检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wang, Guotao Chen, Chenglizhao Hao, Aimin Qin, Hong Fan, Deng-Ping The State Key Laboratory of Virtual Reality Technology and Systems Beihang University China The College of Computer Science and Technology China University of Petroleum China The State Key Laboratory of Virtual Reality Technology and Systems Beihang University Research Unit of Virtual Human and Virtual Surgery Chinese Academy of Medical Sciences and with Pengcheng Laboratory China The Computer Science Department Stony Brook University United States ETH Zurich Zurich Switzerland

To date, the widely adopted way to perform fixation collection in panoptic video is based on a head-mounted display (HMD), where users' fixations are collected while wearing an HMD to explore the given panoptic scene freely. However, this widely-used data collection method is insufficient for training deep models to accurately predict which regions in a given panoptic are most important when it contains intermittent salient events. The main reason is that there always exist "blind zooms" when using HMD to collect fixations since the users cannot keep spinning their heads to explore the entire panoptic scene all the time. Consequently, the collected fixations tend to be trapped in some local views, leaving the remaining areas to be the "blind zooms". Therefore, fixation data collected using HMD-based methods that accumulate local views cannot accurately represent the overall global importance - the main purpose of fixations - of complex panoptic scenes. To conquer, this paper introduces the auxiliary window with a dynamic blurring (WinDB) fixation collection approach for panoptic video, which doesn't need HMD and is able to well reflect the regional-wise importance degree. Using our WinDB approach, we have released a new PanopticVideo-300 dataset, containing 300 panoptic clips covering over 225 categories. Specifically, since using WinDB to collect fixations is blind zoom free, there exists frequent and intensive "fixation shifting" - a very special phenomenon that has long been overlooked by the previous research - in our new set. Thus, we present an effective fixation shifting network (FishNet) to conquer it. All these new fixation collection tool, dataset, and network could be very potential to open a new age for fixation-related research and applications in 360o environments. © 2023, CC BY.

关键词： Helmet mounted displays

来源：评论

学校读者我要写书评

暂无评论

Effects of virtual environment and self-representations on perception and physical performance in redirected jumping

引用

virtual reality & Intelligent Hardware 2021年第6期3卷 451-469页

作者： Yijun LI Miao WANG Derong JIN Frank STEINICKE Qinping ZHAO State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100083China Peng Cheng Laboratory Shenzhen 518055China Universiẗat Hamburg Hamburg 21071Germany

Background Redirected jumping(RDJ)allows users to explore virtual environments(VEs)naturally by scaling a small real-world jump to a larger virtual jump with virtual camera motion manipulation,thereby addressing the problem of limited physical space in VR *** RDJ studies have mainly focused on detection threshold ***,the effect VE or self representation(SR)has on the perception or performance of RDJs remains *** In this paper,we report experiments to measure the perception(detection thresholds for gains,presence,embodiment,intrinsic motivation,and cybersickness)and physical performance(heart rate intensity,preparation time,and actual jumping distance)of redirected forward jumping under six different combinations of VE(low and high visual richness)and SRs(invisible,shoes,and human-like).Results Our results indicated that the detection threshold ranges for horizontal translation gains were significantly smaller in the VE with high rather than low visual *** different SRs were applied,our results did not suggest significant differences in detection thresholds,but it did report longer actual jumping distances in the invisible body case compared with the other two *** the high visual richness VE,the preparation time for jumping with a human-like avatar was significantly longer than that with other ***,some correlations were found between perception and physical performance *** All these findings suggest that both VE and SRs influence users'perception and performance in RDJ and must be considered when designing locomotion techniques.

