Ph.D. student in Carnegie Mellon University
My main research area is Computer Vision. Topics include 3D Generative Adversarial Nets (GANs), Face Manipulation and Recognition.
LinkedIn Profile
Google Scholar Profile
“Before we judge, seek to understand.”
I’m a senior Ph.D. student from the ECE department at Carnegie Mellon University (check out my Resume). My current interests lie broadly in the intersection of generative model, computer vision and disentangled representation learning. I worked with Prof. Marios Savvides at the CyLab Biometrics Center. I also work closely with Oosto (formerly AnyVision), a visual AI company, taking charge of cooperative tasks under Dr. Guosheng Hu. Some of my previous works were put into application in Bossa Nova Robotics, Walmart and the government issued projects for criminal investigation.
Much of my work is centered around the problem of semantic disentanglement and representation learning. Building semantically interpretable representations of data are of paramount importance. Ideally, a single good representation would be interpretable for a human that requires minimal supervision to obtain. Towards this goal, representations learned by modeling the natural processes are presumably more treasured. Some of my work has explored learning such representations by 1) loss function that normalizes the energy of neuron clusters, 2) a sparse constraint that captures local facial perturbations to mimic muscle distribution, and finally 3) inductive biases in generator architectures that explicitly promote pose variation and symmetry. Video and/or binocular dataset has also emerged as a promising direction that promotes rich representation learning through stereopsis while requiring minimum supervision. Some of my ongoing work aims to provide a better understanding of the phenomenon of stereopsis, paving the way for the development of more effective techniques.
Regularly serve as a reviewer for CVPR, ICCV, ECCV, WACV, AAAI.
Yutong Zheng, Yu-Kai Huang, Ran Tao, Zhiqiang Shen, and Marios Savvides. Unsupervised Disentanglement of Linear-Encoded Facial Semantics., CVPR 2021, poster
Yutong Zheng, Dipan K. Pal and Marios Savvides, Ring loss: Convex Feature Normalization for Face Recognition., CVPR 2018, poster
Chenchen Zhu, Yutong Zheng, Khoa Luu, and Marios Savvides. Cms-rcnn: contextual multi-scale region-based cnn for unconstrained face detection. In Deep learning for biometrics, pp. 57-79. Springer, Cham, 2017.
Yutong Zheng, Chenchen Zhu, Khoa Luu, Chandrasekhar Bhagavatula, T. Hoang Ngan Le, and Marios Savvides. Towards a deep learning framework for unconstrained face detection. BTAS 2016.
Zhiqiang Shen, Mingyang Huang, Jianping Shi, Zechun Liu, Harsh Maheshwari, Yutong Zheng, Xiangyang Xue, Marios Savvides, and Thomas S. Huang. CDTD: A Large-Scale Cross-Domain Benchmark for Instance-Level Image-to-Image Translation and Domain Adaptive Object Detection. IJCV 2021.
Zhiqiang Shen, Zhankui He, Wanyun Cui, Jiahui Yu, Yutong Zheng, Chenchen Zhu, and Marios Savvides. Adversarial-based knowledge distillation for multi-model ensemble and noisy data refinement. arXiv preprint arXiv:1908.08520 (2019).
Dipan Pal, Chandrasekhar Bhagavatula, Yutong Zheng, Ran Tao, and Marios Savvides. Is pose really solved? a frontalization study on off-angle face matching. WACV 2019.
Chenchen Zhu, Yutong Zheng, Khoa Luu, and Marios Savvides. Enhancing interior and exterior deep facial features for face detection in the wild. FG 2018.
T. Hoang Ngan Le, ChenChen Zhu, Yutong Zheng, Khoa Luu, and Marios Savvides. DeepSafeDrive: A grammar-aware driver parsing approach to Driver Behavioral Situational Awareness (DB-SAW). Pattern Recognition 66 (2017): 229-238.
T. Hoang Ngan Le, Chenchen Zhu, Yutong Zheng, Khoa Luu, and Marios Savvides. Robust hand detection in vehicles. ICPR 2016.
Chenchen Zhu, Yutong Zheng, Khoa Luu, T. Hoang Ngan Le, Chandrasekhar Bhagavatula, and Marios Savvides. Weakly supervised facial analysis with dense hyper-column features. CVPRW 2016.
T. Hoang Ngan Le, Yutong Zheng, Chenchen Zhu, Khoa Luu, and Marios Savvides. Multiple scale faster-rcnn approach to driver’s cell-phone usage and hands on steering wheel detection. CVPRW 2016.
Yutong Zheng, Ruonan Jia, Yiqing Qian, Yang Ye, and Changhong Liu. Correlation between electric potential and peristaltic behavior in Physarum polycephalum. BioSystems 132 (2015): 13-19.
Marios Savvides, Khoa Luu, Yutong Zheng, and Chenchen Zhu. Methods and software for detecting objects in images using a multiscale fast region-based convolutional neural network. U.S. Patent 10354362, Published 2019-07-16.
Marios Savvides, Dipan Kumar Pal, Yutong Zheng. Convex Feature Normalization for Face Recognition. U.S. Patent 2021034984, Published 2021-11-17.
Marios Savvides, Sreena Nallamothu, Magesh Kannan, Uzair Ahmed, Ran Tao, Yutong Zheng. System and method for identifying misplaced products in a shelf management system. U.S. Patent 20220051177, published 2022-02-17.
Marios Savvides, Yutong Zheng, Yu Kai Huang. System and method for class-identity-preserving data augmentation. Publication of WO2022173820A2, published 2022-08-18.
Marios Savvides, Yutong Zheng, Yu Kai Huang. System and method for photorealistic image synthesis using unsupervised semantic feature disentanglement. Publication of WO2022173814A1, published 2022-08-18.