检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wang, Yin Li, Mu Liu, Jiapeng Leng, Zhiying Li, Frederick W.B. Zhang, Ziyao Liang, Xiaohui B. State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Department of Computer Science University of Durham United Kingdom Zhongguancun Laboratory Beijing China

We address the challenging problem of fine-grained text-driven human motion generation. Existing works generate imprecise motions that fail to accurately capture relationships specified in text due to: (1) lack of effective text parsing for detailed semantic cues regarding body parts, (2) not fully modeling linguistic structures between words to comprehend text comprehensively. To tackle these limitations, we propose a novel fine-grained framework Fg-T2M++ that consists of: (1) an LLMs semantic parsing module to extract body part descriptions and semantics from text, (2) a hyperbolic text representation module to encode relational information between text units by embedding the syntactic dependency graph into hyperbolic space, and (3) a multi-modal fusion module to hierarchically fuse text and motion features. Extensive experiments on HumanML3D and KIT-ML datasets demonstrate that Fg-T2M++ outperforms SOTA methods, validating its ability to accurately generate motions adhering to comprehensive text semantics. Copyright © 2025, 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

key Mention Pairs Guided Document-Level Relation Extraction 29

Key Mention Pairs Guided Document-Level Relation Extraction

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Jiang, Feng Niu, Jianwei Mo, Shasha Fan, Shengda State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China School of Cyber Science and Technology Beihang University Beijing100191 China

Document-level Relation Extraction (DocRE) aims at extracting relations between entities in a given document. Since different mention pairs may express different relations or even no relation, it is crucial to identify key mention pairs responsible for the entity-level relation labels. However, most recent studies treat different mentions equally while predicting the relations between entities, leading to sub-optimal performance. To this end, we propose a novel DocRE model called key Mention pairs Guided Relation Extractor (KMGRE) to directly model mention-level relations, containing two modules: a mention-level relation extractor and a key instance classifier. These two modules could be iteratively optimized with an EM-based algorithm to enhance each other. We also propose a new method to solve the multi-label problem in optimizing the mention-level relation extractor. Experimental results on two public DocRE datasets demonstrate that the proposed model is effective and outperforms previous state-of-the-art models. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Object-level Hyperspectral Target Detection Based on Spectral-Spatial Features Integrated YOLOv4-Tiny Network 2022

Object-level Hyperspectral Target Detection Based on Spectra...

引用

4th International Conference on Image, Video and Signal Processing, IVSP 2022

作者： Nie, Jinyan Guo, Jian Xu, Qizhi State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China School of Computer Science and Technology Beijing Institute of Technology Beijing China School of Mechatronical Engineering Beijing Institute of Technology Beijing China

ISBN: (纸本)9781450387415

The spectral resolution and spatial resolution of hyperspectral remote sensing images are mutually limited. To keep the same signal-to-noise ratio, the spatial resolution will decrease when the spectral resolution improves. The targets in low-resolution hyperspectral image, such as airplanes, cars and ships, appear as several pixels or sub-pixels. Current hyperspectral target detection methods mainly focus on pixel-level targets, which process spectral information and simple neighbourhood-pixel-related information in a pixel-by-pixel detection strategy. The contribution of spatial features is limited, and it takes a long time to train and detect pixel-by-pixel. Inspired by the deep learning-based object detection technologies for RGB images, we designed a hyperspectral image target detection method based on spectral-spatial features integrated YOLOv4-tiny network (SS-YOLONet). The 3D hyperspectral images were directly sent to the detection network, their spectral information and complex spatial features were extracted by channel attention module, spatial attention module and 3D convolution. Considering the small size of targets such as airplanes, we extracted two shallow features for small-scale objects. In the experiment, we used the pansharpened EO-1 hyperspectral images to verify the effectiveness of the proposed algorithm. © 2022 ACM.

关键词： Spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Diff-VPS: Video Polyp Segmentation via a Multi-task Diffusion Network with Adversarial Temporal Reasoning

arXiv

引用

arXiv 2024年

作者： Lu, Yingling Yang, Yijun Xing, Zhaohu Wang, Qiong Zhu, Lei The Hong Kong University of Science and Technology Guangzhou China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China The Hong Kong University of Science and Technology Hong Kong

