成果/Result
- Improving Few-shot Image Generation by Structural Discrimination and Textural Modulation被引量：62收藏
- 作者：Yang, Mengping Wang, Zhe Feng, Wenyi Zhang, Qian Xiao, Ting
- 机构： Key Laboratory of Smart Manufacturing in Energy Chemical Process; Department of Computer Science and Engineering
- 来源：arXiv 2023
- 关键词：Semantics
- Semantic-Aware Generator and Low-level Feature Augmentation for Few-shot Image Generation被引量：58收藏
- 作者：Wang, Zhe Guan, Jiaoyan Yang, Mengping Xiao, Ting Chi, Ziqiu
- 机构： Key Laboratory of Smart Manufacturing in Energy Chemical Process; Department of Computer Science and Engineering
- 来源：MM 2023 - Proceedings of the 31st ACM International Conference on Multimedia 2023
- 关键词：Computer vision - Semantic Web - Semantics
- VSNet: classification of pulmonary nodules in 3D using vision transformer and sequence spatial attention mechanism被引量：37收藏
- 作者：Tang, Dongfang Xiao, Ting Yang, Fan Zhang, Conghao Wang, Zhe Gao, Wen
- 机构： Department of Thoracic Surgery; Department of Computer Science and Engineering
- 来源：Multimedia Tools and Applications 2025
- 关键词：Classification (of information) - Computer aided diagnosis - Computerized tomography - Positron emission tomography
- Vision-Core Guided Contrastive Learning for Balanced Multi-modal Prognosis Prediction of Stroke被引量：36收藏
- 作者：Chen, Liren Sun, Lidong Huang, Mingyan Tang, Junzhe Zhu, Yinghui Wang, Guanjie Xia, Yiqing Xiao, Ting
- 机构： School of Information Science and Engineering
- 来源：arXiv 2026
- 关键词：Alignment - Brain - Computer vision - Deep learning - Diagnosis - Information fusion - Learning systems - Medical image processing - Modal analysis - Visual languages
- Few-Shot Adaptive Diffusion with Semantic Injection and Parameter Smoothing被引量：36收藏
- 作者：Cai, Yunjie Xiao, Ting Zhang, Yanbing Wang, Zhe
- 机构： Key Laboratory of Smart Manufacturing in Energy Chemical Process
- 来源：ICMR 2025 - Proceedings of the 2025 International Conference on Multimedia Retrieval 2025
- 关键词：Diffusion - Image texture - Quality control - Semantic Web - Semantics - Textures
- BioProVLA-Agent: An Affordable, Protocol-Driven, Vision-Enhanced VLA-Enabled Embodied Multi-Agent System with Closed-Loop-Capable Reasoning for Biological Laboratory Manipulation被引量：35收藏
- 作者：Du, Zhaohui Wang, Zhe Fei, Hongmei Cao, Xiwen Xiao, Ting Wang, Qi Jin, Huanbo Gu, Jiaming Lu, Quan Liu, Zhe
- 机构： Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education; Department of Computer Science and Engineering; Department of Laboratory Medicine; School of Information Science and Technology
- 来源：arXiv 2026
- 关键词：Intelligent agents - Interface states - Laboratories - Molecular biology - Robots - User interfaces - Vision - Visual languages - Waste disposal
- An Embodied Simulation Platform, Benchmark, and Data-Efficient Augmentation Framework for Wet-Lab Robotics被引量：31收藏
- 作者：Liu, Zhe Jin, Huanbo Du, Zhaohui Wang, Zhe Xu, He Li, Peijia Gu, Jiaming Lu, Quan Wang, Qi Ji, Bin Xiao, Ting
