng Yang and Ram Nevatia, “A multi-scale cascade fully convolutional network face detector”, International Conference on Pattern Recognition (ICPR), 2016. [paper], [model]

Academic Services

Organizer: 2nd Extreme Vison workshop (with CVPR 2021) [link]

Senior program committee: IJCAI 2021

Reviewer: WACV 2020, ICCV 2019, CVPR 2019, TVCJ, AAAI 2019, WACV 2019, ECCV workshop 2018, CVPR 2018, AAAI 2018, ACCV 2018, ACM MM 2017, ICCV workshop 2017, IPTA 2017

Program committee member: AAAI 2019, ICCV CHI workshop 2017