Diffusion Probabilistic Models have recently attracted significant attention in the community of computer vision due to their outstanding performance. However, while a substantial amount of diffusion-based research has focused on generative tasks, no work introduces diffusion models to advance the results of polyp segmentation in videos, which is frequently challenged by polyps’ high camouflage and redundant temporal cues. In this paper, we present a novel diffusion-based network for video polyp segmentation task, dubbed as Diff-VPS. We incorporate multi-task supervision into diffusion models to promote the discrimination of diffusion models on pixel-by-pixel segmentation. This integrates the contextual high-level information achieved by the joint classification and detection tasks. To explore the temporal dependency, Temporal Reasoning Module (TRM) is devised via reasoning and reconstructing the target frame from the previous frames. We further equip TRM with a generative adversarial self-supervised strategy to produce more realistic frames and thus capture better dynamic cues. Extensive experiments are conducted on SUN-SEG, and the results indicate that our proposed Diff-VPS significantly achieves state-of-the-art performance. Code is available at https://***/lydia-yllu/Diff-VPS. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Self-adjustable hyper-graphs for video pose estimation based on spatial-temporal subspace construction

引用

Science China(Information Sciences) 2022年第3期65卷 260-262页

作者： Jizhou MA Shuai LI Hong QIN Aimin HAO Qinping ZHAO State Key Laboratory of Virtual Reality Technology and Systems Beihang University Department of Computer Science Stony Brook University

Dear editor,In recent years many supervised video pose estimation methods have achieved growing successes based on well-labeled training datasets. Nonetheless, when facing roughly-labeled training data, it still remains challenging to intrinsically encode the video contents' spatial-temporal coherency for robust video pose *** researches aimed to directly improve and refine the existing confidence maps by combining the spatial-temporal structure models [1, 2]. Li et al.

关键词： Video Pose Estimation Self-adjustable Hyper-graph Spatial-temporal Subspace Exploration Maximum Matching Subspace Operator Action Pattern

来源：评论

学校读者我要写书评

暂无评论

Semantics-Aware Avatar Locomotion Adaption for Indoor Cross-Scene AR Telepresence

引用

IEEE Transactions on Visualization and computer Graphics 2025年 PP卷 PP页

作者： Li, Yi-Jun Yang, Hao-Zhong Shu, Wen-Tong Wang, Miao Tsinghua University Department of Computer Science and Technology Beijing100084 China Beihang University China Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Zhongguancun Laboratory Beijing100094 China

Geographically dispersed users often rely on virtual avatars as intermediaries to facilitate interactive communication and collaboration. However, existing methods for augmented reality (AR) telepresence applications exhibit limitations, including restricted movement within confined sub-areas, lack of smooth transitions, and the necessity for manually establishing object mapping between dissimilar environments. We present a novel interactive AR framework for virtual avatar locomotion adaption while preserving semantic coherence across dissimilar indoor scenes. Initially, we conduct a preliminary user study to identify key attributes influencing preferred avatar movement. These attributes are quantified as features, and a dataset of user annotations on avatar movements is created. Based on the user interaction and scene configurations, we employ a deep reinforcement learning neural network to guide the avatar to the ideal position while maximizing semantic coherence. We validate our proposed framework through simulations and user studies by implementing an AR-based 3D telepresence prototype, demonstrating the efficacy of our framework in conveying user intentions across dissimilar environments, enabling natural and immersive 3D telepresence interactions. © 1995-2012 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

High-Order Differential Regularizing Implicit Surface Representation of Point Cloud

High-Order Differential Regularizing Implicit Surface Repres...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yuhang Cheng Ziyang Fan Hongyu Wu Xiaogang Wang College of Computer and Information Science Southwest University Chongqing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Reconstructing surfaces from diverse raw data in computer graphics poses an enduring challenge. While recent methods deploy neural networks for direct implicit surface reconstruction, they struggle with degraded raw data quality, especially in edge regions. To address this, we advocate for employing high-order total generalized variation (TGV) as a regularization term for implicit surface representation. Acknowledging the non-trivial nature of extending typical image processing methods to implicit surfaces, we present an end-to-end trainable network framework for TGV in implicit surface reconstruction. This approach preserves sharp features, enhances smooth region recovery, and minimizes artificial artifacts. Simultaneously, we address the challenge of increased computational complexity associated with current algorithms by predicting it directly through an implicit neural function. Experimental results demonstrate the efficacy of our technical approach, providing a promising solution for robust implicit surface reconstruction.