- 机构： Key Laboratory of Smart Manufacturing in Energy Chemical Process; Department of Computer Science and Engineering; Department of Laboratory Medicine
- 来源：arXiv 2026
- 关键词：Computer simulation languages - Laboratories - Natural language processing systems - Personnel training - Pipelines - Robot learning - Robots - Simulation platform
- Robust Structured Sparse Subspace Clustering with Neighborhood Preserving Projection被引量：28收藏
- 作者：Feng, Wenyi Guo, Wei Xiao, Ting Wang, Zhe
- 机构： Key Laboratory of Smart Manufacturing in Energy Chemical Process; Department of Computer Science and Engineering; Qinghai University
- 来源：Proceedings - IEEE International Conference on Multimedia and Expo 2023
- 关键词：Structural optimization
- Stroke Outcome Prediction via Multi-level Feature and Multi-modal Fusion Network被引量：27收藏
- 作者：Xiao, Ting Shi, Lei Wang, Hao Wang, Zhe Lin, Yi
- 机构： East China University of Science and Technology; Harbin Medical University
- 来源：Proceedings - 2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024 2024
- 关键词：Deep learning - Image coding - Medical image processing - Multi-task learning - Network coding - Prediction models
- Adaptive weighted dictionary representation using anchor graph for subspace clustering被引量：26收藏
- 作者：Feng, Wenyi Wang, Zhe Xiao, Ting Yang, Mengping
- 机构：East China Univ Sci & Technol;East China Univ Sci & Technol;Qinghai Univ
- 来源：PATTERN RECOGNITION 2024
- 关键词：Dictionary representation Subspace clustering Anchor graph Projection learning
- FedGAN: Federated GAN for Few-shot Image Generation被引量：23收藏
- 作者：Zhang, Yanbing Zhang, Qian Yang, Mengping Xiao, Ting Wang, Zhe
- 机构： East China University of Science and Technology
- 来源：2023 3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023 2023
- Extended Multi-scale Feature Fusion and Balanced Generative Adversarial Network for Image Inpainting under Limited Data被引量：21收藏
- 作者：Xiao, Ting Sun, Minqian Chen, Haoyuan Li, Jiaqi Qiu, Yixing Wang, Zhe Lu, Dan
- 机构： Department of Computer Science and Engineering; School of Artificial Intelligence; School of Computer Science and Technology
- 来源：Proceedings of SPIE - The International Society for Optical Engineering 2025
- Monotonic Quantile Network for Worst-Case Offline Reinforcement Learning被引量：11收藏
- 作者：Bai, Chenjia Xiao, Ting Zhu, Zhoufan Wang, Lingxiao Zhou, Fan Garg, Animesh He, Bin Liu, Peng Wang, Zhaoran
- 机构：Shanghai AI Lab;East China Univ Sci & Technol;Shanghai Univ Finance & Econ;Northwestern Univ;Northwestern Univ
- 来源：IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024
- 关键词：Behavioral sciences Task analysis Standards Estimation Training Service robots Learning systems Monotonic quantile network (MQN) offline reinforcement learning (RL) quantile regression risk-sensitive learning
- 基于注意力机制和改进YOLOv3的红外弱小目标检测被引量：9收藏
- 作者：冯伟 薛如翔 傅志凌 席永辉 钮赛赛 肖婷 王喆
- 机构：华东理工大学信息科学与工程学院;上海航天控制技术研究所
- 来源：《飞控与探测》 2023
- 关键词：红外弱小目标 目标检测 YOLOv3 深度学习 注意力机制
- 摘要：红外弱小目标检测技术是红外探测系统的核心技术之一。针对远距离复杂场景下红外弱小目标对比度低、信噪比低和纹理特征稀疏分散导致目标检测率低的问题,提出一种融合注意力机制和改进YOLOv3的红外弱小目标检测算法。首先,在YOL...
