检索结果-内蒙古大学图书馆

International Conference on Computer Vision (ICCV)

作者： Jinqing Zhang Yanan Zhang Qingjie Liu Yunhong Wang State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Zhongguancun Laboratory Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China

Recently, the pure camera-based Bird’s-Eye-View (BEV) perception provides a feasible solution for economical autonomous driving. However, the existing BEV-based multiview 3D detectors generally transform all image features into BEV features, without considering the problem that the large proportion of background information may submerge the object information. In this paper, we propose Semantic-Aware BEV Pooling (SA-BEVPool), which can filter out background information according to the semantic segmentation of image features and transform image features into semantic-aware BEV features. Accordingly, we propose BEV-Paste, an effective data augmentation strategy that closely matches with semantic-aware BEV feature. In addition, we design a Multi-Scale Cross-Task (MSCT) head, which combines task-specific and cross-task information to predict depth distribution and semantic segmentation more accurately, further improving the quality of semantic-aware BEV feature. Finally, we integrate the above modules into a novel multi-view 3D object detection framework, namely SA-BEV Experiments on nuScenes show that SA-BEV achieves state-of-the-art performance. Code has been available at https://***/mengtan00/***.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multi-head Convolution Network with Attention Consistency for Facial Expression Recognition

A Multi-head Convolution Network with Attention Consistency ...

引用

第42届中国控制会议

作者： Wenkang Liu Mingyi Sun Yang Li the Department of Automation Science and Electrical Engineering Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beihang University Advanced Institute of Information Technology Peking University

In recent years,the demand for facial expression recognition applications has increased rapidly,and its research has received extensive attention from ***,the current recognition methods based on deep learning ignore the idea of multiple head attention and semantic consistency,resulting in the model only paying attention to the local area of the feature *** addition,the model's inconsistent attention to the images before and after the flip,resulting the poor robustness,poor interpretation,and other shortcomings in the *** address the above problems,we propose an Affinity Separation Loss(ASLoss),which improves the separability of samples through ***,a Separate Multi-head Attention block(SMA),and a Zonal Loss(ZLoss) are also designed to decentralize the model's *** results demonstrate that our proposed MACNet method achieves competitive recognition performance on two public datasets RAF-DB and FERPlus.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-view Semantic Information Guidance for Light Field Image Segmentation

Multi-view Semantic Information Guidance for Light Field Ima...

引用

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Li, Yiming Cong, Ruixuan Wang, Sizhe Zhao, Mingyuan Zhang, Yang Li, Fangping Sheng, Hao Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang Hangzhou Innovation Institute Yuhang Xixi Octagon City Hangzhou310023 China Beijing University of Chemical Technology College of Information Science and Technology Beijing100029 China Macao Polytechnic University Faculty of Applied Sciences 999078 China

ISBN: (纸本)9798350302493

One of the great important fields of computer vision is semantic segmentation. As for single image semantic segmentation, due to limited available information, it appears poor performance when the occlusion and similar color interference occur, and has difficulty exploiting the rich scene information. In comparison, the special micro-len array structure of light field camera can record multi-view information of the scene, which provides us with a new solution to solve this issue. In this paper, we propose a multi-view semantic information guidance network (MSIGNet) for light field semantic segmentation. It can effectively utilize semantic information from multi-view images to guide pixel feature of center view image. First, we extract feature of each view image and further obtain semantic probability. Then all probabilities are aggregated through a self-adaptive multi-view probability fusion module. Last, the resulting coarse fusion representation interacts with center view feature to obtain the refined segmentation result. The proposed method shows excellent performance on both real-world and synthetic light field datasets. © 2023 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

3D Face Reconstruction With Geometry Details From a Single Color Image Under Occluded Scenes

arXiv

引用

arXiv 2024年

作者： Zhao, Dapeng Qi, Yue State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Peng Cheng Laboratory Shenzhen China Qingdao Research Institute of Beihang University Qingdao China

3D face reconstruction technology aims to generate a face stereo model naturally and realistically. Previous deep face reconstruction approaches are typically designed to generate convincing textures and cannot generalize well to multiple occluded scenarios simultaneously. By introducing bump mapping, we successfully added mid-level details to coarse 3D faces. More innovatively, our method takes into account occlusion scenarios. Thus on top of common 3D face reconstruction approaches, we in this paper propose a unified framework to handle multiple types of obstruction simultaneously (e.g., hair, palms and glasses et al.).Extensive experiments and comparisons demonstrate that our method can generate high-quality reconstruction results with geometry details from captured facial images under occluded scenes. Copyright © 2024, The Authors. All rights reserved.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Multi-DOF Robot System Based on LightGBM-Driven EEG Decoding Model for BCI Human-machine Interaction

A Multi-DOF Robot System Based on LightGBM-Driven EEG Decodi...

