Query：
学者姓名：朱青
Refining：
Year
Type
Indexed by
Source
Complex
Co-Author
Language
Clean All
Abstract ：
Our work presents a novel spectrum-inspired learning-based approach for generating clothing deformations with dynamic effects and personalized details. Existing methods in the field of clothing animation are limited to either static behavior or specific network models for individual garments, which hinders their applicability in real-world scenarios where diverse animated garments are required. Our proposed method overcomes these limitations by providing a unified framework that predicts dynamic behavior for different garments with arbitrary topology and looseness, resulting in versatile and realistic deformations. First, we observe that the problem of bias towards low frequency always hampers supervised learning and leads to overly smooth deformations. To address this issue, we introduce a frequency-control strategy from a spectral perspective that enhances the generation of high-frequency details of the deformation. In addition, to make the network highly generalizable and able to learn various clothing deformations effectively, we propose a spectral descriptor to achieve a generalized description of the global shape information. Building on the above strategies, we develop a dynamic clothing deformation estimator that integrates graph attention mechanisms with long short-term memory. The estimator takes as input expressive features from garments and human bodies, allowing it to automatically output continuous deformations for diverse clothing types, independent of mesh topology or vertex count. Finally, we present a neural collision handling method to further enhance the realism of garments. Our experimental results demonstrate the effectiveness of our approach on a variety of free-swinging garments and its superiority over state-of-the-art methods.
Keyword ：
graph learning graph learning Clothing deformation Clothing deformation spectral analysis spectral analysis dynamics dynamics
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Li, Tianxing , Shi, Rui , Zhu, Qing et al. SwinGar: Spectrum-Inspired Neural Dynamic Deformation for Free-Swinging Garments [J]. | IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS , 2024 , 30 (10) : 6913-6927 . |
| MLA | Li, Tianxing et al. "SwinGar: Spectrum-Inspired Neural Dynamic Deformation for Free-Swinging Garments" . | IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 30 . 10 (2024) : 6913-6927 . |
| APA | Li, Tianxing , Shi, Rui , Zhu, Qing , Kanai, Takashi . SwinGar: Spectrum-Inspired Neural Dynamic Deformation for Free-Swinging Garments . | IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS , 2024 , 30 (10) , 6913-6927 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
As a novel bio-inspired vision sensor, spike cameras offer significant advantages over conventional cameras with a fixed low sampling rate, recording fast-moving scenes by firing a continuous stream of spikes. Reconstruction methods including Texture from ISI (TFI), Texture from Playback (TFP), and Texture from Adaptive threshold (TFA) produce undesirable noise or motion blur. A spiking neural model distinguishes the dynamic and static spikes before reconstruction, but the reconstruction of motion details is still unsatisfactory even with the advanced TFA method. To address this issue, we propose a coarse-to-fine high-speed motion scene reconstruction (CFSR) method with a region-adaptive-based spike distinction (RASE) framework to reconstruct the full texture of natural scenes from the spike data. We utilize the spike distribution of dynamic and static regions to propose the RASE to distinguish the spikes of different moments. After distinction, the TFI, TFP, and patch matching are exploited for image reconstruction in different regions, respectively, which does not introduce unexpected noise or motion blur. Experimental results on the PKU-SPIKE-RECON dataset demonstrate that our CFSR method outperforms the state-of-the-art approaches in terms of objective and subjective quality.
