Zihang Meng

Facebook AI
Email: zihangm at cs dot wisc dot edu

Biography

I am a research scientist at Facebook AI. Prior to that, I completed my Ph.D. in Computer Sciences Department at University of Wisconsin-Madison, advised by Vikas Singh. Before this, I earned my B.S. degree in electronic information engineering from Zhejiang University in 2017. My current research interests lie in machine learning and its applications in computer vision. I am a recipient of the Best Paper Award in ECCV 2022.

Publications

• On the Versatile Uses of Partial Distance Correlation in Deep Learning [code] [video]
  Xingjian Zhen, Zihang Meng, Rudrasis Chakraborty, Vikas Singh
  European Conference on Computer Vision (ECCV), 2022 (Best Paper Award)


• Object-Centric Unsupervised Image Captioning [code] [video]
  Zihang Meng, David Yang, Xuefei Cao, Ashish Shah, Ser-Nam Lim
  European Conference on Computer Vision (ECCV), 2022


• Differentiable Optimization of Generalized Nondecomposable Functions using Linear Programs [code] [video]
  Zihang Meng, Lopamudra Mukherjee, Vikas Singh, Yichao Wu, Sathya N. Ravi
  Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS), 2021


• An Online Riemannian PCA for Stochastic Canonical Correlation Analysis [code] [video]
  Zihang Meng^*, Rudrasis Chakraborty^*, Vikas Singh
  Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS), 2021


• Neural TMDlayer: Modeling Instantaneous flow of features via SDE Generators [code] [video]
  Zihang Meng, Vikas Singh, Sathya Ravi
  International Conference on Computer Vision (ICCV), 2021 (Oral)


• Connecting What to Say With Where to Look by Modeling Human Attention Traces [code]
  Zihang Meng, Licheng Yu, Ning Zhang, Tamara Berg, Babak Damavandi, Vikas Singh, Amy Bearman
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021


• Physarum Dynamics and Differentiable Linear Program Layers [code]
  Zihang Meng, Sathya Ravi, Vikas Singh
  AAAI Conference on Artificial Intelligence (AAAI), 2021


• Efficient Relative Attribute Learning using Graph Neural Networks [code]
  Zihang Meng, Nagesh Alduru, Hyunwoo J. Kim, Glenn Fung, Vikas Singh
  European Conference on Computer Vision (ECCV), 2018

Teaching

I was a TA for

• CS 354: Machine Organization and Programming (Fall 2017)