关键词： virtual reality virtual locomotion Redirected jumping

来源：评论

学校读者我要写书评

暂无评论

Transforming vision transformer: towards efficient multi-task asynchronous learning 24

Transforming vision transformer: towards efficient multi-tas...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Hanwen Zhong Jiaxin Chen Yutong Zhang Di Huang Yunhong Wang State Key Laboratory of Virtual Reality Technology and Systems Beihang University China and School of Computer Science and Engineering Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9798331314385

Multi-Task Learning (MTL) for vision Transformer aims at enhancing the model capability by tackling multiple tasks simultaneously. Most recent works have predominantly focused on designing Mixture-of-Experts (MoE) structures and integrating Low-Rank Adaptation (LoRA) to efficiently perform multi-task learning. However, their rigid combination hampers both the optimization of MoE and the effectiveness of reparameterization of LoRA, leading to sub-optimal performance and low inference speed. In this work, we propose a novel approach dubbed Efficient Multi-Task Learning (EMTAL) by transforming a pre-trained vision Transformer into an efficient multi-task learner during training, and reparameterizing the learned structure for efficient inference. Specifically, we firstly develop the MoEfied LoRA structure, which decomposes the pre-trained Transformer into a low-rank MoE structure and employ LoRA to fine-tune the parameters. Subsequently, we take into account the intrinsic asynchronous nature of multi-task learning and devise a learning Quality Retaining (QR) optimization mechanism, by leveraging the historical high-quality class logits to prevent a well-trained task from performance degradation. Finally, we design a router fading strategy to integrate the learned parameters into the original Transformer, archiving efficient inference. Extensive experiments on public benchmarks demonstrate the superiority of our method, compared to the state-of-the-art multi-task learning approaches. The project page is available at https://***/Yewen1486/EMTAL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Heuristic-Driven, Type-Specific Embedding in Parallel Spaces for Enhancing Knowledge Graph Reasoning

Heuristic-Driven, Type-Specific Embedding in Parallel Spaces...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yao Liu Yongfei Zhang Xin Wang Shan Yang Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang University Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Department of Computer Science and Technology Tsinghua University Beijing China

Knowledge Graph Reasoning aims to derive new insights from existing Knowledge Graphs (KGs) and address any missing or incomplete data. Existing models primarily rely on explicit information while neglecting the implicit constraints imposed by entity types on relations types. For example, when the entity type is "person-person," the relation type should be constrained to interpersonal connections like "co-worker." Based on this perspective, we introduce a priori knowledge-based approach for inferring relations types. This approach utilizes the relations type distribution across different entity types in the dataset to guide the inference process. Additionally, recognizing that mapping all different relations types to a single space can decrease inference accuracy due to the diversity of semantics, we propose a parallel spaces KG embedding model that partitions the entire KG into multiple subspaces. Each subspace is dedicated to learning information associated with a specific relation type. Experimental results on three KG reasoning benchmarks demonstrate that our model outperforms other baselines in accuracy. Importantly, our model shows significant advantages when applied to datasets with a substantial number of relations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SEMANTICALLY-GUIDED DISENTANGLED REPRESENTATION FOR ROBUST GAIT RECOGNITION

SEMANTICALLY-GUIDED DISENTANGLED REPRESENTATION FOR ROBUST G...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Chai, Tianrui Mei, Xinyu Li, Annan Wang, Yunhong State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China

ISBN: (纸本)9781665438643

Gait is an important biometric that can recognize people at a distance. Recently, Disentangled Representation Learning (DRL) has been introduced for distinguishing identity-irrelevant covariate features from identity features for better recognition performance. However, such a simple gait energy image (GEI) pairing operation inevitably brings in over-disentanglement effects that degrade the performance. To address this issue, we proposed a covariate feature control gate module that compensates for the discriminative feature loss by using additional semantic labels. Furthermore, a shared attention module, which allows the identity and covariate part to pay attention to different spatial regions, is also proposed for better spatial disentanglement. Experimental results show that our method outperforms the state-of-the-art and well-explain the mechanism of how the improvement is achieved. The code is available at https://***/ctrasd/GA-ICDNet. © 2021 IEEE

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Semantic Contrastive Bootstrapping for Single-positive Multi-label Recognition

arXiv

引用

arXiv 2023年

作者： Chen, Cheng Zhao, Yifan Li, Jia State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China School of Computer Science Peking University China

