Hi there 👋

I’m Shengli Zhou, a fourth-year undergraduate in Computer Science and Technology at Southern University of Science and Technology (SUSTech). My research interest mainly focuses on multimodal perception and embodied intelligence.

📫 How to reach me: zhousl2022@mail.sustech.edu.cn

Education

sustech

Undergraduate: Sep. 2022 - Jul. 2026 (Expected)

Southern University of Science and Technology (SUSTech)

Department of Computer Science and Engineering (CSE) & Zhiren College

Major: Computer Science and Technology (GPA: 3.97 / 4.00, rank: 1 / 166)

Member of Turing Class (designated for elite CS students at SUSTech)

Affiliation: Space-Time AI Research (STAR) Lab

Supervisor: Prof. Feng Zheng | Advisor: Prof. Jin Zhang

Publications

Learn 3D VQA Better with Active Selection and Reannotation

  • Shengli Zhou, Yang Liu, Feng Zheng†
  • Accepted by ACM MM 2025 / Paper (arXiv) / Code (GitHub)
  • To address the negative impact of inevitable improper annotation in 3D Visual Question-Answering and the scarcity of annotations, we propose a multi-turn interactive active learning strategy, combining semantic variance-based data selection with interactive oracle reannotation, enhancing answer quality and reducing training costs.

HCNQA: Enhancing 3D VQA with Hierarchical Concentration Narrowing Supervision

  • Shengli Zhou, Jianuo Zhu, Qilin Huang, Fangjing Wang, Yanfu Zhang, Feng Zheng†
  • Accepted by ICANN 2025 / Paper (arXiv) / Code (GitHub)
  • 3D VQA models suffer from superficial shortcuts due to high model complexity and data scarcity; thus, we propose a hierarchical concentration narrowing supervision paradigm to guide the model to perform spatial reasoning under a general pathway and suppress superficial shortcuts.

Research & Visiting Experience

nus

May 2024 - Jul. 2024

National University of Singapore (NUS)

School of Computing (SoC) Summer Workshop (SWS) 2024

Visual Computing | Lecturer: Prof. Terence Sim | Poster

pku

Feb. 2025 - Jul. 2025

Peking University (PKU)

Wangxuan Institute of Computer Technology (WICT)

Multimedia Information Processing Lab (MIPL)

Supervisor: Prof. Yang Liu

Projects

When Active Learning and Data Augmentation meet at Object Detection

  • Autonomous driving systems face challenges in real-time object detection due to high labeling costs and limited dataset diversity, prompting optimization of the RT-DETR-v2 model.
  • Integrated active learning (AL) and data augmentation to enhance detection accuracy while minimizing labeling efforts, focusing on evaluating AL strategies (random, entropy-based, information gain) and augmentation levels (e.g., motion blur, noise).
  • Achieved 75.4% mAP (6% improvement) on KITTI, validating entropy-based AL as optimal and medium-strength augmentation for balancing accuracy and real-world alignment, enabling efficient data utilization. Github

Masked-Unmasked Face Recognition

  • Face recognition struggles with brightness, angle, expression, and occlusion variations.
  • This project uses a non-deep learning approach to develop a classifier inspired by human recognition. It focuses on selecting high-quality local features to improve accuracy and reliability in face recognition. The classifier adaptively selects features based on current conditions, excluding less relevant local features to enhance recognition accuracy.
  • A mask detector with 100% accuracy on the Georgia Tech Dataset and maintaining high accuracy on harder datasets.

Selected Honors

News Reports

[Feb. 2025] 大学生开始感到孤独？如何破解高校“陌生人现象”

  • Mentioned by the official WeChat account of China Comment (半月谈) under Xinhua News Agency (57k views).

[Dec. 2024] 今夜，共赴音乐与青春之约

  • The National Scholarship Awarding Ceremony on SUSTech 2025 New Year Reception Gala, reported by SUSTech Official WeChat Account (5000+ views).

[Nov. 2024] 祝贺！南科大2024年本科生先进集体及优秀个人

  • Reported by SUSTech Official WeChat Account (12k views).

[Oct. 2024] 优秀！他们获得校训奖学金

  • Reported by SUSTech Official WeChat Account (21k views).

[May 2023] 2023年（第二十届）广东省大学生程序设计竞赛成功举办

  • Reported by the official WeChat account of Guangdong Computer Federation.