检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Zhou, Yibo Hu, Hai-Miao Xiang, Yirong Zhang, Xiaokang Wu, Haotian Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang University Beijing100191 China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China Hangzhou Innovation Institute of Beihang University Hangzhou310051 China The University of Manchester United Kingdom

Rooting in the scarcity of most attributes, realistic pedestrian attribute datasets exhibit unduly skewed data distribution, from which two types of model failures are delivered: (1) label imbalance: model predictions lean greatly towards the side of majority labels;(2) semantics imbalance: model is easily overfitted on the under-represented attributes due to their insufficient semantic *** render perfect label balancing, we propose a novel framework that successfully decouples label-balanced data re-sampling from the curse of attributes co-occurrence, i.e., we equalize the sampling prior of an attribute while not biasing that of the co-occurred *** diversify the attributes semantics and mitigate the feature noise, we propose a Bayesian feature augmentation method to introduce true in-distribution *** both imbalances jointly, our work achieves best accuracy on various popular benchmarks, and importantly, with minimal computational budget. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Power of Age-based Reward in Fresh Information Acquisition 42

The Power of Age-based Reward in Fresh Information Acquisiti...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Wang, Zhiyuan Meng, Qingkai Zhang, Shan Luo, Hongbin Beihang University School of Computer Science and Engineering Beijing China Beihang University State Key Laboratory of Virtual Reality Technology and Systems China Beihang University Institute of Artificial Intelligence Beijing China State Key Laboratory of Software Development Environment China

ISBN: (纸本)9798350334142

Many Internet platforms collect fresh information of various points of interest (PoIs) relying on users who happen to be nearby the PoIs. The platform will offer reward to incentivize users and compensate their costs incurred from information acquisition. In practice, the user cost (and its distribution) is hidden to the platform, thus it is challenging to determine the optimal reward. In this paper, we investigate how the platform dynamically rewards the users, aiming to jointly reduce the age of information (AoI) and the operational expenditure (OpEx). Due to the hidden cost distribution, this is an online non-convex learning problem with partial feedback. To overcome the challenge, we first design an age-based rewarding scheme, which decouples the OpEx from the unknown cost distribution and enables the platform to accurately control its OpEx. We then take advantage of the age-based rewarding scheme and propose an exponentially discretizing and learning (EDAL) policy for platform operation. We prove that the EDAL policy performs asymptotically as well as the optimal decision (derived based on the cost distribution). Simulation results show that the age-based rewarding scheme protects the platform's OpEx from the influence of the user characteristics, and verify the asymptotic optimality of the EDAL policy. © 2023 IEEE.

关键词： Simulation platform

来源：评论

学校读者我要写书评

暂无评论

Audio-Driven Talking Face Video Generation with Emotion

Audio-Driven Talking Face Video Generation with Emotion

引用

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

作者： Jiadong Liang Feng Lu State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China

ISBN: (数字)9798350374490

ISBN: (纸本)9798350374506

Vivid talking face generation has potential applications in virtual reality. Existing methods can generate talking faces that are synchronized with the audio, but typically ignore the accurate expression of emotions. In this paper, we propose an advanced two-step framework to synthesize talking face videos with vivid emotional appearances. The first step is designed to generate emotional fine-grained landmarks, including the normalized landmarks, gaze, and head pose. In the second step, we map the facial landmarks to latent key points, which are then fed into the pre-trained model to generate high-quality face images. Extensive experiments demonstrate the effectiveness of our method.

关键词： Solid modeling Three-dimensional displays Conferences virtual reality User interfaces Digital humans Synchronization

来源：评论

学校读者我要写书评

暂无评论

Optimizing Link-Identified Forwarding Framework in LEO Satellite Networks 21

Optimizing Link-Identified Forwarding Framework in LEO Satel...

引用

21st International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks, WiOpt 2023

作者： Zhang, Hefan Wang, Zhiyuan Zhang, Shan Meng, Qingkai Luo, Hongbin School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China Institute of Artificial Intelligence Beihang University Beijing China State Key Laboratory of Software Development Environment China State Key Laboratory of Virtual Reality Technology and Systems China

ISBN: (纸本)9783903176553

Low earth orbit (LEO) satellite networks have the potential to provide low-latency communication with global coverage. To unleash this potential, it is crucial to achieve efficient data delivery. In this paper, we analyze the topology characteristics of LEO satellite networks, and propose a source-route-style forwarding framework. Specifically, we leverage the deterministic neighbor relationship and identify all the unidirectional inter-satellite links (ISLs). Moreover, our framework utilizes the in-packet bloom filter (BF) to store the source-route-style forwarding information. This way, the source satellite could encode multiple ISL identifiers into the BF, which actually specifies the forwarding path. The intermediate satellites only need to check whether the outgoing ISLs are encoded and forward packets accordingly. Due to false positives caused by BF, the more ISLs are encoded at a time, the more redundant forwardings emerge. To reduce forwarding overhead, we take into account segment encoding, allowing the source and intermediate satellites to encode part of ISLs towards the destination. Overall, segment encoding seeks the right balance between forwarding overhead and encoding delay. We characterize a wide range of segment encoding policy in a unified framework, and derive the expected forwarding overhead in a closed-form. The segment encoding design is formulated as a binary non-linear programming, which is NP-hard. To overcome the challenge, we leverage its decomposable structure, and propose an efficient algorithm to solve it optimally. Finally, we validate our analytical results via packet-level experiments. Results also show that our proposed segment encoding policy significantly reduces the queuing delay compared to source encoding. © 2023 IFIP.