关键词： Point cloud compression Surface reconstruction Image edge detection Data integrity Neural networks computer graphics Prediction algorithms Computational complexity Image reconstruction Surface treatment

来源：评论

学校读者我要写书评

暂无评论

AdaLog: Post-Training Quantization for vision Transformers with Adaptive Logarithm Quantizer

arXiv

引用

arXiv 2024年

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

vision Transformer (ViT) has become one of the most prevailing fundamental backbone networks in the computer vision community. Despite the high accuracy, deploying it in real applications raises critical challenges including the high computational cost and inference latency. Recently, the post-training quantization (PTQ) technique has emerged as a promising way to enhance ViT's efficiency. Nevertheless, existing PTQ approaches for ViT suffer from the inflexible quantization on the post-Softmax and post-GELU activations that obey the power-law-like distributions. To address these issues, we propose a novel non-uniform quantizer, dubbed the Adaptive Logarithm AdaLog (AdaLog) quantizer. It optimizes the logarithmic base to accommodate the power-law-like distribution of activations, while simultaneously allowing for hardware-friendly quantization and de-quantization. By employing the bias reparameterization, the AdaLog quantizer is applicable to both the post-Softmax and post-GELU activations. Moreover, we develop an efficient Fast Progressive Combining Search (FPCS) strategy to determine the optimal logarithm base for AdaLog, as well as the scaling factors and zero points for the uniform quantizers. Extensive experimental results on public benchmarks demonstrate the effectiveness of our approach for various ViT-based architectures and vision tasks including classification, object detection, and instance segmentation. Code is available at https://***/GoatWu/AdaLog. Copyright © 2024, The Authors. All rights reserved.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

FanPad: A Fan Layout Touchpad keyboard for Text Entry in VR

FanPad: A Fan Layout Touchpad Keyboard for Text Entry in VR

引用

IEEE Annual International Symposium virtual reality

作者： Jian Wu Ziteng Wang Lili Wang Yuhan Duan Jiaheng Li State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Peng Cheng Laboratory Shenzhen Guangdong China

Text entry poses a significant challenge in the realm of virtual reality (VR). This paper introduces FanPad, a novel solution designed to facilitate dual-hand text input within head-mounted displays (HMDs). FanPad accomplishes this by ingeniously mapping and curving the 26 typing keys (T26) QWERTY keyboard onto the touchpads of both controllers. The curved key layout of FanPad is derived from the natural movement of the thumb when interacting with the touchpad, resembling an arc with a thumb-length fixed *** optimize the experience, we introduce a customization process for the FanPad curve to better cope with individual hand shapes and thumb movements. We also provide a version with more overlap area named FanPad-Ov for different users with different typing *** first user study examined the effects of curving and different overlap areas by comparing four potential layouts. The results clearly favor the FanPad and FanPad-Ov layout compared to the nocurving version, SKPad(-Ov). Subsequently, the second user study was conducted to assess long-term performance and improvement on customized FanPads. Notably, novices achieved a typing speed of 19.73 words per minute (WPM), demonstrating a remarkable increase of 58.47% after a 60-phrase training in six days. The highest typing speed reached an impressive 24.19 WPM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FEAT: Towards Fast Environment-Adaptive Task Offloading and Power Allocation in MEC 42

FEAT: Towards Fast Environment-Adaptive Task Offloading and ...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Ren, Tao Hu, Zheyuan He, Hang Niu, Jianwei Liu, Xuefeng Institute of Software Chinese Academy of Sciences Laboratory for Internet Software Technologies Beijing China Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing China Zhongguancun Laboratory Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China

ISBN: (纸本)9798350334142

Mobile edge computing (MEC) has been proposed to provide mobile devices with both satisfactory computing resources and latency. key issues in MEC include task offloading and power allocation (TOPA), for which deep reinforcement learning (DRL) is becoming a popular methodology. However, most DRL-based TOPA approaches are typically developed in a certain environment, lacking the adaptability to unseen environments. Motivated by this, this paper proposes a Fast Environment-Adaptive TOPA (FEAT) approach that could adapt to unseen environments with little fine-tuning. Specifically, we first split MEC states into the internal state and environmental state. Then, based on these two types of states, we develop two main components of FEAT - a group of internal state-dependent TOPA meta-policies and an environmental state-embedded steerer. Meta-policies learn TOPA skills within the internal state space (allowing reusing meta-policies in different environments), while the steerer learns to choose appropriate meta-policies according to embedded environmental states. When encountering an unseen environment with the same internal state space, FEAT only needs to fine-tune the steerer using the newly embedded environmental state with few internal state explorations. Extensive experimental results on simulation and testbed demonstrate that FEAT outperforms the state-of-the-art by more than 16.4% in terms of fine-tuning speeds. © 2023 IEEE.

关键词： Mobile edge computing

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：