Learning multi-label image recognition with incomplete annotation is gaining popularity due to its superior performance and significant labor savings when compared to training with fully labeled datasets. Existing literature mainly focuses on label completion and co-occurrence learning while facing difficulties with the most common single-positive label manner. To tackle this problem, we present a semantic contrastive bootstrapping (Scob) approach to gradually recover the cross-object relationships by introducing class activation as semantic guidance. With this learning guidance, we then propose a recurrent semantic masked transformer to extract iconic object-level representations and delve into the contrastive learning problems on multi-label classification tasks. We further propose a bootstrapping framework in an Expectation-Maximization fashion that iteratively optimizes the network parameters and refines semantic guidance to alleviate possible disturbance caused by wrong semantic guidance. Extensive experimental results demonstrate that the proposed joint learning framework surpasses the state-of-the-art models by a large margin on four public multi-label image recognition benchmarks. Codes can be found at https://***/iCVTEAM/Scob. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling with Informative-Preserved Reconstruction and Self-Distilled Consistency

MM-3DScene: 3D Scene Understanding by Customizing Masked Mod...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Mingye Xu Mutian Xu Tong He Wanli Ouyang Yali Wang Xiaoguang Han Yu Qiao The Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Chinese Academy of Sciences Shenzhen Institute of Advanced Technology Shenzhen China University of Chinese Academy of Sciences Shanghai Artificial Intelligence Laboratory SSE CUHKSZ FNii CUHKSZ

Masked Modeling (MM) has demonstrated widespread success in various vision challenges, by reconstructing masked visual patches. Yet, applying MM for large-scale 3D scenes remains an open problem due to the data sparsity and scene complexity. The conventional random masking paradigm used in 2D images often causes a high risk of ambiguity when recovering the masked region of 3D scenes. To this end, we propose a novel informative-preserved reconstruction, which explores local statistics to discover and preserve the representative structured points, effectively enhancing the pretext masking task for 3D scene understanding. Integrated with a progressive reconstruction manner, our method can concentrate on modeling regional geometry and enjoy less ambiguity for masked reconstruction. Besides, such scenes with progressive masking ratios can also serve to self-distill their intrinsic spatial consistency, requiring to learn the consistent representations from unmasked areas. By elegantly combining informative-preserved reconstruction on masked areas and consistency self-distillation from unmasked areas, a unified framework called MM-3DScene is yielded. We conduct comprehensive experiments on a host of downstream tasks. The consistent improvement (e.g., +6.1% mAP@0.5 on object detection and +2.2% mIoU on semantic segmentation) demonstrates the superiority of our approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Image Desaturation for SDO/AIA Using Mixed Convolution Network

引用

Research in Astronomy and Astrophysics 2022年第6期22卷 91-100页

作者： Xuexin Yu Long Xu Zhixiang Ren Dong Zhao Wenqing Sun National Astronomical Observatories Chinese Academy of SciencesBeijing 100101China University of Chinese Academy of Sciences Beijing 100049China Peng Cheng National Laboratory Shenzhen 518000China National Space Science Center Chinese Academy of SciencesBeijing 100190China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100190China

The Atmospheric Imaging Assembly(AIA)onboard the Solar Dynamics Observatory(SDO)provides full-disk solar images with high temporal cadence and spatial resolution over seven extreme ultraviolet(EUV)wave ***,as violent solar flares happen,images captured in EUV wave bands may have saturation in active regions,resulting in signal *** this paper,we propose a deep learning model to restore the lost signal in saturated regions by referring to both unsaturated/normal regions within a solar image and statistical probability model of massive normal solar *** proposed model,namely mixed convolution network(MCNet),is established over conditional generative adversarial network(GAN)and the combination of partial convolution(PC)and validness migratable convolution(VMC).These two convolutions were originally proposed for image *** addition,they are implemented only on unsaturated/valid pixels,followed by certain compensation to compensate the deviation of PC/VMC relative to normal *** results demonstrate that the proposed MCNet achieves favorable desaturated results for solar images and outperforms the state-of-the-art methods both quantitatively and qualitatively.