- 下载全文在线阅读
- Subtype-WGME enables whole-genome-wide multi-omics cancer subtyping被引量：6收藏
- 作者：Yang, Hai Zhao, Liang Li, Dongdong An, Congcong Fang, Xiaoyang Chen, Yiwen Liu, Jingping Xiao, Ting Wang, Zhe
- 机构：East China Univ Sci & Technol;Cornell Univ;Natl Univ Singapore
- 来源：CELL REPORTS METHODS 2024
- Freezing partial source representations matters for image inpainting under limited data被引量：6收藏
- 作者：Zhang, Yanbing Yang, Mengping Xiao, Ting Wang, Zhe Chi, Ziqiu
- 机构：East China Univ Sci & Technol;East China Univ Sci & Technol
- 来源：ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024
- 关键词：Image inpainting Transfer learning Limited data
- Robust Structured Sparse Subspace Clustering with Neighborhood Preserving Projection被引量：5收藏
- 作者：Feng, Wenyi Guo, Wei Xiao, Ting Wang, Zhe
- 机构：East China Univ Sci & Technol;East China Univ Sci & Technol;Qinghai Univ
- 来源：2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME 2023
- 关键词：Sparse Subspace Clustering Self-Representation Manifold Learning Projection Learning
- Semantic-Aware Generator and Low-level Feature Augmentation for Few-shot Image Generation被引量：4收藏
- 作者：Wang, Zhe Guan, Jiaoyan Yang, Mengping Xiao, Ting Chi, Ziqiu
- 机构：East China Univ Sci & Technol;East China Univ Sci & Technol
- 来源：PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023 2023
- 关键词：few-shot image generation generative adversarial network generator features
- Relationship constraint deep metric learning被引量：3收藏
- 作者：Zhang, Yanbing Xiao, Ting Wang, Zhe Wang, Xinru Feng, Wenyi Fu, Zhiling Yang, Hai
- 机构：East China Univ Sci & Technol;East China Univ Sci & Technol
- 来源：APPLIED INTELLIGENCE 2024
- 关键词：Deep metric learning Data relationship Proxy relationship constraint Sample relationship constraint Proxy correction
- 基于元学习自适应的小样本语音合成被引量：2收藏
- 作者：吴郅昊 迟子秋 肖婷 王喆
- 机构：华东理工大学信息科学与工程学院
- 来源：《计算机应用》 2024
- 关键词：小样本生成 语音合成 元学习 说话人适配 特征提取
- 摘要：在小样本条件下的语音合成(TTS)要求在仅有少量样本的情况下合成与原说话人相似的语音,然而现有的小样本语音合成面临如下问题:如何快速适配新说话人,并且在保证语音质量的情况下提高生成语音与说话人的相似性。现有模型在适配新说...
- 下载全文在线阅读
- 基于多模态特征融合的小样本图像分类方法被引量：1收藏
- 作者：李琛琛 王喆 肖婷 马学铭 杨孟平
- 机构：华东理工大学信息科学与工程学院
- 来源：《计算机工程与设计》 2025
- 关键词：小样本图像分类 多模态 注意力机制 特征筛选 语义融合 视觉语言模型 大语言模型
- 摘要：为提升小样本图像分类任务中的模型性能,提出了一种基于多模态特征融合的小样本图像分类方法(AMTAdapter)。该方法通过引入注意力机制模块增强模型对图像的关注能力,利用类内相似度与类间相似度对特征进行筛选,并采用Min...
- 下载全文在线阅读
- 平衡信息与动态更新的原型表示联邦学习被引量：1收藏
- 作者：徐炜钦 肖婷 王喆
- 机构：华东理工大学信息科学与工程学院
- 来源：《华东理工大学学报（自然科学版）》 2024
- 关键词：联邦学习 特征空间聚合 原型表示 对比学习 数据异构
- 摘要：联邦学习(FL)是一种分布式机器学习方法,旨在通过训练模型而不共享客户之间的原始数据来解决隐私问题。然而,跨客户端数据的异构性会阻碍FL中的优化收敛性和泛化性能。为了解决这个问题,本文提出了平衡信息与动态更新的联邦原型学...
