Research
ResearchHowTo
- Please carefully read and think the resources collected by MAC@XMU.
- Research: are we on the right way? by Prof. Song-Chun Zhu.
Funding
- Research of Generalized Zero-Shot Learning towards Open-World Image Recognition. National Natural Science Foundation (NSFC) Youth. Grant No.62206260, Duration: 2023.01-2025.12, Principal Investigator. ¥300 Thousand.
- Research on the Construction of Multimodal Traffic Dataset and Traffic Prediction Model. Duration: 2024.10-2025.04, Principal Investigator (3rd Place). ¥490 Thousand.
- Research on Multimodal Data Semantic Modeling Technology for the Association of Social Governance Case (Event) Elements. National Natural Science Foundation (NSFC). Duration: 2023.11-2026.10, Main Investigator. ¥1500 Thousand.
Publications
Please see my Google Scholar for the full publication list.
2025
-
Neurocomputing
-
TCSVT
Dual Prototype Contrastive Network for Generalized Zero-Shot LearningIEEE Transactions on Circuits and Systems for Video Technology (TCSVT) , 2025
2024
-
TCSVT
Fair Attention Network for Robust Visual Question AnsweringIEEE Transactions on Circuits and Systems for Video Technology (TCSVT) , 2024 -
TKDD
Incorporating Multi-Level Sampling with Adaptive Aggregation for Inductive Knowledge Graph CompletionACM Transactions on Knowledge Discovery from Data (TKDD) , 2024 -
PRL
Self-Supervised Knowledge Distillation in Counterfactual Learning for VQAPattern Recognition Letters (PRL) , 2024 -
TCSVT
Domain-Aware Prototype Network for Generalized Zero-Shot LearningIEEE Transactions on Circuits and Systems for Video Technology (TCSVT) , 2024 -
TCSVT
See and Learn More: Dense Caption-Aware Representation for Visual Question AnsweringIEEE Transactions on Circuits and Systems for Video Technology (TCSVT) , 2024
2023
-
MM
Breaking the Barrier Between Pre-training and Fine-tuning: A Hybrid Prompting Model for Knowledge-Based VQAProceedings of the 31st ACM International Conference on Multimedia (MM) , 2023 -
PRL
Multi-Level Attention for Referring Expression ComprehensionPattern Recognition Letters (PRL) , 2023
2022
-
AAAI
Unsupervised Coherent Video Cartoonization with Perceptual Motion ConsistencyProceedings of the AAAI Conference on Artificial Intelligence (AAAI) , 2022 -
PRL
CGNN: Caption-Assisted Graph Neural Network for Image-Text RetrievalPattern Recognition Letters (PRL) , 2022
2019
-
SPL
2018
-
IVC
Attribute Annotation on Large-Scale Image Database by Active Knowledge TransferImage and Vision Computing (IVC) , 2018
2017
2015
Patents
- 姜华杰, 李正先, 胡永利, 尹宝才. 基于视觉语义提示协作的泛化零样本学习方法. CN119580001A. 2025.
- 胡永利, 张家森, 姜华杰, 尹宝才. 一种基于隐属性增强网络的小样本类增量学习方法. CN119251548A. 2025.
- 胡永利, 夏东烽, 姜华杰, 尹宝才. 一种基于实例对齐顺序融合的3D目标检测方法. CN117935248A. 2024.
- 胡永利, 刘梦婷, 姜华杰, 尹宝才. 基于多层次知识蒸馏类增量学习方法. CN117494790A. 2024.
- 孙艳丰, 张云茹, 胡永利, 姜华杰, 尹宝才. 基于多层注意力的视觉定位方法. CN115984372A. 2023.
- 姜华杰, 刘昊淼, 金鑫, 涂丹丹. 一种故障检测方法和装置. CN115937057A. 2023.
- 杜长德, 金鑫, 姜华杰, 涂丹丹. 故障图像生成方法与装置. CN115294007A. 2022.
- 姜华杰, 刘昊淼, 金鑫, 涂丹丹. 一种图像处理方法以及相关设备. CN114757250A. 2022.