检索结果-内蒙古大学图书馆

2015 122nd ASEE Annual Conference and Exposition

作者： McCrae, Eric Scott Fernandez, Eugenia Indiana University Purdue University Indianapolis United States Blue Octopus Printing Company United States Computer and Information Technology Department of Computer Information and Graphics Technology Purdue School of Engineering and Technology United States

The retention of students is a goal that all universities strive to achieve. With more and more emphasis placed on degree completion, retaining students becomes even more important. University faculty and staff continually try to identify what possible factors affect a student's decision to remain in their chosen field of study. Faculty in the computer graphics technology (CGT) program are concerned with what factors, if any, affect the persistence of students in the CGT program. The goal of this study was to determine if personal factors such as gender and being a first-generation student and/or academic factors such as admission status, semester course load, and academic grades are related to the first-year persistence of CGT students. Results indicate that first semester performance is a significant indicator of persistence. Gender, first generation student, and admission status were not found to be significant indicators. This points out the importance of efforts focused on students in their first semester of college. © American Society for Engineering Education, 2015.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Events and findings of the Purdue University Calumet computer Information technology & graphics (CIT & G) department teaching partnership with the College of Software Engineering of Southeast University in Nanjing China 09

Events and findings of the Purdue University Calumet Compute...

引用

10th ACM Special Interest Group for Information technology Education, SIGITE 2009

作者： Winer, Charles Wu, Hanqian Department of Computer Information Technology and Graphics Purdue University Calumet Hammond IN United States College of Software Engineering Southeast University Nanjing China

ISBN: (纸本)9781605587653

In this poster session we are reporting on the results of two, three-week summer graduate teaching experiences that took place in Nanjing, China over a two-year period. A faculty exchange program was entered into between Southeast University of Nanjing China and Purdue University Calumet of Hammond, Indiana, USA. One of the goals of the exchange program was to expose Chinese students to the instructional methods employed by United States Universities. By understanding the cultural differences and utilizing various teaching methodologies employed by American teachers, the faculty and students involved in these three-week classroom intensive training courses were able to adapt and successfully complete the graduate level material that was presented.

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

Using Immersive Virtual Environments for Intercultural Learning Experiences 3

Using Immersive Virtual Environments for Intercultural Learn...

引用

3rd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： Giri, Nandhini Purdue University Department of Computer Graphics Technology West LafayetteIN United States

ISBN: (纸本)9798331515911

This case study paper presents results from a pilot study to test the use of immersive virtual environments as a pre-departure training module in study abroad programs for intercultural learning experiences. Insights from the pilot study are used in developing a scenario-based immersive pre-departure training module for further testing and refinement. Study abroad programs introduce students to novel cultural experiences that lead to enriched learning experiences, friendships, and a lifetime of memories. Our study presents insights on the current student experiences in these programs and how immersive technologies can enhance their experiences through prior virtual cultural exposure and interactions. For the pilot study, six students from a computer graphics technology program who had previously enrolled in study abroad programs were recruited. Participants were guided through an exploratory tour of popular locations in Google earth VR. Once participants got comfortable using the VR headset and controller, they were asked to explore their prior study abroad destination and share their experiences in those foreign destinations. The VR session lasted for roughly 20 minutes followed by filling out a post-session questionnaire. The insights gained through this pilot study show that 1. Participants appreciated the visual immersion of the VR experience. However, participants preferred real-life experiences over virtual ones. They did see the VR module as preparation for real-world cultural exploration. 2. There was a lack of cultural interaction in the VR space. Participants valued experiences that help them better understand differences in the way of life and values of people, more than just viewing eye-catching monuments. These insights informed the design of a scenario-based immersive pre-departure training module in VR for students to explore virtual scenarios and encounters with cultural ambassadors in the foreign destination. © 2025 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

SAda-Net: A Self-supervised Adaptive Stereo Estimation CNN For Remote Sensing Image Data 27th

SAda-Net: A Self-supervised Adaptive Stereo Estimation CNN F...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Hirner, Dominik Fraundorfer, Friedrich Institute of Computer Graphics and Vision Graz University of Technology Graz Austria Cologne Germany

ISBN: (纸本)9783031781919

Stereo estimation has made many advancements in recent years with the introduction of deep-learning. However the traditional supervised approach to deep-learning requires the creation of accurate and plentiful ground-truth data, which is expensive to create and not available in many situations. This is especially true for remote sensing applications, where there is an excess of available data without proper ground truth. To tackle this problem, we propose a self-supervised CNN with self-improving adaptive abilities. In the first iteration, the created disparity map is inaccurate and noisy. Leveraging the left-right consistency check, we get a sparse but more accurate disparity map which is used as an initial pseudo ground-truth. This pseudo ground-truth is then adapted and updated after every epoch in the training step of the network. We use the sum of inconsistent points in order to track the network convergence. The code for our method will be made available after acceptance at https://***/thedodo/SAda-Net. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

DEMIS: Electron Microscopy Image Stitching Using Deep Learning Features and Global Optimisation

DEMIS: Electron Microscopy Image Stitching Using Deep Learni...

