About me

Hi there 👋 My name is Wanrong (Zoey) Zheng [CV].

I am a first-year Ph.D. student in Computer Science at the University of Southern Califonia, advised by Prof. Laurent Itti. I received a M.S. degree in Computer Science from USC, advised by Prof. Ram Nevatia and Prof. Laurent Itti. Before USC, I was working in SenseTime as fulltime research engineer (2019-2021), advised by Dr. Xiaoke Jiang and Dr. Yichao Wu.

My research interests lie in computer vision and deep learning, especially include Data-centric and Human-centric AI. My long-term research goal is to build a data-driven AI system that: (1) recognizes and represents scenes effectively, (2) is adaptive to multi-modalities (vision, language, spatial information, etc.), (3) can be reconstructed, understood, and corrected by humans.

Specifically, my current research focuses include:

• Multi-modal Perception: Exploring the synergistic effects of diverse data for enhanced machine understanding, such as applications in Large Multimodal Models (LMMs) and Large Language Models (LLMs);
• Explainable Artificial Intelligence: Transparent and effective human-in-the-loop learning.

Publications

• GaitSTR: Gait Recognition with Sequential Two-stream Refinement
  Wanrong Zheng*, Haidong Zhu*, Zhaoheng Zheng, and Ram Nevatia
  IEEE Transactions on Biometrics, Behavior, and Identity Science (TBIOM), 2024 [Paper]

• ShARc: Shape and Appearance Recognition for Person Identification In-the-wild
  Haidong Zhu, Wanrong Zheng, Zhaoheng Zheng, and Ram Nevatia
  IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024 [Paper] [Poster] [Slides]

• GaitRef: Gait Recognition with Refined Sequential Skeletons
  Haidong Zhu*, Wanrong Zheng*, Zhaoheng Zheng, and Ram Nevatia
  IEEE International Joint Conference on Biometrics (IJCB), 2023 Oral [Paper] [Code] [Project] [Poster] [Slides]

• CAT-NeRF: Constancy-Aware Tx2Former for Dynamic Body Modeling
  Haidong Zhu, Zhaoheng Zheng, Wanrong Zheng, and Ram Nevatia
  IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023 [Paper] [Code] [Supp]

• SSN3D: Self-Separated Network to Align Parts for 3D Convolution in Video Person Re-Identification
  Xiaoke Jiang, Yu Qiao, Junjie Yan, Qichen Li, Wanrong Zheng, and Dapeng Chen
  Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2021 [Paper] [Supp] [Poster] [Slides]

Research Experience

iLab, USC, Los Angeles, CA
Research Assistant. Jan. 2022 – Present
Advisor: Prof. Laurent Itti

IRIS Computer Vision Lab, USC, Los Angeles, CA
Research Assistant. Jan. 2022 – May. 2024
Advisor: Prof. Ram Nevatia

Research Center, SenseTime, China
Research Engineer. Sep. 2019 – Aug. 2021
Advisor: Dr. Xiaoke Jiang and Dr. Yichao Wu

Shenzhen Institue of advanced technology, Chinese Academy of Sciences, China
Research Assistant. Jul. 2018 – Jun. 2019

Shenzhen Research Institute, the Chinese University of Hong Kong, China
Research Intern. Dec. 2017 – Jun. 2018

Awards

• Oct. 2021: 1st on MS1M dataset in ICCV 2021 Masked Face Recognition Challenge out of 136 teams.
• Oct. 2021: 2nd on Glint360k dataset in ICCV 2021 Masked Face Recognition Challenge out of 86 teams.

• Nov. 2017: National Endeavor Scholarship (top 1% Undergraduate Students of China).

Patents

• A Railway Face Recognition Solution Based on History Passengers’ Riding Pattern.
  Wanrong Zheng, Xiaoke Jiang, Jikui Bao, Qichen Li and Cong Ji. CN202110654499.8 (2021)

• A Identification method Based on History Passenger Flow Big Data.
  Wanrong Zheng and Xiaoke Jiang. CN202011132611.3 (2020)

• Passenger Illegal Handing Bags Across Railing Detection in Real Railway Scene.
  Sun Zhe and Wanrong Zheng. (2020)