Keyword ：
coarse-to-fine coarse-to-fine image reconstruction image reconstruction region adaptive region adaptive spike camera spike camera spike distinction spike distinction
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Du, Shangdian , Qi, Na , Zhu, Qing et al. CFSR: Coarse-to-Fine High-Speed Motion Scene Reconstruction with Region-Adaptive-Based Spike Distinction [J]. | APPLIED SCIENCES-BASEL , 2023 , 13 (4) . |
| MLA | Du, Shangdian et al. "CFSR: Coarse-to-Fine High-Speed Motion Scene Reconstruction with Region-Adaptive-Based Spike Distinction" . | APPLIED SCIENCES-BASEL 13 . 4 (2023) . |
| APA | Du, Shangdian , Qi, Na , Zhu, Qing , Xu, Wei , Jin, Shuang . CFSR: Coarse-to-Fine High-Speed Motion Scene Reconstruction with Region-Adaptive-Based Spike Distinction . | APPLIED SCIENCES-BASEL , 2023 , 13 (4) . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Featured Application Cerebrovascular. To develop a precise semantic segmentation method with an emphasis on the edges for automated segmentation of the arterial vessel wall and plaque based on the convolutional neural network (CNN) in order to facilitate the quantitative assessment of plaque in patients with ischemic stroke. A total of 124 subjects' MR vessel wall images were used to train, validate, and test the model using deep learning. An end-to-end architecture network that can emphasize the edge information, namely the Edge Vessel Segmentation Network (EVSegNet) for automated segmentation of the arterial vessel wall, is proposed. The EVSegNet network consists of two workflows: one is implemented to achieve finely and multiscale segmentation by combining Dense Upsampling Convolution (DUC) and Hybrid Dilated Convolution (HDC) with different dilation rates modules, and the other utilizes edge information and is fused with another workflow to finally segment the vessel wall. The proposed network demonstrates robust segmentation of the vessel wall and better performance with a Dice (%) of 87.5, compared with the traditional U-net that has a Dice (%) of 81.0 and other U-net-based models on the test dataset. The results suggest that the proposed segmentation method with an emphasis on the edges improves segmentation accuracy effectively and will facilitate the quantitative assessment of atherosclerosis.
Keyword ：
MR vessel wall image MR vessel wall image automated segmentation automated segmentation edge information edge information
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xu, Wenjing , Zhu, Qing . A Semantic Segmentation Method with Emphasis on the Edges for Automatic Vessel Wall Analysis [J]. | APPLIED SCIENCES-BASEL , 2022 , 12 (14) . |
| MLA | Xu, Wenjing et al. "A Semantic Segmentation Method with Emphasis on the Edges for Automatic Vessel Wall Analysis" . | APPLIED SCIENCES-BASEL 12 . 14 (2022) . |
| APA | Xu, Wenjing , Zhu, Qing . A Semantic Segmentation Method with Emphasis on the Edges for Automatic Vessel Wall Analysis . | APPLIED SCIENCES-BASEL , 2022 , 12 (14) . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Point cloud data has been extensively used in all kinds of applications, such as autonomous driving and augmented reality, since it can provide detailed and realistic depictions of 3D scenes or objects. Meanwhile, 3D point clouds generally occupy a large amounts of storage space that is a big burden for efficient communication. However, it is difficult to efficiently compress such sparse, disordered, nonuniform and high dimensional data. Therefore, this work proposes a novel deep learning framework for point cloud geometric compression based on an autoencoder architecture. Specifically, a multi-layer residual module is designed on a sparse convolution-based auto-encoders that progressively downsamps the input point clouds and reconstructs the point clouds in a hierarchically way. It effectively constrains the accuracy of the sampling process at the encoder side, which significantly preserves the feature information with the decreasing of data volume. Compared with the state-of-the-art geometry-based point cloud compression (G-PCC) schemes, our approach obtains more than 70%-90% BD-Rate gain on object point cloud dataset, and achieves a better point cloud reconstruction quality.
