Hello! 👋 I'm Zhengzhuo Xu

Recently

My research interests 🔎 are in Computer Vision, including but not limited to imbalanced data learning / 3D recognization. Contact me via ✉️ xzzthu@gmail.com.

Research Intern 💼

• 2022.11 - Now
  IDEA supervised by Dr. Haiqin Yang and focus on Long-Tailed Recognition and Unsupervised Visual Pretraining.
• 2021.07 - 2022.07
  Tencent AI lab supervised by Dr. Linchao Bao and focus on 3D Reconstruction / Style Transfer.
• 2019.12 - 2020.06
  Ping An Tech supervised by Dr. Haiqin Yang and focus on Data Mining.

Education 🎓

• 2020.09 - Today
Ph.D Candidate at SIGS, Tsinghua University, supervised by Prof. Chun Yuan and focus on Long-tailed Data Mining.
GPA: 3.89/4.00

• 2017.07 - 2017.09
Short-term exchange at Oriel College, Oxford.

• 2016.09 - 2020.06
Receive the Bachelor degree of Electrical Engineering in Qiming College, EIC, HUST.
Weighted score: 88.84/100 (Top 3%)

Publication 📄

• Learning Imbalanced Data with Vision Transformers
  Zhengzhuo Xu, Ruikang Liu, Shuo Yang, Zenghao Chai, Chun Yuan
  CVPR, 2023. [Arxiv] [Code] [PDF]

• Rethink Long-tailed Recognition with Vision Transforms
  Zhengzhuo Xu*, Shuo Yang*, Xingjun Wang, Chun Yuan
  ICASSP，2023. [Arxiv] [Code to release] [PDF]

• HHF: Hashing-guided Hinge Function for Deep Hashing Retrieval
  Chengyin Xu*, Zhengzhuo Xu*, Zenghao Chai*, Hongjia Li, Qiruyi Zuo, Lingyu Yang, Chun Yuan
  IEEE TMM. [Arxiv] [IEEE] [Code]

• REALY: Rethinking the Evaluation of 3D Face Reconstruction
  Zenghao Chai*, Haoxian Zhang*, Jing Ren, Di Kang, Zhengzhuo Xu, Xuefei Zhe, Chun Yuan, Linchao Bao
  ECCV, 2022. [Arxiv] [Page] [Code] [PDF]

• Semantic-Sparse Colorization Network for Deep Exemplar-based Colorization
  Yunpeng Bai, Chao Dong, Zenghao Chai, Andong Wang, Zhengzhuo Xu, Chun Yuan
  ECCV, 2022. [Arxiv] [Code] [PDF]

• HyP2 Loss: Beyond Hypersphere Metric Space for Multi-label Image Retrieval
  Chengyin Xu, Zenghao Chai, Zhengzhuo Xu, Chun Yuan, Yanbo Fan, Jue Wang
  ACM MM, 2022. [Arxiv] [Code] [PDF]

• CMS-LSTM: Context Embedding and Multi-Scale Spatiotemporal Expression LSTM for Predictive Learning
  Zenghao Chai, Zhengzhuo Xu, Yunpeng Bai, Zhihui Lin, Chun Yuan
  ICME, 2022. [Arxiv] [Code] [PDF]

• MoDeRNN: Towards Fine-grained Motion Details for Spatiotemporal Predictive Learning
  Zenghao Chai, Zhengzhuo Xu, Chun Yuan
  ICASSP, 2022. [Arxiv] [Code] [PDF]

• Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective
  Zhengzhuo Xu*, Zenghao Chai*, Chun Yuan
  NeurIPS, 2021. [Arxiv] [OpenReview] [Code] [PDF] [Supplementary Material]

• Backscatter-assisted computation offloading for energy harvesting IoT devices via policy-based deep reinforcement learning
  Yutong Xie, Zhengzhuo Xu, Yuxing Zhong, Jing Xu, Shimin Gong, Yi Wang
  IEEE/CIC ICCC Workshops, 2019. [IEEE] [PDF]

• Backscatter-assisted hybrid relaying strategy for wireless powered IoT communications
  Yutong Xie, Zhengzhuo Xu, Shimin Gong, Jing Xu, Dinh Thai Hoang, Dusit Niyato
  IEEE GLOBECOM, 2019. [IEEE] [PDF]

• Backscatter-aided hybrid data offloading for mobile edge computing via deep reinforcement learning
  Yutong Xie, Zhengzhuo Xu, Jing Xu, Shimin Gong, Yi Wang
  MLICOM, 2019. [Springer]

Patent 🧾

• Retrieval Method, Device and Equipment and Computer Readable Storage Medium.
  Chengyin Xu, Zenghao Chai, Zhengzhuo Xu, Yanbo Fan.
  Invention patent, CN115146143A.

• A Lightweight Fine-grained Spatiotemporal Predictive Method and System.
  Chun Yuan, Zenghao Chai, Zhengzhuo Xu.
  Invention patent, CN114445463A.

• A Method for Obtaining Interpretability Parameters of Deep Learning Models.
  Zhengzhuo Xu, Haiqin Yang.
  Invention patent, CN112052957A.

Awards 🌟

• Tsinghua Friend JiuJiang Scholarship (TOP 5%)
• Excellent Students of QiMing College (best honor of HUST, TOP 1%)
• HaiHang Scholarship (TOP 1%)
• Outstanding Undergraduate Graduates of HUST (TOP 5%)
• First Class Scholarship of HUST (3 times, TOP 10%)
• New Student Scholarship of HUST (TOP 30%)

Project 🔨

• China Collegiate Computing Contest (CCCC) 2019.
  Second class prize in the FINAL [App] available at Apple Store [Present Video]
• Rubik’s Cube Robot Design.
  An automatic cube solving robot via visual recognization and stepper motor [Demo Video]
• BeiBei Seed Cup Competition 2017.
  Rank 11/1000 [Code]
• Music Visualizer Circut
  A hardware circuit which uses LEDs and a power amplifier (LM386) to visualize music (low, medium and high frequence bandwidth) [Demo Video]
• Digital Signal Processing Course Design.
  A electronic piano simulator[Code]

Leadership 🔭

• Outstanding annual member of the branch committee for post-graduate from Dept. of SIGS, Tsinghua.
• Commissary in charge of organization, the Party branch for post-graduate from the Dept. of SIGS, Tsinghua.
• Person in charge the Dept. of Club, Students’ Association Union of Huazhong University of Science and Technology.