⚙️ Projects

⚙️ Projects

This section documents research software, evaluation platforms, academic challenges, and funded projects. Associated research outputs are listed under Publications.

Research Software

Darknet-Cross

Lightweight Deep Learning Framework for Heterogeneous Computing

2018.03 – 2018.11

A cross-platform acceleration framework developed for Android and Ubuntu across mobile and desktop GPUs. This work formed the engineering component of my master’s thesis at HKU.

GitHub repository →

Research Platforms

VideoCube / MGIT

2019.11 – Present

Evaluation infrastructure for the Global Instance Tracking and Multi-modal Global Instance Tracking studies published at TPAMI 2023 and NeurIPS 2023. The platform supports dataset access, tracker registration, standardized submission, and reproducible evaluation.

1.66M+ visits1.9K+ users720+ trackers960+ submissions

Visit platform →

SOTVerse / VLTVerse

2021.07 – Present

A task-space evaluation platform for the SOTVerse and VLTVerse research program, including the study published in IJCV 2024. It provides structured evaluation across tracking scenarios, target categories, and linguistic specifications.

267K+ visitsTask-space evaluation

Visit platform →

BioDrone

2022.05 – Present

Benchmark and evaluation infrastructure for real-world drone tracking research, including the BioDrone study published in IJCV 2024. It supports dataset access, standardized benchmarking, and comparative evaluation.

541K+ visitsReal-world UAV tracking

Visit platform →

GOT-10k

2020.07 – Present

Long-term maintenance of the large-scale evaluation platform supporting the GOT-10k research published in TPAMI 2021. It provides benchmark access, tracker registration, result submission, and evaluation services.

7.56M+ visits11K+ users32.7K+ trackers406K+ submissions

Visit platform →

Challenges

Hislopvision Challenge

2023.05 – 2023.11

Organization of the Hislopvision track for the 3rd High-speed and Low-power Visual Understanding Challenge at PRCV 2023, with participating teams from Tsinghua University, Beijing Institute of Technology, and Jilin University.

Challenge platform →

Cell Tracking Challenge

2021.01 – 2021.04

Our method ranked second on Fluo-C2FL-MSC+ and third on Fluo-C2FL-Huh7, based on the challenge rankings recorded in October 2023.

Challenge website →

Funded Research Project

Human-Computer Interaction in Intelligent Education

2024.01 – 2025.01

Proposal development and project delivery for a study funded by the 2023 Intelligent Education PhD Research Fund at the Shanghai Institute of AI Education, East China Normal University.