引用

18th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2025

作者： Šilling, Petr Španěl, Michal Department of Computer Graphics and Multimedia Brno University of Technology Brno Czech Republic

Accurate stitching of overlapping image tiles is essential for reconstructing large-scale Electron Microscopy (EM) images during Whole Slide Imaging. Current stitching approaches rely on handcrafted features and translation-only global alignment based on Minimum Spanning Tree (MST) construction. This results in sub optimal global alignment since it neglects rotational errors and works only with transformations estimated from pairwise feature matches, discarding valuable information tied to individual features. Moreover, hand crafted features may have trouble with repetitive textures. Motivated by the limitations of current methods and recent advancements in deep learning, we propose DEMIS, a novel EM image stitching method. DEMIS uses Local Feature TRansformer (LoFTR) for image matching, and optimises translational and rotational pa rameters directly at the level of individual features. For evaluation and training, we create EM424, a synthetic dataset generated by splitting high-resolution EM images into arrays of overlapping image tiles. Furthermore, to enable evaluation on unannotated real-world data, we design a no-reference stitching quality metric based on optical flow. Experiments that use the new metric show that DEMIS can improve the average results from 32.11 to 2.28 compared to current stitching techniques (a 1408% improvement). Code is available at: https://***/PSilling/demis. © 2025 by SCITEPRESS– Science and technology Publications, Lda.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Implementation of computer Integrated Print Manufacturing (CIPM) in the graphics technology Curriculum (GTC)

Implementation of Computer Integrated Print Manufacturing (C...

引用

65th Annual Technical Conference of the Technical Association of the Graphic Arts, TAGA: Disseminating Graphic Arts Research Internationally since 1948

作者： Poku, Nana Dharavath, H. Naik Joshi, Nilesh N. Department of Computer Electronics and Graphics Technology Central Connecticut State University New Britain CT 06050 United States Department of Applied Engineering and Technology Morehead State University Morehead KY 40351 United States

ISBN: (纸本)9781935185055

This paper discusses the impact of computer Integrated Manufacturing (CIM) principles on the U.S. printing industry and a demonstration of its applications in the graphics technology course curriculum in U.S. schools. Implementation of CIM-based print production technologies in graphics technology curriculum is important in order to prepare future graduates of these programs for jobs in a constantly evolving printing industry. The paper covers technologies such as network digital infrastructure and JDF enabled workflow and their inclusion in graphics technology educational laboratories. A case study is provided on the ongoing implementation of JDF, DAM, PPF, CAD, MIS, CMW, and CTP technologies in the graphics technology laboratory at the Central Connecticut State University. The goal is to provide a comprehensive discussion on the inclusion of various CIPM (computer Integrated Print Manufacturing) lab modules in the graphics technology curriculum, related digital printing devices, and an example JDF enabled workflow. The paper will be of interest to educators in graphics technology programs who are planning to introduce CIPM in their laboratories.

关键词： computer integrated manufacturing

来源：评论

学校读者我要写书评

暂无评论

Combining Stable Diffusion and Object Detection for Semi-automatic Environment Decoration 41st

Combining Stable Diffusion and Object Detection for Semi-a...

引用

41st computer graphics International Conference, CGI 2024

作者： Drescher, Philipp Ruprecht, Irena Settgast, Volker Computer Graphics and Knowledge Visualization Graz University of Technology Graz Austria Fraunhofer Austria Research GmbH Graz Austria

ISBN: (纸本)9783031820236

Enhancing immersive environments in an efficient way is essential across various industries. However, the task of selecting and placing suitable objects to decorate 3D scenes often requires a substantial investment of time and expertise. We present a novel semi-automatic approach to accelerate this process by fusing state-of-the-art generative text-to-image models with object detection. We use a rendering of a plain 3D scene as input for Stable Diffusion and generate an image depicting a decorated version. With object detection, we identify the location, size and class of decorative elements in the generated image. Based on this information, we populate the original 3D scene with matching assets from a database. Our results demonstrate the capabilities of our proposed approach in enhancing 3D scenes through the incorporation of decorative models across different scenarios. We show that our method seamlessly integrates into existing 3D content creation tools highlighting its applicability within established workflows. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Architectural design

来源：评论

学校读者我要写书评

暂无评论

Perceptions of AI in Animation Production 14th

Perceptions of AI in Animation Production

引用

14th International Conference on Artificial Intelligence in Music, Sound, Art and Design, EvoMUSART 2025, held as part of EvoStar 2025

作者： Hu, Dalong Choi, Minsoo Giri, Nandhini Mousas, Christos Adamo-Villani, Nicoletta Department of Computer Graphics Technology Purdue University West LafayetteIN47907 United States