关键词： Sun:activity Sun atmosphere-Sun chromosphere

来源：评论

学校读者我要写书评

暂无评论

How to Route CUBIC and BBR Packets in Space

How to Route CUBIC and BBR Packets in Space

引用

International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)

作者： Shuo Huang Zhiyuan Wang Wenhao Lu Kai Shen Jiayi Zhang Shan Zhang Hongbin Luo School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beijing China State Key Laboratory of Software Development Environment Beijing China

ISBN: (数字)9783903176652

ISBN: (纸本)9798331508722

Low-earth-orbit satellite constellation (e.g., Starlink) is becoming the indispensable component of future Internet. Due to the mobility nature, ground-satellite links (GSLs) and inter-satellite links (ISLs) are not as stable as the fiber links of wired Internet. Consequently, end-to-end TCP connections traversing the LEO constellation will suffer from packet loss and latency variation caused by GSL handover and ISL failure. However, typical congestion control algorithms (e.g., loss-based CUBIC and bandwidth-estimated BBR) rely on these feedbacks to detect congestion in wired Internet. This leads to performance degradation for CUBIC/BBR in LEO satellite networks. In this paper, we propose a Default-and-Backup Routing (DB-R) mechanism to enhance the performance of CUBIC/BBR in LEO satellite networks. Specifically, DB-R leverages default routing to address the packet loss caused by frequent GSL handover. Moreover, DB- R utilizes backup routing to eliminate the packet loss caused by occasional ISL failure. Overall, DB-R only incurs negligible control overhead, but can effectively improve the performance of CUBIC and BBR in LEO satellite networks. We implement DB-R in Linux kernel and evaluate its performance based on OpenSN (i.e., an open-source libarary for emulating LEO satellite networks). Results show that our DB-R mechanism can improve the average throughput of CUBIC (and BBR, respectively) by up to 37 % (and 18 %, respectively) compared with classic OSPF.

关键词： Satellites Linux Wireless networks Low earth orbit satellites Packet loss Handover Routing Throughput Internet Kernel

来源：评论

学校读者我要写书评

暂无评论

Rethinking Lightweight Salient Object Detection via Network Depth-Width Tradeoff

arXiv

引用

arXiv 2023年

作者： Li, Jia Qiao, Shengye Zhao, Zhirui Xie, Chenxi Chen, Xiaowu Xia, Changqun The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Laboratory Shenzhen518000 China

Existing salient object detection methods often adopt deeper and wider networks for better performance, resulting in heavy computational burden and slow inference speed. This inspires us to rethink saliency detection to achieve a favorable balance between efficiency and accuracy. To this end, we design a lightweight framework while maintaining satisfying competitive accuracy. Specifically, we propose a novel trilateral decoder framework by decoupling the U-shape structure into three complementary branches, which are devised to confront the dilution of semantic context, loss of spatial structure and absence of boundary detail, respectively. Along with the fusion of three branches, the coarse segmentation results are gradually refined in structure details and boundary quality. Without adding additional learnable parameters, we further propose Scale-Adaptive Pooling Module to obtain multi-scale receptive filed. In particular, on the premise of inheriting this framework, we rethink the relationship among accuracy, parameters and speed via network depth-width tradeoff. With these insightful considerations, we comprehensively design shallower and narrower models to explore the maximum potential of lightweight SOD. Our models are purposed for different application environments: 1) a tiny version CTD-S (1.7M, 125FPS) for resource constrained devices, 2) a fast version CTD-M (12.6M, 158FPS) for speed-demanding scenarios, 3) a standard version CTD-L (26.5M, 84FPS) for high-performance platforms. Extensive experiments validate the superiority of our method, which achieves better efficiency-accuracy balance across five benchmarks. Copyright © 2023, The Authors. All rights reserved.

关键词： Efficiency

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：