Keyword ：
progressive sampling progressive sampling point cloud geometry compression point cloud geometry compression multi-layer residual module multi-layer residual module
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yu, Jiawen , Sun, Longhua , Wang, Jin et al. A Multi-layer Residual Architecture for Point Cloud Geometry Compression [J]. | 2022 INTERNATIONAL CONFERENCE ON VIRTUAL REALITY, HUMAN-COMPUTER INTERACTION AND ARTIFICIAL INTELLIGENCE, VRHCIAI , 2022 : 95-99 . |
| MLA | Yu, Jiawen et al. "A Multi-layer Residual Architecture for Point Cloud Geometry Compression" . | 2022 INTERNATIONAL CONFERENCE ON VIRTUAL REALITY, HUMAN-COMPUTER INTERACTION AND ARTIFICIAL INTELLIGENCE, VRHCIAI (2022) : 95-99 . |
| APA | Yu, Jiawen , Sun, Longhua , Wang, Jin , Zhu, Qing . A Multi-layer Residual Architecture for Point Cloud Geometry Compression . | 2022 INTERNATIONAL CONFERENCE ON VIRTUAL REALITY, HUMAN-COMPUTER INTERACTION AND ARTIFICIAL INTELLIGENCE, VRHCIAI , 2022 , 95-99 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Point cloud data are extensively used in various applications, such as autonomous driving and augmented reality since it can provide both detailed and realistic depictions of 3D scenes or objects. Meanwhile, 3D point clouds generally occupy a large amount of storage space that is a big burden for efficient communication. However, it is difficult to efficiently compress such sparse, disordered, non-uniform and high dimensional data. Therefore, this work proposes a novel deep-learning framework for point cloud geometric compression based on an autoencoder architecture. Specifically, a multi-layer residual module is designed on a sparse convolution-based autoencoders that progressively down-samples the input point clouds and reconstructs the point clouds in a hierarchically way. It effectively constrains the accuracy of the sampling process at the encoder side, which significantly preserves the feature information with a decrease in the data volume. Compared with the state-of-the-art geometry-based point cloud compression (G-PCC) schemes, our approach obtains more than 70-90% BD-Rate gain on an object point cloud dataset and achieves a better point cloud reconstruction quality. Additionally, compared to the state-of-the-art PCGCv2, we achieve an average gain of about 10% in BD-Rate.
Keyword ：
point cloud geometry compression point cloud geometry compression multi-layer residual module multi-layer residual module progressive sampling progressive sampling
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yu, Jiawen , Wang, Jin , Sun, Longhua et al. Point Cloud Geometry Compression Based on Multi-Layer Residual Structure [J]. | ENTROPY , 2022 , 24 (11) . |
| MLA | Yu, Jiawen et al. "Point Cloud Geometry Compression Based on Multi-Layer Residual Structure" . | ENTROPY 24 . 11 (2022) . |
| APA | Yu, Jiawen , Wang, Jin , Sun, Longhua , Wu, Mu-En , Zhu, Qing . Point Cloud Geometry Compression Based on Multi-Layer Residual Structure . | ENTROPY , 2022 , 24 (11) . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
针对服务计算、物联网、云计算、服务互联网、工业互联网、数字智慧服务等新兴产业对具有原始创新能力的软件设计人才需求，探讨如何围绕软件设计核心价值体系进行本科软件设计与体系结构课程内容建设及实践环节创新，提出以“知识型工程创新设计(KEID)”为核心价值的课程知识体系结构并介绍以开放式领域建模为基础的创新性实践环节设计。
Keyword ：
软件体系结构 软件体系结构 KIIC实践环节设计 KIIC实践环节设计 知识型工程创新设计(KEID) 知识型工程创新设计(KEID) 开放式领域建模 开放式领域建模
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 张建 , 刘博 , 朱青 et al. 软件设计与体系结构课程内容建设及创新探索 [J]. | 计算机教育 , 2022 , PageCount-页数: 5 (07) : 62-66 . |
| MLA | 张建 et al. "软件设计与体系结构课程内容建设及创新探索" . | 计算机教育 PageCount-页数: 5 . 07 (2022) : 62-66 . |
| APA | 张建 , 刘博 , 朱青 , 张丽 . 软件设计与体系结构课程内容建设及创新探索 . | 计算机教育 , 2022 , PageCount-页数: 5 (07) , 62-66 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
本文对数字媒体技术专业中计算机知识相关的基础课程内容进行了调整优化,并从广度、难度以及内在逻辑的合理性方面设计了课程实验,实现了在有限的课时内促进学生理解关键概念、提高动手能力,学生兴趣,培养自学能力的目标.