引用

第42届中国控制会议

作者： Weidong Yan Zhaoliang Xu Yang Li the Department of Automation Science and Electrical Engineering Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beihang University Advanced Institute of Information Technology Peking University

In this study,a multi-degree-of-freedom(Multi-DOF) robot(MDR) system based on a LightGBM-driven electroencephalogram(EEG) decoding model is designed and developed to assist subjects with hand motor dysfunction in their daily activities and *** system mainly consists of a motor imagery electroencephalogram(MI-EEG)evoking layer,an intention decoding layer,and an interaction executive *** MI-EEG evoking layer initially displays a virtual reality(VR) motion imagination scenario,instructing the subjects to imagine a real hand gripping movement,simultaneously collecting the electrical EEG signals and preprocessing the EEG ***,in the intention decoding layer,a network combining temporal-spectral feature fusion and LightGBM(TSFF-LightGBM) for MI-BCI classification is used to more effectively boost brain decoding accuracy and decrease decoding ***,in the interaction executive layer,the Multi-DOF wearable robot is developed to offer hand grasp motion kinesthetic feedback and visual feedback synced with *** following are the key benefits of the proposed MDR system:(1) We propose a new lightweight network structure more suitable for brain computer interface(BCI) interaction systems,achieving more accurate decoding and shorter identification time in different data sets,which helps to improve the practicability of the system and promote the practical clinical application of BCI rehabilitation technology.(2) We integrate BCI,VR,a wearable Multi-DOF robot,motion kinesthetic feedback,and visual feedback to improve human-machine *** to the most recent investigations,the average accuracy of the MDR system on the publicly accessible datasets BCIIV 2a and HGD reached 75.89% and 93.53%,respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LFNAT 2023 Challenge on Light Field Depth Estimation: Methods and Results

LFNAT 2023 Challenge on Light Field Depth Estimation: Method...

引用

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Hao Sheng Yebin Liu Jingyi Yu Gaochang Wu Wei Xiong Ruixuan Cong Rongshan Chen Longzhao Guo Yanlin Xie Shuo Zhang Song Chang Youfang Lin Wentao Chao Xuechun Wang Guanghui Wang Fuqing Duan Tun Wang Da Yang Zhenglong Cui Sizhe Wang Mingyuan Zhao Qiong Wang Qianyu Chen Zhengyu Liang Yingqian Wang Jungang Yang Xueting Yang Junli Deng LFNAT 2023 Challenge State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University and Beihang Hangzhou Innovation Institute Yuhang

This paper reviews the 1st LFNAT challenge on light field depth estimation, which aims at predicting disparity information of central view image in a light field (i.e., pixel offset between central view image and adjacent view image). Compared to multi-view stereo matching, light field depth estimation emphasizes efficient utilization of the 2D angular information from multiple regularly varying views. This challenge specifies UrbanLF [20] light field dataset as the sole data source. There are two phases in total: submission phase and final evaluation phase, in which 75 registered participants successfully submit their predicted results in the first phase and 7 eligible teams compete in the second phase. The performance of all submissions is carefully reviewed and shown in this paper as a new standard for the current state-of-the-art in light field depth estimation. Moreover, the implementation details of these methods are also provided to stimulate related advanced research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GooDFlight: Goal-Oriented Diffusion Model for Flight Trajectory Prediction

引用

IEEE Transactions on Aerospace and Electronic systems 2025年

作者： Yang, Songru Liu, Liqin Chen, Bowen Cheng, Shaoyuan Shi, Zhenwei Zou, Zhengxia Beihang University Department of Aerospace Intelligent Science and Technology School of Astronautics China Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beijing100191 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China Beijing Institute of Space Mechanics and Electricity Beijing100076 China

