检索结果-内蒙古大学图书馆

Localizing object parts in 3D from a single image

Science China(Information Sciences) 2019年第7期62卷 217-219页

作者： shen YIN Bin ZHOU Mingjia YANG Yu ZHANG State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang University

Object localization in 3D from 2D images is an important computer vision problem that enables modern robotic vision systems to interact properly with the objects present in the real world. Owing to its significance, techniques for recovering the 6-DOF pose and dimensions of objects from images has received increasing attention in recent years [1–3]. However, to the best of our knowledge,the existing approaches all focus on object-level inference instead of analyzing object parts. Most of

关键词： pro Localizing object parts in 3D from a single image

来源：评论

学校读者我要写书评

暂无评论

MagicCube: A One-Handed Interaction Approach in 3D Environment on Smartphones

MagicCube: A One-Handed Interaction Approach in 3D Environme...

引用

virtual reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Mengyuan Wang Yong Hu Chuchen Li xukun shen State Key Laboratory of Virtual Reality Technology and Systems Beihang University School of New Media Art and Design Beihang University

When users have only one free hand to operate smartphones, interaction with 3D virtual environment(VE) is restricted. We propose MagicCube, a cube with 5 DOF that perfectly integrates navigation and selection in 3D VE, to address this problem. Three sets of opposing faces are assigned to feature faces with translation, rotation, and selection. Any operation can be performed by dragging the corresponding face. Further, by rotating the cube, users can choose the displayed faces and adjust their relative position according to personal preference. A comparative analysis showed that it could effectively reduce the finger's visual occlusion as well as improve the accuracy and stability of interaction operations.

关键词： Visualization Three-dimensional displays Navigation Design methodology Conferences virtual reality User interfaces

来源：评论

学校读者我要写书评

暂无评论

3D Fluid Volume Editing based on a Bidirectional Time Coupling Optimization Approach

3D Fluid Volume Editing based on a Bidirectional Time Coupli...

引用

virtual reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Xiaoying Nie Yong Hu Zhiyuan Su xukun shen State Key Laboratory of Virtual Reality Technology and Systems Beihang University School of New Media Art and Design Beihang University

We propose a novel optimization approach to locally edit a 3D fluid volume. Starting from a fluid reconstruction sequence or a fluid simulation sequence, we formulate geometric deformations as a nonlinear optimization problem to match user-specified targets. To seamlessly blending the edited 3D fluid volume into an original temporal sequence, we provide a bidirectional time coupling optimization approach. This approach takes the physical properties of the previous frame and the next frame as constraints to solve the current frame and meanwhile respect the spatial-temporal consistency of editing in various scenarios. Our results indicate the intuitiveness and efficacy of our method.

关键词： Couplings Solid modeling Fluids Three-dimensional displays Conferences virtual reality User interfaces

来源：评论

学校读者我要写书评

暂无评论

Gaze-Pinch Menu: Performing Multiple Interactions Concurrently in Mixed reality

Gaze-Pinch Menu: Performing Multiple Interactions Concurrent...

引用

virtual reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Lu Lu Pengshuai Duan xukun shen Shijin Zhang Huiyan Feng Yong Flu State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China School of New Media Art and Design Beihang University Beijing China

Performing an interaction using gaze and pinch has been certified as an efficient interactive method in Mixed reality, for such techniques can provide users concise and natural experiences. However, executing a task with individual interactions gradually is inefficient in some application scenarios. In this paper, we propose the Hand-Pinch Menu, which core concept is to reduce unnecessary operations by combining several interactions. Users can continuously perform multiple interactions on a selected object concurrently without changing gestures by using this technique. The user study results show that our Gaze-Pinch Menu can improve operational efficiency effectively.

关键词： Three-dimensional displays Conferences Mixed reality User interfaces Task analysis Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Exploring Social Interactions for Live Performance in virtual reality 20

Exploring Social Interactions for Live Performance in Virtua...

引用

SIGGRAPH Asia 2020 Posters - International Conference on Computer Graphics and Interactive Techniques, SA 2020

作者： Yan, Shuo Yan, Xuning shen, xukun School of New Media Art and Design Beihang University and State Key Laboratory of Virtual Reality Technology Systems Beihang University School of New Media Art Design Beihang University

ISBN: (纸本)9781450381130

Social interaction is important when audience are participating in a live performance. With strong immersion and high degree of freedom (DoF), virtual reality (VR) is often used to present performance events, such as virtual concert. A live performance is also a space with the potential for shared social realities, which could hardly be emulated by remote VR. This paper proposes new approaches to design social interactions that arouse social awareness for the audience in a VR performance. These interactions could be implemented in three different modes, which include both individual expression and group effect. The project brings new possibilities for future VR performance experience. © 2020 Owner/Author.

关键词： virtual reality

来源：评论

学校读者我要写书评

暂无评论

Efficient Metaballs-Based Collision Detection for VR Neurosurgery Simulation on GPU 33rd

Efficient Metaballs-Based Collision Detection for VR Neurosu...