- 下载全文在线阅读
- Improving Few-shot Image Generation by Structural Discrimination and Textural Modulation被引量：1收藏
- 作者：Yang, Mengping Wang, Zhe Feng, Wenyi Zhang, Qian Xiao, Ting
- 机构：East China Univ Sci & Technol;East China Univ Sci & Technol
- 来源：PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023 2023
- 关键词：Few-shot Learning Image Generation Textural Modulation Structural Discrimination
- Low-Rank Representation with Empirical Kernel Space Embedding of Manifolds被引量：1收藏
- 作者：Feng, Wenyi Wang, Zhe Xiao, Ting
- 机构：Qinghai Univ;Minist Educ;East China Univ Sci & Technol;Qinghai Prov Lab Intelligent Comp & Applicat
- 来源：NEURAL NETWORKS 2025
- 关键词：Low-rank representation Kernel mapping Manifold learning Feature extraction
- Stroke Outcome Prediction via Multi-level Feature and Multi-modal Fusion Network被引量：0收藏
- 作者：Xiao, Ting Shi, Lei Wang, Hao Wang, Zhe Lin, Yi
- 机构：East China Univ Sci & Technol;Harbin Med Univ
- 来源：2024 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE, BIBM 2024
- 关键词：Disease Prediction Multi-modal Fusion Ischemic Stroke Multi-level Feature Fusion
- A multimodal framework for comprehensive driver variant prediction in cancer被引量：0收藏
- 作者：Yang, Hai Chen, Yijia Zhou, Tianyi Wang, Yingzhuo Zhou, Qin Xiao, Ting Zhang, Qian Zhang, Jing Li, Dongdong Wang, Zhe
- 机构：East China Univ Sci & Technol;East China Univ Sci & Technol;Univ Michigan;Imperial Coll London
- 来源：COMMUNICATIONS MEDICINE 2025
- 基于自适应跨域距离一致的有限数据图像修复被引量：0收藏
- 作者：厉嘉琦 肖婷 杨孟平 王喆
- 机构：华东理工大学信息科学与工程学院;华东理工大学能源化工过程智能制造教育部重点实验室
- 来源：《计算机工程与设计》 2024
- 关键词：图像修复 深度学习 有限数据 预训练 域自适应 公共表征 相对距离
- 摘要：针对现有深度学习图像修复方法在有限数据场景下存在的修复质量差、多样性弱等问题,在预训练基础上提出一种域自适应的方法,迁移源域中可学习的知识,补充训练中所需的信息。对源域和目标域中的特征信息进行探究,发现特征中的结构信息可...
- 下载全文在线阅读
- Enhancing Lung Nodule Classification with Triple Union Efficient Attention and Neural Architecture Search被引量：0收藏
- 作者：Huang, Haihua Yang, Fan Xiao, Ting Tang, Dongfang Wang, Zhe Gao, Wen
- 机构：East China Univ Sci & Technol;East China Univ Sci & Technol;Fudan Univ
- 来源：JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2026
- 关键词：Artificial intelligence Attention mechanism Lung nodule classification Neural Architecture Search Parameter-performance balance
- Automated quantification of the Alberta Stroke Programme Early CT Score (ASPECTS) and infarct core on diffusion-weighted imaging in acute ischaemic stroke: multi-centre validation and severity stratification被引量：0收藏
- 作者：Wei, Lai Xiao, Ting Wang, Hao Shi, Lei Xi, Qian Liu, Ming Xu, Huali Zhang, Kangwei Zhou, Xiang Luo, Yu Wang, Peijun
- 机构：Tongji Univ;East China Univ Sci & Technol;Tongji Univ;Shanghai Jiao Tong Univ;Shanghai Univ Tradit Chinese Med
- 来源：BRAIN COMMUNICATIONS 2026
- 关键词：acute ischaemic stroke (AIS) diffusion-weighted imaging (DWI) the Alberta Stroke Programme Early CT Score (ASPECTS) corevolume deep learning (DL)
- MSCFNet: mixed-scale context fusion network for medical image segmentation被引量：0收藏
- 作者：Xu, Lingyi Tang, Dongfang Xiao, Ting Wang, Hao Wang, Zhe Gao, Wen
- 机构：East China Univ Sci & Technol;Fudan Univ;Minist Educ
- 来源：APPLIED INTELLIGENCE 2026
- 关键词：Medical image segmentation Context fusion Mixed-scale attention