Flight trajectory prediction is an essential task in the air traffic control field. Previous approaches to this problem usually follow a single-stage or short-term intention-guided prediction paradigm, which suffers from problems such as insufficient trajectory prediction diversity, limited accuracy and interpretability. Different from existing paradigms, in this paper, we present GooDFlight - A Goal-oriented Diffusion Model for Flight trajectory prediction. GooDFlight is a long-term intention-guided, diversity-emphasizing framework that decouples the flight trajectory prediction process into two stages: goal estimation and trajectory prediction. In the first stage, we propose a One-then-all goal estimation method to sufficiently cover the macro-uncertainty in flight patterns and then tailor the interaction-aware joint goal distribution, which extends the flight intention from a single, deterministic ground truth to the empirical intention distribution from the similar experience. In the second stage, we employ a transformer-based diffusion model to generate stochastic flight trajectories conditioned on the intention estimations, modeling the micro-uncertainty in flight operations under each pattern estimated in stage one. In terms of evaluation metrics, existing metrics have difficulties in accurately reflecting the model's ability to handle the natural uncertainty of trajectories. We further propose a simple yet effective Global-local endpoints Variance (GLeV) metric for evaluating the diversity of predicted trajectories under social acceptance. Our proposed method is validated in-depth on TrajAir, a large-scale dataset collected from the real-world air traffic control environment at the Pittsburgh-Butler Regional Airport, a non-towered general aviation airport. The experimental results demonstrate that the proposed method significantly outperforms other methods in terms of both accuracy and diversity with superior interpretability. © 1965-2011 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

A Multilayer Component Pane 3D Layout Frame Design for Responsive Websites

A Multilayer Component Pane 3D Layout Frame Design for Respo...

引用

IEEE International Symposium on Mixed and Augmented reality Workshops (ISMARW)

作者： Guohui Xu Shan Wang Yong Hu Xukun Shen School of New Media Art and Design Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beihang University Yunnan Innovation Institute of Beihang University

With a virtual reality (VR) head-mounted display (HMD), users can easily achieve immersive browsing. However, popular VR browsers use a virtual floating screen for web presentations, which severely limits the user experience. In this paper, we propose a responsive website based on Web VR and a 3D UI layout framework equipped with VR device features. The framework consists of two parts: Main Content and 3D Navigation. To test the usability of the framework, we designed an experimental prototype and conducted user tests with 24 participants. The experiments show that the framework can effectively improve the quality of the user experience when browsing the web in a virtual reality environment. The research shows the possible design direction of the user interface for presenting web pages in the future virtual environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring the Display Patterns of Object-Centered User Interface in Head-Worn Mixed reality Environment

Exploring the Display Patterns of Object-Centered User Inter...

引用

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

作者： Yihan Li Yong Hu Xukun Shen School of New Media Art and Design Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beihang University Yunnan Innovation Institute of Beihang University

Object-centered user interface (UI), which UI displayed around real-world objects provides convenience for users to interact with real objects in head-worn Mixed reality (MR) environment. However, it remains unclear how to design the object-centered UI to reduce the interference of always displayed UI. In this research, we designed two display patterns of object-centered UI and compared them with the basic object-centered UI without any display patterns. Our results demonstrate the trade-offs among the three UIs and collect user preference. Both display patterns can provide better support for users while reducing the occlusion and interference of the UI.

关键词： Three-dimensional displays Conferences Mixed reality virtual reality Interference User interfaces

来源：评论

学校读者我要写书评

暂无评论

ActiveDC: Distribution Calibration for Active Finetuning

arXiv

引用

arXiv 2023年

作者： Xu, Wenshuai Hu, Zhenghui Lu, Yu Meng, Jinzhou Liu, Qingjie Wang, Yunhong School of Software Beihang University China Hangzhou Innovation Institute Beihang University China State Key Laboratory of Virtual Reality Technology and Systems Beihang University China

The pretraining-finetuning paradigm has gained popularity in various computer vision tasks. In this paradigm, the emergence of active finetuning arises due to the abundance of large-scale data and costly annotation requirements. Active finetuning involves selecting a subset of data from an unlabeled pool for annotation, facilitating subsequent finetuning. However, the use of a limited number of training samples can lead to a biased distribution, potentially resulting in model overfitting. In this paper, we propose a new method called ActiveDC for the active finetuning tasks. Firstly, we select samples for annotation by optimizing the distribution similarity between the subset to be selected and the entire unlabeled pool in continuous space. Secondly, we calibrate the distribution of the selected samples by exploiting implicit category information in the unlabeled pool. The feature visualization provides an intuitive sense of the effectiveness of our method to distribution calibration. We conducted extensive experiments on three image classification datasets with different sampling ratios. The results indicate that ActiveDC consistently outperforms the baseline performance in all image classification tasks. The improvement is particularly significant when the sampling ratio is low, with performance gains of up to 10%. Our code will be publicly available. Copyright © 2023, The Authors. All rights reserved.

关键词： Image classification

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：