Welcome to my website! 😆😆😆
I am now working on Multi-image/video understanding and reasoning, Infrared small target detection, and Multimodal image registration. If you are seeking any form of academic cooperation (学术合作), please feel free to email me at yuchuang@sia.cn / yuchuang1205@163.com.
I am a PHD student in the SIA-CAS’s Master-Doctor combined program, supervised by Prof. Yunpeng Liu.
Since October 2024, I have been honored to be a Research Assistant at CUHK-MMLab, under the supervision of Prof. Xiangyu Yue.
I was honored with the CAS President Award - Special Prize (中国科学院院长特别奖) in 2025 and was twice awarded the National Scholarship for Ph.D. Students in 2022 and 2024.
I won the 1st place of Water Body Extraction from High-resolution and Multi-modal Optical Images in the 2024 ISPRS TC I Contest on Intelligent Interpretation for Multi-modal Remote Sensing Application (Team leader) and the 1st prize in the PRCV2024 Wide-area Infrared Small Target Detection Challenge (Team leader).
🔥 News 🔥
-2025.12: 🌟🌟 Our new works, MIND and FDEP Framework, have been released.
-2025.11: 🎉🎉 One paper (MSDA-Net) is accepted by TGRS 2025.
-2025.09: 🎉🎉 One paper (RRL-Net) is accepted to Information Fusion 2025.
-2025.06: 🎉🎉 One paper (PAL Framework) is accepted to ICCV 2025.
-2025.05: 🌸🌸 Honored with the CAS President Award – Special Prize.
-2024.11: 🥇🥇 Awarded 1st Prize in the PRCV2024 Wide-area Infrared Small Target Detection Challenge.
-2024.11: 🥇🥇 Awarded 2nd Prize in the ICPR 2024 Resource-Limited Infrared Small Target Detection Challenge Track 1 and Track2.
-2024.11: 🌸🌸 Honored with the National Scholarship.
-2024.05: 🥇🥇 Awarded 1st Place in the 2024 ISPRS TC I Contest on Intelligent Interpretation for Multi-modal Remote Sensing Application.
-2023.10: 🎉🎉 One paper (FIL-Net) is accepted to TIP 2023.
-2023.06: 🎉🎉 One paper (EFR-Net) is accepted to TGRS 2023.
-2022.11: 🌸🌸 Honored with the National Scholarship.
-2022.06: 🎉🎉 One paper (MFD-Net) is accepted to TGRS 2022.
-2022.06: 🎉🎉 One paper is accepted to J-START 2022.
-2022.05: 🎉🎉 Two paper (MLCL-Net) and (ALCL-Net) is accepted to IPT 2022 and GRSL 2022.
📝 Publications (Some representative papers)
MIND: Multi-rationale INtegrated Discriminative Reasoning Framework for Multi-modal Large Models
Chuang Yu, Jinmiao Zhao, Mingxuan Zhao, Yunpeng Liu*, Xiujun Shu, Yuanhao Feng, Bo Wang, Xiangyu Yue*
arXiv Preprint, 2025
We propose a Multi-rationale INtegrated Discriminative (MIND) reasoning framework, which is designed to endow MLLMs with human-like cognitive abilities of “Understand → Rethink → Correct”, and achieves a paradigm evolution from passive imitation-based reasoning to active discriminative reasoning.
Rethinking Infrared Small Target Detection: A Foundation-Driven Efficient Paradigm
Chuang Yu, Jinmiao Zhao, Yunpeng Liu*, Yaokun Li, Xiujun Shu, Yuanhao Feng, Bo Wang, Yimian Dai, Xiangyu Yue*
arXiv Preprint, 2025
We systematically introduce the frozen representations from VFMs into the SIRST task for the first time and propose a Foundation-Driven Efficient Paradigm (FDEP), which can seamlessly adapt to existing encoder-decoder-based methods and significantly improve accuracy without additional inference overhead.
From Easy to Hard: Progressive Active Learning Framework for Infrared Small Target Detection with Single Point Supervision
Chuang Yu, Jinmiao Zhao, Yunpeng Liu*, Sicheng Zhao, Yimian Dai, Xiangyu Yue*
ICCV 2025 (Accepted)
Inspired by organisms gradually adapting to their environment and continuously accumulating knowledge, we construct an innovative Progressive Active Learning (PAL) framework, which drives the existing SIRST detection networks progressively and actively recognizes and learns harder samples.
Why and How: Knowledge-Guided Learning for Cross-Spectral Image Patch Matching
Chuang Yu, Yunpeng Liu*, Jinmiao Zhao, Xiangyu Yue*
arXiv Preprint, 2025
We make the first attempt to explore a stable and efficient bridge between descriptor learning and metric learning, and construct a knowledge-guided learning network (KGL-Net), which achieves amazing performance improvements while abandoning complex network structures.
