以第一作者、通信作者(*)在国内外权威期刊和会议上发表论文20余篇,其中SCI收录9篇,EI 收录8篇。 [1] Yan Gui, Zhuo Liu, Li-Dan Kuang, Zhihua Chen. Structure-aware and Memory-Enhanced Video Instance Segmentation for Echocardiography. In Processing of 2026 IEEE International Conference on Multimedia and Expo, ICME 2026, Bangkok, Thailand, 5-9 July, 2026. (Accepted) [2] Ruojun Guo, Yan Gui*, Jianming Zhang, Fengling Li. Learnable Bilateral Downsampling and Triple-Augmented Feature Fusion in YOLOv8 for Small Object Detection of UAV Aerial Images. In Processing of the 32nd International Conference on Neural Information, ICONIP 2025, Okinawa, Japan, 20–24 November, LSCS, 16313: 393-408. [3] Yuhang Yi, Yan Gui*, Zhuo Liu. Boosting Memory Network for Video Object Segmentation in Complex Scenes. Visual Computer, 41(9): 6571-6585, 2025. [4] Yan Gui, Yaning Liu, Chen Yan, Lidan Kuang, Zhihua Chen. Lightweight structure-guided network with hydra interaction attention and global–local gating mechanism for high-resolution image inpainting. Expert Systems With Applications, 272:126717, 2025. [5] 黄文韬,桂彦,潘祖望. 目标尺度自适应Transformer的图像彩色化方法. 计算机辅助设计与图形学学报,1-13,2025 [6] 潘祖望,桂彦,易宇航,张建明. 全局特征增强及掩模矫正的半监督视频目标分割方法, 计算机辅助设计与图形学学报,37(10): 1837-1848,2025. [7] 桂 彦, 叶文倩, 王建新, 吕松涛, 葛冬冬. 基于CNN和尺度自适应融合网络的路面裂缝分割方法. 中国公路学报, 37(12): 418-432, 2024. [8] Yan Gui, Yiru Ou, Ruojun Guo, Jianming Zhang, and Zhihua Chen. Efficient Visual Object Tracking with Temporal Context-Aware Token Learning and Scale Adaptive Token Pruning, Proceedings of 31st International Conference Neural Information Processing, ICONIP 2024, Auckland, New Zealand, December 2–6, 2024 [9] Yan Gui, Yiru Ou, Min Liang, Jianming Zhang, Zhihua Chen. Spatio-temporal SiamFC: per-clip visual tracking with siamese non-local 3D convolutional networks and multi-template updating. Pattern Analysis and Applications, 27: 109, 2024. [10] Yan Gui, Yan Xie, Lidan Kuang, Zhihua Chen, and Jin Zhang. Enhancing Image Rescaling Using High Frequency Guidance and Attentions in Downscaling and Upscaling Network. Computer Graphics International Conference 2023, Lecture Notes in Computer Science, 14495: 427–439, 2024. [11] Yan Gui, Zhengyan Zhang, Zhihua Chen, Chuang Zhang, Jin Zhang. CGAN: lightweight and feature aggregation network for high-performance interactive image segmentation, Visual Computer, 40, 2203-2217, 2024. [12] Yan Gui, Bingqiang Zhou, Jianming Zhang, Cheng Sun, Lingyun Xiang, Jin Zhang: Learning interactive multi-object segmentation through appearance embedding and spatial attention. IET Image Processing, 16(10): 2722-2737, 2022. [13] Yan Gui, Bingqiang Zhou, Daming Xiong, Wu Wei. Fast and robust interactive image segmentation in bilateral space with reliable color modeling and higher order potential, Journal of Electronic Imaging, 30(3), 033018, 2021. [14] Yan Gui, Ying Tian, Daojian Zeng, Zhifeng Xie, Yiyu Cai. Reliable and Dynamic Appearance Modeling and Label Consistency Enforcing for Fast and Coherent Video Object Segmentation with the Bilateral Grid. IEEE Transactions on Circuits and Systems for Video Technology, 30(12): 4781-4795, 2020. [15] Yan Gui and Guang Zeng. Joint Learning of Visual and Spatial Features for Edit Propagation from a Single Image. Visual Computer, 36(3): 469-482, 2020. [16] Yan Gui and Yang Liu. Discrete Texture Elements Synthesis on Surfaces using Elements Distribution. Int. J. Computational Vision and Robotics, 10(1): 61-78, 2020. [17] Feng Li, Chaofeng Ou, Yan Gui*, and Lingyun Xiang. Instant Edit Propagation on Images Based on Bilateral Grid. CMC-Computers Materials & Continua, 2019, 61(2): 643-656. [18] 桂彦,郭林,曾光. 单幅图像训练深度神经网络的编辑传播方法. 计算机辅助设计与图形学学报, 2019, 31(8): 1391-1402. [19] 桂彦,曾光,汤问. 基于双边网格和置信颜色模型的快速图像鲁棒分割方法. 计算机辅助设计与图形学学报,2018,30(7): 1284-1296. [20] 桂彦,汤问,曾光. 梯度约束SLIC的快速视频目标提取方法. 计算机科学与探索,2019,13(02): 285-299. [21] 桂彦,刘杨,李峰. 元素分布构建的三维模型表面纹理合成方法. 计算机科学与探索,2017,11(9): 1484-1495. [22] 何豪杰,桂彦*,李峰. 具有重复场景元素的复杂自然图像颜色编辑. 计算机科学与探索,2017,11(11): 1792-1803. [23] 桂彦,王培玉,李峰,刘杨. 基元GPU加速的几何纹理合成方法. 浙江大学学报(理学版),2016,43(6): 638-646. [24] 杨弄影,李峰,桂彦*. 纹理图像中重复纹理元素提取方法. 计算机科学与探索,2016,10(8): 1154-1165. |
|
1. 易宇航,桂彦. 一种全局局部特征融合的半监督视频目标分割方法及系统, 2024-11-25, CN 202411688385.5 2. 潘祖望, 桂彦. 一种全局特征增强的半监督视频目标分割方法及系统, 2024-01-12, 中国, CN 2024100490131 3. 潘祖望, 桂彦.一种掩码矫正的半监督视频目标分割方法及系统, 2024-03-07, 中国, CN 202410262004.0 4. 张创,桂彦. 一种基于改进 DAB-DETR 的目标检测方法及系统,2024-01-12,中国, CN 202410049017.X 5. 张创,桂彦. 一种基于改进 Deformable-DAB-DETR 的小目标检测方法及系统, 2024-03-07, 中国, CN 202410262100.5 6. 张珍艳, 桂彦等. 一种基于条件生成对抗的交互式图像分割方法及系统, 2026-03-20, 中国, ZL 202211487962.5 7. 陈旺,桂彦. 基于道路约束的车道线鲁棒检测与提取方法, 2025-11-21, 中国, ZL 202310332526.9 8. 桂彦,魏武,梁敏. 一种基于深度相似的编辑传播方法及系统, 2025-03-25, 中国, ZL 202111330683.3 9. 桂彦,魏武,张珍艳. 周炳强, 一种基于深度循环注意力的图像多目标提取方法及系统, 2024-06-07, 中国, ZL 202111330682.9 10. 桂彦,田颖,曾光. 一种双边视频目标分割方法及系统,2023-02-24,中国,ZL 201910417693.7 |