引用

33rd International Conference on Computer Animation and Social Agents, CASA 2020

作者： shen, Yang Feng, Huiwei Su, Jian Pan, Junjun National Engineering Laboratory for Cyberlearning and Intelligent Technology Beijing Normal University Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Peng Cheng Lab Shenzhen China

ISBN: (纸本)9783030634254

This paper presents a novel hybrid model comprising both surface mesh and the metaballs which occupy organs’ interior for the soft tissue modeling. Through the utility of metaballs, we are capable of simplifying the organ interior using a set of overlapping spheres with different radii. We first develop an adaptive approach based on Voronoi Diagram for the initialization of inner metaballs. Then, we resort to global optimization and devise an electrostatic attraction technique to drive the metaballs to best fill the space inside the organ’s boundary. We simplify the surgical instrument as a collection of cylinders with different radii and orientation, and develop an adaptive collision detection method to facilitate the collision between the surgical instrument and metaballs. Our framework is built on the parallel computation architecture of CUDA, and thus can afford interactive performance on a commodity desktop. To illustrate the effectiveness, the above techniques have all been integrated into a VR-based ventriculoscopic surgery simulator. © 2020, Springer Nature Switzerland AG.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Unmanned aerial systems coordinate target allocation based on wolf behaviors

引用

Science China(Information Sciences) 2019年第1期62卷 205-207页

作者： Haibin DUAN Qing YANG Yimin DENG Pei LI Huaxin QIU Tianjie ZHANG Daifeng ZHANG Mengzhen HUO Yankai shen Bio-inspired Autonomous Flight Systems (BAFS) Research Group State Key Laboratory of Virtual Reality Technology and SystemsSchool of Automation Science and Electrical EngineeringBeihang University (BUAA)

Unmanned aerial systems (UASs), especially the cluster of UAS, are highly focused and widely used in various domains. The application of small and inexpensive UAS with a large-scale group to perform complex tasks has ... 详细信息

关键词： UAS Unmanned aerial systems coordinate target allocation based on wolf behaviors

来源：评论

学校读者我要写书评

暂无评论

Learning from future: a novel self-training framework for semantic segmentation 22

Learning from future: a novel self-training framework for se...

引用

Proceedings of the 36th International Conference on Neural Information Processing systems

作者： Ye Du Yujun shen Haochen Wang Jingjing Fei Wei Li Liwei Wu Rui Zhao Zehua Fu Qingjie Liu State Key Laboratory of Virtual Reality Technology and Systems Beihang University and Hangzhou Innovation Institute Beihang University The Chinese University of Hong Kong Institute of Automation Chinese Academy of Sciences SenseTime Research SenseTime Research and Qing Yuan Research Institute Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781713871088

Self-training has shown great potential in semi-supervised learning. Its core idea is to use the model learned on labeled data to generate pseudo-labels for unlabeled samples, and in turn teach itself. To obtain valid supervision, active attempts typically employ a momentum teacher for pseudo-label prediction yet observe the confirmation bias issue, where the incorrect predictions may provide wrong supervision signals and get accumulated in the training process. The primary cause of such a drawback is that the prevailing self-training framework acts as guiding the current state with previous knowledge, because the teacher is updated with the past student only. To alleviate this problem, we propose a novel self-training strategy, which allows the model to learn from the future. Concretely, at each training step, we first virtually optimize the student (i.e., caching the gradients without applying them to the model weights), then update the teacher with the virtual future student, and finally ask the teacher to produce pseudo-labels for the current student as the guidance. In this way, we manage to improve the quality of pseudo-labels and thus boost the performance. We also develop two variants of our future-self-training (FST) framework through peeping at the future both deeply (FST-D) and widely (FST-W). Taking the tasks of unsupervised domain adaptive semantic segmentation and semi-supervised semantic segmentation as the instances, we experimentally demonstrate the effectiveness and superiority of our approach under a wide range of settings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning from Future: A Novel Self-Training Framework for Semantic Segmentation

arXiv

引用

arXiv 2022年

作者： Du, Ye shen, Yujun Wang, Haochen Fei, Jingjing Li, Wei Wu, Liwei Zhao, Rui Fu, Zehua Liu, Qingjie State Key Laboratory of Virtual Reality Technology and Systems Beihang University China Hangzhou Innovation Institute Beihang University China The Chinese University of Hong Kong Hong Kong Institute of Automation Chinese Academy of Sciences China SenseTime Research Hong Kong Qing Yuan Research Institute Shanghai Jiao Tong University China

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Drone Video Object Detection using Convolutional Neural Networks with Time Domain Motion Features

Drone Video Object Detection using Convolutional Neural Netw...

引用

IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)

作者： Yugui Zhang Liuqing shen Xiaoyan Wang Hai-Miao Hu Beijing Key Laboratory of Digital Media School of Computer Science and Engineering State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China

ISBN: (数字)9781728142722

ISBN: (纸本)9781728142739

The drone video objection detection is challenging owing to the appearance deterioration, object occlusion and motion blur in video frames, which are caused by the object motion, the camera motion, and the mixture of the object motion and the camera motion in the drone video. One of the typical solutions is to use Convolutional Neural Networks (CNNs) to train detection model by taking single frame as input. The state-of-the-art method only uses the spatial feature of the single frame in the video, but makes no use of the motion features in the time domain. In this paper, we propose a method for detecting drone video object by using convolutional neural networks in combination with time domain motion features. The proposed method includes the steps of firstly extracting the motion information between the two neighbor frames, and then combining the extracted motion information with the baseline network. In the VisDrone2019 dataset, our proposed method is shown to be effective in detecting the objects, especially in significantly reducing the occurrence of the false and missed detection of objects.

关键词： Feature extraction Drones Object detection Time-domain analysis Convolutional neural networks Data mining Cameras

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：