关键词： Satellites

来源：评论

学校读者我要写书评

暂无评论

Neural 3D Strokes: Creating Stylized 3D Scenes with Vectorized 3D Strokes

Neural 3D Strokes: Creating Stylized 3D Scenes with Vectoriz...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Hao-Bin Duan Miao Wang Yan-Xun Li Yong-Liang Yang State Key Laboratory of Virtual Reality Technology and Systems SCSE Beihang University Zhongguanchun Laboratory Department of Computer Science University of Bath

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

We present Neural 3D Strokes, a novel technique to gen-erate stylized images of a 3D scene at arbitrary novel views from multi-view 2D images. Different from existing methods which apply stylization to trained neural radiance fields at the voxel level, our approach draws inspiration from image-to-painting methods, simulating the progressive painting process of human artwork with vector strokes. We develop a palette of stylized 3D strokes from basic primitives and splines, and consider the 3D scene stylization task as a multi-view reconstruction process based on these 3D stroke primitives. Instead of directly searching for the parame-ters of these 3D strokes, which would be too costly, we introduce a differentiable renderer that allows optimizing stroke parameters using gradient descent, and propose a training scheme to alleviate the vanishing gradient issue. The extensive evaluation demonstrates that our approach effectively synthesizes 3D scenes with significant geomet-ric and aesthetic stylization while maintaining a consis-tent appearance across different views. Our method can be further integrated with style loss and image-text con-trastive models to extend its applications, including color transfer and text-driven 3D scene drawing. Results and code are available at http://***/Neura13DStrokes.

关键词： Training Solid modeling Three-dimensional displays Stroke (medical condition) Neural radiance field Vectors Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

GraphFed: A Personalized Subgraph Federated Learning Framework for Non-IID Graphs 20

GraphFed: A Personalized Subgraph Federated Learning Framewo...

引用

20th IEEE International Conference on Mobile Ad Hoc and Smart Systems, MASS 2023

作者： Deng, Pan Liu, Xuefeng Niu, Jianwei Hu, Chunming Zhongguancun Laboratory Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9798350324334

Recently, federated graph learning has attracted significant attention, as subgraphs of a global graph may often distribute across different institutions and are subject to privacy restrictions. However, inevitable data heterogeneity among sub-graphs can lead to poor performance of Graph Neural Networks (GNNs) trained by vanilla federated learning algorithm, which has been neglected before. To address this problem we look at subgraphs and find that there are usually overlapping nodes among them. Inspired by the common overlapping nodes among subgraphs, we propose GraphFed, a subgraph federated learning framework which solve the challenge in terms of both data augmentation and personalized federated learning. GraphFed uses common overlapping nodes among subgraphs to locate lost node information and applies data augmentation by retrieving lost nodes and forming common node sets that mitigates data distribution difference. Furthermore, GraphFed treats the overlapping nodes as bridges to calculate the distance among different subgraphs, which implies the similarity of the graph data distribution. Then, we use the distance to perform personalized federated learning. Empirical results and analysis on three real-world graph datasets with graph federated learning settings demonstrate the effectiveness of our proposed framework. © 2023 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

TopicDVC: Dense Video Captioning with Topic Guidance

TopicDVC: Dense Video Captioning with Topic Guidance

引用

Edge Computing and Scalable Cloud (EdgeCom), IEEE International Conference on

作者： Wei Chen State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China

ISBN: (数字)9798350377132

ISBN: (纸本)9798350377149

Dense video captioning involves detecting and describing multiple events within a video coherently. Events within a video typically share a common topic, and incorporating this topic information into the model can enhance the quality and coherence of the generated captions. However, existing dense video captioning datasets lack explicit topic annotations. To address this, we design a topic generator that utilizes a diffusion model with strong generative capabilities to generate topic information from a given video. During the training stage, we use the features of ground-truth captions as pseudo-topic labels. The video topics diffuse from the features of groundtruth captions to a random distribution, and the model learns to reverse this noising process conditioned on video features. During inference, the model iteratively denoises the Gaussian noise into topic features conditioned on video features. In this paper, we propose TopicDVC, a novel dense video captioning framework. TopicDVC applies the topic information generated by the topic generator to guide the model in generating more coherent captions. Experiments on the ActivityNet Captions dataset demonstrate that leveraging the topics generated by the diffusion model significantly improves the performance of dense video captioning, producing more accurate and coherent captions.

