Zhen ZUO

BIOGRAPHY

Zhen Zuo is currently an Applied Scientist at Amazon, Seattle, WA. Before joining Amazon, she was a senior computer vision research scientist at DeepGlint Tech. Ltd. She obtained her Ph.D. degree from Nanyang Technological University (NTU), Singapore in 2015, advised by Prof. Gang Wang. She received her B.S. degree from Huazhong University of Science and Technology (HUST), Wuhan, China, in 2011. Her research interests include Computer Vision, Machine Learning and Recommandation System.

Projects

• Convolutional Hierarchical Recurrent Neural Networks [Project] is a new type of deep neural networks for large scale image classification task. It significantly increases the representation power of the popular Convolutional Neural Networks by introducing Recurrent Neural Network to encode spatial and scale context information.
• Deep Discriminative and Shareable Feature Learning [Project] is a deep feature learning framework for image classification. It aims to encode class-level discriminative and shareable information in multiple visual level image representation. By combining with Convolutional Neural Network, this work updated the state-of-the-art on MIT indoor and achieved 76.23% in accuracy.

Dataset

• NTU-Tree 51 [Description] is a fine-grained image classification dataset. It contains 51 common tree species in Singapore. All the images were taken at a distance with large intra class variance.

CONFERENCES

• Zhen Zuo, Lixi Wang, Michinari Momma, Wenbo Wang, Yikai Ni, Jianfeng Lin, and Yi Sun. “A Flexible Large-Scale Similar Product Identification System in E-commerce.” Knowledge Discovery and Data Mining (KDD) IRS Workshop, ACM, 2020. [PDF]
• Bing Shuai^*, Zhen Zuo^*, Gang Wang, and Bing Wang. “DAG-Recurrent Neural Networks For Scene Labeling.” In Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2016. (*Equal contribution) [PDF]
• Bing Wang, Li Wang, Bing Shuai, Zhen Zuo, Ting Liu, Kap Luk Chan, and Gang Wang. “Joint Learning of Convolutional Neural Networks and Temporally Constrained Metrics for Tracklet Association.” In Proceedings of the Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE, 2016. [PDF]
• Zhen Zuo, Bing Shuai, Gang Wang, Xiao Liu, Xingxing Wang, Bing Wang, and Yushi Chen. “Convolutional Recurrent Neural Networks: Learning Spatial Dependencies for Image Representation.” In Proceedings of the Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE, 2015. [PDF]
• Bing Shuai, Zhen Zuo, Gang Wang. “Learning semantic visual dictionaries: A new method for local feature encoding.” In Proceedings of the Conference on Digital Signal Processing (DSP), pp. 901-905. IEEE, 2015. [PDF]
• Bing Shuai, Gang Wang, Zhen Zuo, Bing Wang, and Lifan Zhao. “Integrating Parametric and Non-Parametric Models For Scene Labeling.” In Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4249-4258. IEEE, 2015. [PDF]
• Zhen Zuo, Gang Wang, Bing Shuai, Lifan Zhao, Qingxiong Yang, and Xudong Jiang. “Learning Discriminative and Shareable Features for Scene Classification.” In Proceedings of the European Conference on Computer Vision (ECCV), pp. 552-568. Springer, 2014. [PDF]
• Zhen Zuo and Gang Wang. “Recognizing trees at a distance with discriminative deep feature learning.” In Proceedings of the Information, Communications and Signal Processing (ICICS), IEEE, 2013. [Link][Dataset]
• Zhongyuan Lai, Zhen Zuo, Zhe Wang, Zhijun Yao, and Wenyu Liu. “Accurate distortion measurement for B-spline-based shape coding.” In Proceedings of the International Conference on Image Processing (ICIP), IEEE, 2011. [Link]
• Zhongyuan Lai, Zhen Zuo, Zhe Wang, and Wenyu Liu. “Accurate distortion measurement using analytical model for the B-spline-based shape coding.” In Proceedings of the Data Compression Conference (DCC), IEEE, 2011. [Link]
• Zhongyuan Lai, Zhen Zuo, Zhe Wang, and Wenyu Liu. “A hybrid admissible distortion checking algorithm for the B-spline-based operational rate-distortion optimal shape coding.” In Proceedings of the Data Compression Conference (DCC), IEEE, 2011. [Link]

JOURNALS

• Abara H. Abdulnabi, Bing Shuai, Zhen Zuo, Lap-Pui Chau, Gang Wang. “Multimodal Recurrent Neural Networks with Information Transfer Layers for Indoor Scene Labeling." In IEEE Transactions on Multimedia, 2017. [PDF]
• Bing Shuai, Zhen Zuo, Bing Wang, Gang Wang. “Scene Segmentation with DAG-Recurrent Neural Networks." In IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017. [PDF]
• Zhen Zuo, Bing Shuai, Gang Wang, Xiao Liu, Xingxing Wang, and Bing Wang. “Learning Contextual Dependencies with Convolutional Hierarchical Recurrent Neural Networks.” IEEE Transactions on Image Processing, 2016. [PDF]
• Bing Shuai, Zhen Zuo, Gang Wang, and Bing Wang. “Scene Parsing with Integration of Parametric and Non-parametric Models.” IEEE Transactions on Image Processing, 2016. [PDF]
• Zhen Zuo, Gang Wang, Bing Shuai, Lifan Zhao, and Qingxiong Yang. “Exemplar based Deep Discriminative and Shareable Feature Learning for scene image classification.” Pattern Recognition (PR), Elsevier, 2015. [PDF]
• Bing Shuai, Zhen Zuo, and Gang Wang. “Quaddirectional 2D-Recurrent Neural Networks For Image Labeling.” Signal Processing Letters (SPL), IEEE, 2015. [Link]
• Zhen Zuo and Gang Wang. “Learning Discriminative Hierarchical Features for Object Recognition.” Signal Processing Letters (SPL), IEEE, 2014. [Link]
• Zhongyuan Lai, Zhe Wang, Zhen Zuo, Zhijun Yao, and Wenyu Liu. “B-spline-based shape coding with accurate distortion measurement using analytical model.” Neurocomputing, Elsevier, 2015. [Link]