Cheng Zhang ·

Cheng Zhang

chengzh3 at andrew.cmu.edu or czhang0528 at gmail.com

Google Scholar | Github | LinkedIn

About Me

Welcome to my homepage! I am a Postdoctoral Fellow in the Robotics Institute at Carnegie Mellon University, working with Fernando De la Torre. I did my Ph.D. in the Department of Computer Science and Engineering at The Ohio State University with Harry Chao and Dong Xuan. Prior to that, I received my M.S. and B.Eng. degrees from BUPT and Tianjin University, respectively. I have spent time interning at NVIDIA AV, Volvo Cars, FXPAL, and Alibaba. For more information, please see a copy of my CV (Last update: 10/2023).

My research areas are machine learning and its applications to computer vision, multimodal understanding, human modeling for extended reality, and cyber-physical systems. I am particularly interested in developing capable, reliable, and fair intelligent systems, with an emphasis on using data-focused methodologies. My recent work focuses on the following directions: 2D/3D generative modeling, responsible AI, and large-scale perception across imperfect observations, such as limited, biased, and long-tailed data.

News

02/2024 One paper accepted to CVPR 2024 on reliable human image generation

10/2023 ITI-GEN was on the Best Paper Finalist at ICCV 2023 (one of 17 papers out of 8260 submissions)

08/2023 ITI-GEN on Inclusive Text-to-Image Generation accepted to ICCV 2023 as Oral Presentation

07/2022 Defended my PhD dissertation on "Learning with Imperfect Data and Supervision for Visual Perception and Understanding"

07/2022 Check out what our Buckeye AutoDrive Team has done in the Year 1 AutoDrive Challenge II

07/2022 Recognized as an outstanding reviewer (Top 10%) from ICML 2022

07/2022 One paper accepted to ECCV 2022

03/2022 One paper accepted to CVPR 2022 as oral presentation

03/2022 Honored to receive Graduate Research Award (Mike Liu Scholarship) from our CSE department

11/2021 Recognized as an outstanding reviewer from BMVC 2021

10/2021 Invited research talk at LVIS challenge workshop

10/2021 Selected to participate the Doctoral Consortium in ICCV 2021

10/2021 Excited to be part of Buckeye AutoDrive to compete in SAE AutoDrive Challenge II

09/2021 NorCal on model calibration for long-tailed object detection accepted to NeurIPS 2021

09/2021 SimpleAug on visual question answering accepted to EMNLP 2021

07/2021 MosaicOS on long-tailed object detection accepted to ICCV 2021

05/2021 Joined NVIDIA autonomous vehicle team as a perception intern

02/2021 Check out our efforts on ultrasonic-based contact tracing (OSU News, project) and WLAN-log-based superspreader detection

07/2020 One paper accepted by BMVC 2020 on disease localization

06/2020 Started my internship at Volvo Cars AI Research, working on 3D object detection for autonomous driving

03/2020 CSE annual research poster exhibition award (1st place)

07/2019 One paper accepted as oral presentation to BMVC 2019

05/2019 Summer internship at FX Palo Alto Laboratory (FXPAL), working on AI in medicine & imaging

Papers

	Towards Effective Usage of Human-Centric Priors in Diffusion Models for Text-based Human Image Generation Junyan Wang, Zhenhong Sun, Zhiyu Tan, Xuanbai Chen, Weihua Chen, Hao Li, Cheng Zhang, Yang Song Conference on Computer Vision and Pattern Recognition (CVPR), 2024 Paper arXiv Project Code
	ITI-GEN: Inclusive Text-to-Image Generation Cheng Zhang, Xuanbai Chen, Siqi Chai, Chen Henry Wu, Dmitry Lagun, Thabo Beeler, Fernando De la Torre International Conference on Computer Vision (ICCV), 2023 (Oral Presentation, Best Paper Finalist) Paper arXiv Project Code
	OVO: Open-Vocabulary Occupancy Zhiyu Tan, Zichao Dong, Cheng Zhang, Weikun Zhang, Hang Ji, Hao Li Technical Report, 2023 Paper arXiv Code
	Learning with Free Object Segments for Long-Tailed Instance Segmentation Cheng Zhang, Tai-Yu Pan, Tianle Chen, Jike Zhong, Wenjin Fu, Wei-Lun Chao European Conference on Computer Vision (ECCV), 2022 Paper arXiv
	Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations Zirui Peng, Shaofeng Li, Guoxing Chen, Cheng Zhang, Haojin Zhu, Minhui Xue Conference on Computer Vision and Pattern Recognition (CVPR), 2022 (Oral Presentation) Paper arXiv

	On Model Calibration for Long-Tailed Object Detection and Instance Segmentation Tai-Yu Pan, Cheng Zhang, Yandong Li, Hexiang Hu, Dong Xuan, Soravit Changpinyo, Boqing Gong, Wei-Lun Chao Conference on Neural Information Processing Systems (NeurIPS), 2021 Paper arXiv Code
	Discovering the Unknown Knowns: Turning Implicit Knowledge in the Dataset into Explicit Training Examples for Visual Question Answering Jihyung Kil, Cheng Zhang, Dong Xuan, Wei-Lun Chao Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021 Paper arXiv Code
	MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection Cheng Zhang, Tai-Yu Pan, Yandong Li, Hexiang Hu, Dong Xuan, Soravit Changpinyo, Boqing Gong, Wei-Lun Chao International Conference on Computer Vision (ICCV), 2021 Paper arXiv Code Poster
	WLAN-Log-Based Superspreader Detection in the COVID-19 Pandemic Cheng Zhang, Yunze Pan, Yunqi Zhang, Adam C Champion, Zhaohui Shen, Dong Xuan, Zhiqiang Lin, Ness Shroff Elsevier High-Confidence Computing Journal (HCC), 2021 Paper arXiv
	Thoracic Disease Identification and Localization using Distance Learning and Region Verification Cheng Zhang, Francine Chen, Yan-Ying Chen British Machine Vision Conference (BMVC), 2020 Paper arXiv Talk Patent (Filed by Fujifilm in US, JP, and CN)
	An Empirical Study on Leveraging Scene Graphs for Visual Question Answering Cheng Zhang, Wei-Lun Chao, Dong Xuan British Machine Vision Conference (BMVC), 2019 (Oral Presentation) Paper arXiv Poster Talk
	MV-Sports: A Motion and Vision Sensor Integration-Based Sports Analysis System Cheng Zhang, Fan Yang, Gang Li, Qiang Zhai, Yi Jiang, Dong Xuan International Conference on Computer Communications (INFOCOM), 2018 Paper Demo
	Third-Eye: A Mobilephone-Enabled Crowdsensing System for Air Quality Monitoring Liang Liu, Wu Liu, Yu Zheng, Huadong Ma, Cheng Zhang ACM International Joint Conference on Pervasive and Ubiquitous Computing (IMWUT/UbiComp), 2018 Paper iOS APP Android APP
	Siamese Neural Network based Gait Recognition for Human Identification Cheng Zhang, Wu Liu, Huadong Ma, Huiyuan Fu International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016 (Oral Presentation) Paper Code Poster

Miscellaneous

Upcoming conferences: AI and mobile.

I play the guitar, check my melodies: 500 miles, night, dreams link, and sweet home. My favorite song is wonderful tonight by Eric Clapton.

I am a passionate soccer fan and my favorite club is AC Milan.