📝 学术成果(部分)
——————————————————–2025—————————————————————————————–
T. Huai, J. Zhang,X. Wu$^*$, J. Jin, L. He. Efficiency is the rule: Domain adaptive semantic segmentation with minimal annotations[J]. Expert Systems with Applications, 2025, 274: 126892.(通讯作者,中科院一区,IF=7.5)
Z. Zhou, X. Du, Y. Zheng, X. Wu, C. Jin, An Exemplar-based Framework for Chinese Text Recognition, AAAI, 2025 (CCF A类会议)
Z. Xie, C. Han, J. Shi, W. Cui, X. Zhao, X. Wu, J. Zhao. RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual Compensation,ACL,2025(CCF A类会议)
J. Shi, J. Zhao, X. Wu, R. Xu, Y. Jiang, L. He. Mitigating reasoning hallucination through Multi-agent Collaborative Filtering[J]. Expert Systems with Applications, 2025, 263: 125723.(中科院一区,IF=7.5)
X. Du,Z. Zhou,Y. Wang,Y. Zheng,X. Wu,P. Gong,C. Jin. Unleashing the Semantic Adaptability of Controlled Diffusion Model for Image Colorization, IJCAI, 2025(CCF A类会议)
T. Huai, J. Zhou, X. Wu, Q. Chen, Q. Bai, Z. zhou, L. He. CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering, CVPR, 2025(CCF A类会议)
——————————————————–2024—————————————————————————————–
X. Wu, L. Xiao, X. Du, Y. Zheng, X. Li, T. Ma, C. Jin, L. He,Cross-domain document layout analysis using document style guide, Expert Systems with Applications,2024(中科院一区,IF=7.5)
L. Xiao,X. Wu$^*$, J. Xu, W. Li, C. Jin, L. He. Atlantis: Aesthetic-oriented Multiple Granularities Fusion Network for Joint Multimodal Aspect-based Sentiment Analysis, Information Fusion, 2024.(通讯作者,中科院一区,IF=14.7, ESI高被引)
J. Liao ,X. Wu$^*$,Y. Wu and J. Shu. K-NNDP: K-means algorithm based on nearest neighbor density peak optimization and outlier removal, Knowledge-Based Systems, 2024.(通讯作者,中科院一区,IF=7.2)
X. Du, Z. Zhou,__X. Wu$^$__, Y. Wang, Z. Wang, Y. Zheng, C. Jin. MultiColor: Image Colorization by Learning from Multiple Color Spaces, ACM Multimedia, 2024.(共同通讯作者,CCF A)
——————————————————–2023—————————————————————————————–
Y. Wan, W. Li,X. Wu$^*$, J. Xu, and J. Yang. Auto-matic Image Aesthetic Assessment for Human-designed Digital Images. McGE ’23.2023.[Best paper] (通讯作者,CCF A类会议Workshop)
X. Wu, T. Ma, X. Du, Z. Hu, J. Yang, L. He, DRFN: A unified framework for complex document layout analysis, Information Processing & Management., 2023.(中科院一区,IF=7.4)
L. Xiao,X. Wu$^*$, S. Yang, J. Xu, J. Zhou, L. He. Cross-modal Fine-grained Alignment and Fusion Network for Multimodal Aspect-based Sentiment Analysis, Information Processing & Management, 2023.(通讯作者,中科院一区,IF=7.4)
T. Ma, X. Wu†, X.Du, Y. Wang, C. Jin, Image Layer Modeling for Complex Document Layout Generation, ICME, 2023.(共一,CCF B类会议)
J. Zhang, Z. Zhuang, L. Xiao,X. Wu$^*$, T. Ma, L. He, Dual-Expert Distillation Network for Few-Shot Segmentation. ICME, 2023.(通讯作者,CCF B类会议)
X Li, T Ma, Y Hou, B Shi, Y Yang, Y Liu, X Wu, Q Chen, Y Li, Y Qiao, L He. Logonet: Towards accurate 3d object detection with local-to-global cross-modal fusion[C]. CVPR. 2023: 17524-17534.
——————————————————–2022—————————————————————————————–
X. Wu, L. Xiao, Y. Sun, J. Zhang, T. Ma, L. He, A Survey of Human-in-the-loop for Machine Learning, Future Generation Computer Systems,2022.[ Editor’s Choice Papers (编委会从近五年发表论文中提名评选,入选率约0.5% ),ESI热点论文、ESI高被引论文](中科院一区,IF=6.2)
L. Xiao, X. Wu†, W. Wu ,J. Yang, L. He. Multi-channel Attentive Graph Convolutional Network With Sentiment Fusion For Multimodal Sentiment Analysis. ICASSP, 2022.(共一,CCF B类会议)
——————————————————–2021—————————————————————————————–
X. Wu, Y. Zheng, T. Ma, H. Ye, L. He, Document Image Layout Analysis via Explicit Edge Embedding Network, Information Sciences, 2021.(中科院一区,IF=8.1(2022))
X. Wu, Z. Hu, X. Du, J. Yang, L. He. Document Layout Analysis via Dynamic Residual Feature Fusion. ICME, 2021.(CCF B类会议 Oral)
——————————————————–2020之前———————————————————————————–
X. Wu, Y. Zheng, H. Ye, W. Hu, J. Yang, L. He, Adaptive Scenario Discovery for Crowd Counting. ICASSP, 2019.(CCF B类会议)
X. Wu, B. Xu, Y. Zheng, H. Ye, J. Yang, L. He . Fast video crowd counting with a Temporal Aware Network. Neurocomputing, 2020.(中科院二区,IF=5.5)
X. Wu, Y. Zheng, H. Ye, W. Hu, T. Ma, J. Yang, L. He, Counting Crowds with Varying Densities via Adaptive Scenario Discovery Framework[J], Neurocomputing , 2020.(中科院二区,IF=5.5)
X. Wu, S. Kong, Y. Zheng, H. Ye, J. Yang, L. He, Feature channel enhancement for crowd counting. IET Image Processing, 2020.(中科院四区,IF=2.0)
J. He, X. Wu†, W. Hu, J. Yang, LSTMVA: vivid layout via LSTM-based Variational Autoencoder framework. ICDAR, 2021.(共一,CCF C类会议 文档处理顶级会议)
吴俊斌,吴晟,吴兴蛟*.一种用于求解TSP问题的随机最佳插入烟花算法[J].计算机工程与科学,2020,42(11):2080-2087.(CCF C (中文),中文核心,通讯作者)