ISBN: (纸本)9783031901669

We explored how people perceived animations created by artificial intelligence (AI)-driven motion capture, manual keyframe technique, and AI-driven motion capture with manual cleanup methods. We presented our participants with short, full-body animation clips created using the three methods. Participants rated the appeal and naturalness of the animations, and we asked them to discern the creation method. Results revealed differences in perceived appeal and naturalness between manually created animations and those generated through AI-based methods, with manual animations consistently rated higher in appeal and naturalness. However, participants could not discern creation methods regardless of animation experience level, demonstrating an accuracy equivalent to random guessing. The qualitative analysis highlighted diverse perspectives with negative and positive views on AI use, with the most mentioned theme being the importance of quality regardless of creation method. The overwhelming majority of participants asserted that the degree of automatization would influence participants’ perceived value and effort put into an animation. Still, this group did not show divergent ratings, nor did it affect their overall agreeableness towards using AI in creative fields. This study contributes insights into the intersection of animation and AI, informing creators about the effect of different creation methods on audience perceptions. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Forming

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of virtual reality instructional tools for 3D printing processes in digital manufacturing

引用

Journal of Intelligent Manufacturing and Special Equipment 2025年第1期6卷 1-25页

作者： Daniel Cubillos Magesh Chandramouli Computer Graphics Technology Purdue University Northwest Hammond Indiana USA

Purpose In order to allow easy replication of this study, industry standard software that is easily attainable was used. Most of the programs used are free to download, and the ones that are not are available, students can still obtain them through their university or free download options for enrolled university students. There is also a large online community for new users to learn how to use the programs through online tutorials, message boards and free instructional material provided by the developers. As this paper expands on the work created during part 1, the models and information gathered for SLA, SLS and FDM processes were modified and updated in order to be used for the second phase. The models were created using 3ds Max, an industry standard 3D modeling program created by Autodesk Media and entertainment. All the models, textures and animations were created using 3ds Max. While the program is not free, Autodesk does allow students to download the program for free as long as they are enrolled in an accredited university. It is common for universities to get Autodesk licensing for computer labs if they have a technology program, making it possible for students to use the program through the university. Design/methodology/approach The VR system chosen was the Dell Visor: it offered the best combination of software support through SteamVR and Unity compatibility, low cost compared to other currently available VR systems, along with hardware and software requirements that could be met relatively easily (Chandramouli et al., 2018; Chandramouli et al., 2014a). Dell Visor requires 1 HDMI port and 1 USB 3.0 port to connect the headset to the computer, and can work with laptops. Dell Visor uses two hand controllers for movement tracking, Bluetooth connection is used to connect the hand controllers to the headset and computer in order to provide freedom of movement. This small number of ports and connecting wires required for the head set allows easy set up a

关键词： MOOC Visualization 3D printing Virtual reality Digital manufacturing

来源：评论

学校读者我要写书评

暂无评论

Swin3D: A pretrained transformer backbone for 3D indoor scene understanding

引用

Computational Visual Media 2025年第1期11卷 83-101页

作者： Yu-Qi Yang Yu-Xiao Guo Jian-Yu Xiong Yang Liu Hao Pan Peng-Shuai Wang Xin Tong Baining Guo Institute for Advanced Study Tsinghua UniversityBeijing 100084China Tsinghua Shenzhen International Graduate School Tsinghua UniversityShenzhen 518055China Internet Graphics Group Microsoft Research AsiaBeijing 100080China Wangxuan Institute of Computer Technology Peking UniversityBeijing 100080China

The use of pretrained backbones with finetuning has shown success for 2D vision and natural language processing tasks,with advantages over taskspecific *** this paper,we introduce a pretrained 3D backbone,called Swin3D,for 3D indoor scene *** designed a 3D Swin Transformer as our backbone network,which enables efficient selfattention on sparse voxels with linear memory complexity,making the backbone scalable to large models and *** also introduce a generalized contextual relative positional embedding scheme to capture various irregularities of point signals for improved network *** pretrained a large Swin3D model on a synthetic Structured3D dataset,which is an order of magnitude larger than the ScanNet *** model pretrained on the synthetic dataset not only generalizes well to downstream segmentation and detection on real 3D point datasets but also outperforms state-of-the-art methods on downstream tasks with+2.3 mIoU and+2.2 mIoU on S3DIS Area5 and 6-fold semantic segmentation,respectively,+1.8 mIoU on ScanNet segmentation(val),+1.9 mAP@0.5 on ScanNet detection,and+8.1 mAP@0.5 on S3DIS detection.A series of extensive ablation studies further validated the scalability,generality,and superior performance enabled by our approach.

关键词： 3D pretraining ponitcloud analysis trans-former backbone Swin Transformer 3D semantic segmentation 3D object detection

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：