Keyword ：
内在逻辑 内在逻辑 实验设计 实验设计 计算机基础知识 计算机基础知识 数字媒体技术专业 数字媒体技术专业
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 张丽 , 朱青 , 张静 . 关注内在逻辑的课程实验设计 [J]. | 中国信息技术教育 , 2022 , (8) : 105-107 . |
| MLA | 张丽 et al. "关注内在逻辑的课程实验设计" . | 中国信息技术教育 8 (2022) : 105-107 . |
| APA | 张丽 , 朱青 , 张静 . 关注内在逻辑的课程实验设计 . | 中国信息技术教育 , 2022 , (8) , 105-107 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
"软件工程导论"课程在软件工程专业培养方案中的课程地位学科基础必修课,该课程作用是为软件工程专业学生正确打开软件工程领域之门,为后续的软件工程系列课程奠定基础,其课程地位非常重要.同时,在课程开展过程存在课程内容与企业需求脱节,课程枯燥,学生参与程度差等多种问题.本论文以"软件工程导论"课程教学实践为例,围绕课程目标中解决复杂问题能力指标的达成展开,提出"以学生为中心、以大赛为驱动,以集中课程设计为辅助"的实践探索模式,取得了较好的收效.
Keyword ：
大赛驱动 大赛驱动 软件工程导论 软件工程导论 能力指标达成 能力指标达成 显式指标 显式指标 隐式指标 隐式指标
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 于学军 , 张丽 , 俞敏 et al. "软件工程导论"课程能力目标达成的课堂延展模式探索 [J]. | 科教导刊-电子版（下旬） , 2022 , (3) : 123-125 . |
| MLA | 于学军 et al. ""软件工程导论"课程能力目标达成的课堂延展模式探索" . | 科教导刊-电子版（下旬） 3 (2022) : 123-125 . |
| APA | 于学军 , 张丽 , 俞敏 , 朱青 . "软件工程导论"课程能力目标达成的课堂延展模式探索 . | 科教导刊-电子版（下旬） , 2022 , (3) , 123-125 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
高校是思想教育的主战场,研究生是思想相对成熟的群体,研究生思政教育上需要投入更多在方式方法上.通过对互联网体系结构课程内容以及课程教学过程中思政元素的挖掘,实现在专业课教学中传授专业知识、提高研究生专业技能水平的同时,在民族自信心、学术规范、创新精神等几方面对学生思想进行塑型.
Keyword ：
民族自信心 民族自信心 创新精神 创新精神 学术规范 学术规范 课程思政 课程思政
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 张丽 , 朱青 . 互联网体系结构课程思政的思考 [J]. | 科教导刊-电子版（上旬） , 2022 , (3) : 42-43 . |
| MLA | 张丽 et al. "互联网体系结构课程思政的思考" . | 科教导刊-电子版（上旬） 3 (2022) : 42-43 . |
| APA | 张丽 , 朱青 . 互联网体系结构课程思政的思考 . | 科教导刊-电子版（上旬） , 2022 , (3) , 42-43 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
传统的零样本学习方法大多采用一个分离的两步管道,从预先训练的CNN模型中提取图像特征,再利用固定的图像特征来学习嵌入空间,导致零样本学习任务并不能捕捉到辅助信息中丰富的语义信息.对此,借助胶囊网络,提出一种端到端、可训练的模型.相比卷积网络,胶囊网络对物体的平移、旋转和缩放等变化表现出更强的鲁棒性.该模型赋予嵌入空间更强的泛化能力,为零样本学习提供了更多辅助线索,实验结果显示该方法优于现有的识别方法.
Keyword ：
零样本学习 零样本学习 图像分类 图像分类 胶囊网络 胶囊网络
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 徐树振 , 朱青 . 基于胶囊网络进行可区别特征学习的零样本识别方法研究 [J]. | 计算机应用与软件 , 2021 , 38 (8) : 182-186 . |
| MLA | 徐树振 et al. "基于胶囊网络进行可区别特征学习的零样本识别方法研究" . | 计算机应用与软件 38 . 8 (2021) : 182-186 . |
| APA | 徐树振 , 朱青 . 基于胶囊网络进行可区别特征学习的零样本识别方法研究 . | 计算机应用与软件 , 2021 , 38 (8) , 182-186 . |
| Export to | NoteExpress RIS BibTex |
Export
| Results： |
Selected to |
| Format： |