关键词： Training Accuracy Annotations Video description Gaussian noise Coherence Diffusion models

来源：评论

学校读者我要写书评

暂无评论

Robust Dual-Modal Speech keyword Spotting for XR Headsets

arXiv

引用

arXiv 2024年

作者： Cai, Zhuojiang Ma, Yuhan Lu, Feng State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China

While speech interaction finds widespread utility within the Extended reality (XR) domain, conventional vocal speech keyword spotting systems continue to grapple with formidable challenges, including suboptimal performance in noisy environments, impracticality in situations requiring silence, and susceptibility to inadvertent activations when others speak nearby. These challenges, however, can potentially be surmounted through the cost-effective fusion of voice and lip movement information. Consequently, we propose a novel vocal-echoic dual-modal keyword spotting system designed for XR headsets. We devise two different modal fusion approches and conduct experiments to test the system’s performance across diverse scenarios. The results show that our dual-modal system not only consistently outperforms its single-modal counterparts, demonstrating higher precision in both typical and noisy environments, but also excels in accurately identifying silent utterances. Furthermore, we have successfully applied the system in real-time demonstrations, achieving promising results. The code is available at https://***/caizhuojiang/VE-KWS. Copyright © 2024, The Authors. All rights reserved.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

A Doctors Behavior Aware and Domain Knowledge Driven Model for Medical Report Generation

A Doctors Behavior Aware and Domain Knowledge Driven Model f...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Wang, Han Niu, Jianwei Liu, Xuefeng Wang, Yong Beihang University School of Computer Science Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beijing China Zhongguancun Laboratory Beijing China Peking Union Medical College Chinese Academy of Medical Sciences Beijing China

ISBN: (纸本)9798350337488

When doctors write a medical report, they first focus on key regions in the image, which usually contain abnormal information. Then, they write the report based on their experience and professional knowledge. Some existing medical report generation methods design corresponding schemes to model this process, but they still have some drawbacks. Some of them adopt the attention map to model the doctors' image-reading behavior, which requires additional cropping and feature extraction operations, bringing many extra computations. Other methods manually construct knowledge graphs to model the doctors' domain knowledge, which requires manual construction for different disease domains and has less generalization. Therefore, We propose DEKG, a doctors behavior aware and domain knowledge driven model, to improve the quality of generated reports by modeling the fixed pattern of doctors when writing reports. Specifically, feature clustering is utilized to model the doctors' image-reading behavior that only brings fewer computations, and then we capture key regions with possible abnormalities. We also design a method to automatically construct domain knowledge graphs, which can quickly accomplish the construction process for different disease domains without human intervention. Extensive experiments on datasets from different disease domains demonstrate that DEKG achieves competitive results with state-of-the-art methods and can generate high-quality reports. © 2023 IEEE.

关键词： Feature Clustering Knowledge Graph Medical Report Generation Transformer

来源：评论

学校读者我要写书评

暂无评论

Frequency-Guided Network for Low-contrast Staining-free Dental Plaque Segmentation

Frequency-Guided Network for Low-contrast Staining-free Dent...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Jiang, Yiming Song, Wenfeng Li, Shuai Yang, Yuming Xia, Bin Hao, Aimin Qin, Hong Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beijing China Beijing Information Science and Technology University School of Computer Science Beijing China Peking University School and Hospital of Stomatology Department of Pediatric Dentistry Beijing China Stony Brook University Department of Computer Science New York United States

ISBN: (纸本)9798350386226

Traditional dental plaque detection relies on medical staining reagents and professional intervention. Deep learning-based automatic staining-free dental plaque segmentation provides an alternative for patients to perform plaque detection at home without staining reagents. However, existing methods still struggle with low-contrast visual features between unstained plaque and healthy teeth. To address this, we propose a Frequency-Guided Network (FGN) for low-contrast staining-free dental plaque segmentation. We observe that dental plaque tends to concentrate specifically near the junction between the teeth and the gingiva. This junction demonstrates abrupt changes in pixel values, indicating high-frequency regions in the image. In other words, dental plaque tends to appear near the high-frequency regions of oral endoscope images. Exploiting this characteristic, we employ a frequency-guided decoupling module to separate the image into high-frequency and low-frequency regions automatically and expand the high-frequency region to encompass nearby potential dental plaque. Then we supervise two regions individually to specifically focus on the expended high-frequency region for localizing nearby dental plaque. Additionally, we propose a high-to-low frequency multiple tasks framework. In the first phase, the network segments the teeth region, and then we input the teeth mask into the second phase. In the second stage, the teeth mask allows us to have a higher frequency at the junction between the teeth and gums, thereby enhancing the effectiveness of frequency-guided decoupling. Furthermore, FGN integrates a frequency-driven refinement module to enhance the guidance quality of the teeth mask for the second phase. Extensive evaluations of the oral endoscope dataset demonstrate that our method outperforms existing high-performance segmentation methods. User studies also confirm that our approach achieves superior results to experienced dentists. https://frequency-guided-netw

关键词： Image segmentation

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：