I am a currently a third year (2022.09-) Master student at the Huazhong University of Science and Technology (HUST), advised by Qiang Li and Zhiwei Wang. Before that, I recieved my Bachelor Engineering degree at the HUST in 2022.

My research interests foucs on algorithms for Health Examination in Endoscopy images/videos, including segmentation, detection, classfication. Recently, I am exploring the potential of visual-language models for endoscopy. If you are interested in my research, welcome to communicate with me!!!

🔥 News

• 2024.12:  🎉🎉 One paper PSDNet was accepted by ICASSP 2025!
• 2024.12:  🎉🎉 One paper MonoBox was accepted by AAAI 2025!
• 2024.10:  🎉🎉 One paper was accepted by JBHI. Congratulations to Fang Peng!
• 2024.09:  🎉🎉 I won the National Scholarship for Master Students (WNLO, HUST).
• 2024.09:  🎉🎉 Our paper SALI was invited as an Oral presentation (<3%) in MICCAI 2024.
• 2024.06:  🎉🎉 One paper SALI was accepted by MICCAI 2024. Congratulations to the co-author Zhenyu Yi!

📝 Publications

AAAI 2025

MonoBox: Tightness-free Box-supervised Polyp Segmentation using Monotonicity Constraint

Qiang Hu, Zhenyu Yi, Ying Zhou, Fan Huang, Mei Liu, Qiang Li, Zhiwei Wang

Code Paper

• MonoBox proposes a novel monotonicity constraint to liberate the training of existing MIL-based box-supervised segmentation methods from the user-unfriendly box-tightness assumption. It is plug-and-play and can improve the tolerance of any MIL-based box-supervised segmentation methods (e.g., BoxInst, BoxLevelSet, IBoxCLA, etc.) to tightness-free box annotations in any scenarios (e.g., common, medical, etc.).

ICASSP 2025

First-frame Supervised Video Polyp Segmentation via Propagative and Semantic Dual-teacher Network

Qiang Hu, Mei Liu, Qiang Li, Zhiwei Wang

Code Paper

• PSDNet greatly reduces the labeling costs of training video segmentation models, which require only one frame of annotation on each video, regardless of the length. It benefits from the existing powerful fundamental video segmentation models (e.g., XMem and SAM 2).

MICCAI 2024 (Oral)

SALI: Short-Term Alignment and Long-Term Interaction Network for Colonoscopy Video Polyp Segmentation

Qiang Hu, Zhenyu Yi, Ying Zhou, Fang Peng, Mei Liu, Qiang Li, Zhiwei Wang

Code Paper

• SALI, a hybrid of Short-term Alignment Module (SAM) and Long-term Interaction Module (LIM), achieves the SOTA performance on the SUN-SEG dataset (currently the largest video polyp segmentation dataset).

• JBHI 2024 Fine-Grained Temporal Site Monitoring in EGD Streams Via Visual Time-Aware Embedding and Vision-Text Asymmetric Coworking, Fang Peng, Hongkuan Shi, Shiquan He, Qiang Hu, Ting Li, Fan Huang, Xinxia Feng, Mei Liu, Jiazhi Liao, Qiang Li, Zhiwei Wang

🎖 Honors and Awards

• 2024.9 National Scholarship (Highest Scholarship from the Ministry of Education of China).

📖 Educations

• 2022.09 - (now), Master, Huazhong University of Science and Technology (HUST), Wuhan.
• 2018.09 - 2022.06, Undergraduate, Huazhong University of Science and Technology (HUST), Wuhan.

💬 Invited Talks

💻 Internships