Yi Fang, Ph.D.

Yi Fang, Ph.D.

Research Assistant Professor

Electrical and Computer Engineering

Biography

Prof. Yi Fang directs the NYU Multimedia and Visual Computing Lab. He received his PhD from Purdue University with research focus on 3D computer vision. Upon one year industry experience as a research intern in Siemens in Princeton, New Jersey and a senior research scientist in Riverain Technologies in Dayton, Ohio, and a half-year academic experience as a senior staff scientist at Department of Electrical Engineering and Computer science, Vanderbilt University, Nashville, he has built well-round skill set and expertise in multimedia and visual computing and the applied fields in medicine and biology. He has developed a comprehensive and diverse research fields in large-scale 3D visual data processing. He is currently working on the development of state-of-the-art techniques in large-scale visual computing that consists of 3D scene understanding, data-driven 3D visual data processing, and deep cross-domain and cross-modality visual multimedia processing. The development in 3D scene understanding research enables a robust 3D dynamic scene reconstruction as well as explores the relations between visual/geometric features and semantic context information, the development in data-driven 3D visual data processing includes the techniques for 3D object registration, retrieval and segmentation that aim to discover geometric, structural, and semantic relationships between 3D objects in a large-scale collection, resulting in intelligent modeling, editing, and visualization of geometric data, and the development in cross-domain and cross-modality aims to robustly exploit the cross-representation for cross-domain and cross-modality objects retrieval as well as multi-view feature integration and fusion for the generation of decision level feature. 

Journal Articles

Fan Zhu and Yi Fang*, “Heat Diffusion Long-Short Term Memory Learning for 3D Shape Analysis”, 14th European Conference on Computer Vision (ECCV), 2016

Meng Wang and Yi Fang*, “Global Consistent Shape Correpondence for Efficient and Effective Active Shape Models”, ACM Multimedia 2016 (ACMMM), 2016

Meng Wang and Yi Fang*, “Local diffusion map signature for symmetry-aware non-rigid shape correspondence”, ACM Multimedia 2016 (ACMMM), 2016

Jin Xie, Guoxian Dai, Fan Zhu, Edward Wong and Yi Fang*, “DeepShape: Deep-Learned Shape Descriptor for 3D Shape Retrieval”, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016

Fan Zhu, Ling Shao and Yi Fang*, “From Handcrafted to Learned-Based Representations for Human Action: A Survey”, Image and Vision Computing (IMAVIS), 2016

Meng Wang, Jin Xie, Fan Zhu and Yi Fang*, “Linear Discrimination Dictionary Learning for Shape Descriptors”, Pattern Recognition Letters (PRL), 2016 

Guoxian Dai, Jin Xie, Fan Zhu and Yi Fang*, “Learning a discriminative deformation-invariant 3D shape descriptor via many-to-one encoder”, Pattern Recognition Letters (PRL), 2016 

Jin Xie and Yi Fang*, “Dynamic Texture Recognition With Video Set Based Collaborative Representation”, Image and Vision Computing (IMAVIS), 2016 

Jin Xie and Yi Fang*, “Learned Binary Spectral Shape Descriptor for 3D Shape Correspondence “, IEEE Computer Vision and Pattern Recognition (CVPR), 2016 

Fan Zhu, Ling Shao and Yi Fang*, “Boosted Cross-Domain Dictionary Learning for Visual Categorization”, IEEE Intelligent Systems, 2016

Tiantian Xu, Fan Zhu, Edward Wong and Yi Fang*, “Dual Many-to-One-Encoder-Based Transfer Learning for Cross-Dataset Human Action Recognition”,Image and Vision Computing (IMAVIS), 2016 

Fan Zhu, Jin Xie and Yi Fang*, “Pyramid Cross-Domain Neural Networks for Sketch-Based 3D Shape Retrieval”,The Thirtieth AAAI Conference on Artificial Intelligence (oral), AAAI 2016 

Yi Fang*, Jin Xie, Guoxian Dai, Meng Wang, Fan Zhu, Tiantian Xu and Edward Wong, “3D Deep Shape Descriptor”, IEEE Computer Vision and Pattern Recognition (CVPR), 2015 

Jin Xie, Yi Fang*, Fan Zhu and Edward Wong, “DeepShape: Deep Learned Shape Descriptor for 3D Shape Matching and Retrieval”, IEEE Computer Vision and Pattern Recognition (CVPR), 2015 

Jin Xie, L. Zhang, J. You and S. Shiu, “Effective Texture Classification by Texton Encoding Induced Statistical Features,” Pattern Recognition (PR), vol. 48, issue 2, pp. 447-457, February 2015 

Zhengjian Kang, Edward K. Wong, “Parts-based Multi-task Learning for Visual Tracking,” IEEE International Conference on Image Processing (ICIP), 2015. 

Yi Fang*, Mengtian Sun, Guoxian Dai, and Karthik Ramani, “The intrinsic geometric structure of protein-protein interaction networks for protein interaction prediction”, IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2015 

Jin Xie, Fan Zhu, Guoxian Dai, Yi Fang*, Deep Progressive Shape-Distribution-Encoder for 3D Shape Retrieval, ACM Multimedia 2015 (ACMMM), 2015 

Jing Zhu, Fan Zhu, Edward Wong, Yi Fang*, Learning Pairwise Neural Network Encoder for Depth Image-based 3D Model Retrieval, ACM Multimedia 2015 (ACMMM) , 2015 

Other Publications

Kaimo Hu and Yi Fang*, 3D Laplacian pyramid signature, Lecture Notes in Computer Science, Volume 9010, Part III, 2014 

Yi Fang*, Biharmonic Shape Signature for Robust Partial Shape Matching, PlosOne (Major Revision), 2014 

Yi Fang*, Karthik Ramani, Heat-passing framework for robust interpretation of data in networks, PlosOne, 2014 

Yi Fang*, Mengtian Sun, Guoxian Dai, and Karthik Ramani, The intrinsic geometric structure of protein-protein interaction networks for protein interaction prediction, Lecture Notes in Computer Science, Volume 8590, pp 487-493, 2014 

Yi Fang*, Mengtian Sun, Guoxian Dai and Karthik Ramani, Global voting model for protein function prediction from protein-protein interaction networks, Lecture Notes in Computer Science, Volume 8590, pp 466-477, 2014 

Zhengjian Kang, Edward K. Wong, “Learning Multi-Scale Sparse Representation for Robust Visual Tracking,” (oral), IEEE International Conference on Image Processing (ICIP), pp. 4897-4901, 2014. 

Education

Purdue University, 2011

Ph.D.,

Research Interests

  • 3D computer vision and pattern recongition 
  • Large-scale visual computing
  • Deep visual computing
  • Deep cross-domain and cross-modality multimedia analysis
  • Computational Structural Biology