Multi-Scale Direction-Aware Network for Infrared Small Target Detection
Jinmiao Zhao, Zelin Shi*, Chuang Yu, Yunpeng Liu, Xinyi Ying, Yimian Dai
IEEE Transactions on Geoscience and Remote Sensing, 2025 (Accepted)
We propose a multi-scale direction-aware network (MSDA-Net), which is the first attempt to integrate the high-frequency directional features of infrared small targets as domain prior knowledge into neural networks.
Towards Robust Infrared Small Target Detection: A Feature-Enhanced and Sensitivity-Tunable Framework
Jinmiao Zhao, Zelin Shi*, Chuang Yu, Yunpeng Liu, Yimain Dai
Knowledge-Based Systems, 2025 (Accepted)
Different from most existing deep learning-based methods that focus on improving network architectures, we propose a feature-enhanced and sensitivitytunable (FEST) framework, which is compatible with existing SIRST detection networks and further enhances their detection performance.
Relational Representation Learning Network for Cross-Spectral Image Patch Matching
Chuang Yu, Yunpeng Liu*, Jinmiao Zhao, Dou Quan, Xiangyu Yue*
Information Fusion, 2024 (Accepted)
We propose an innovative relational representation learning idea that simultaneously focuses on sufficiently mining the intrinsic features of individual image patches and the relations between image patch features. Based on this, we construct a Relational Representation Learning Network (RRL-Net).
Feature Interaction Learning Network for Cross-Spectral Image Patch Matching
Chuang Yu, Yunpeng Liu*, Jinmiao Zhao, Shuhang Wu, Zhuhua Hu
IEEE Transactions on Image Processing, 2023 (Accepted)
We propose a novel two-branch feature interaction learning network (FIL-Net), which can effectively mine common and private features between cross-spectral image patches, and extract richer and deeper feature relations with invariance and discriminability.
Efficient Feature Relation Learning Network for Cross-Spectral Image Patch Matching
Chuang Yu, Jinmiao Zhao, Yunpeng Liu*, Shuhang Wu, Chenxi Li
IEEE Transactions on Geoscience and Remote Sensing, 2023 (Accepted)
We construct a novel four-branch efficient feature relation learning network (EFR-Net), which reasonably combines multiple feature relation learning to comprehensively and effectively extract the differential features and consistent features between image patches.
Multi-branch Feature Difference Learning Network for Cross-Spectral Image Patch Matching
Chuang Yu, Yunpeng Liu*, Chenxi Li et al.
IEEE Transactions on Geoscience and Remote Sensing, 2022 (Accepted)
We propose a novel multibranch feature difference learning network (MFD-Net), which can capture richer and more discriminative feature difference information and achieve significant improvements on matching tasks.
🏆 Honors and Awards
- 2025 CAS President Award – Special Prize (中国科学院院长特别奖) (Top 0.1%) (news report)
- 2024 The 1st place of Water Body Extraction from High-resolution and Multi-modal Optical Images in the 2024 ISPRS TC I Contest on Intelligent Interpretation for Multi-modal Remote Sensing Application (Team leader) (news report)
- 2024 The 1st prize in the PRCV2024 Wide-area Infrared Small Target Detection Challenge (Team leader) (news report)
- 2024 The 2nd prize in the ICPR 2024 Resource-Limited Infrared Small Target Detection Challenge Track 1. (Team leader)
- 2024 The 2nd prize in the ICPR 2024 Resource-Limited Infrared Small Target Detection Challenge Track 2. (Team leader)
- 2024 The 3rd prize of the First “Shensi Cup” - Urban Lifeline·AI Problem Solving Challenge. (Team leader)
- 2024 The 3rd place of Marine Farms Segmentation in High-Resolution SAR Images in the 5TH Gaofen Challenge on Automated High Resolution Earth Observation Image Interpretation (Team leader)
- 2024 and 2022 National Scholarship (Top 1%)
- 2024 Outstanding Communist Youth League Member of CAS (Top 0.1%) (news report)
- 2023 Outstanding Graduate Student Award of Shenyang Institute of Automation, CAS (Top 1%)
- 2023 and 2024 Pacemaker to Merit Student of the University of Chinese Academy of Sciences (Top 1%)
- 2021, 2023 and 2024 First Class Academic Scholarship of Shenyang Institute of Automation, CAS (Top 10%)
- 2020 Outstanding Graduates (Top 1%)
- 2019 The 2nd prize of China Collegiate Computing Contest Artificial Intelligence Innovation Contest. (Team leader)
⚡ Academic Service:
- Conference Reviewer: CVPR, ICCV, ICPR, etc.
- Journal Reviewer: TGRS, Inf. Fusion, KBS, ESWA, EAAI, JSTARS, IPT, Neurocomputing, etc.
🎯 Hobbies
- 🍳 Cooking and exploring different cuisines
- 🏃 Running and physical conditioning
- 🎧 Music appreciation
- 🎬 Watching films