检索结果-内蒙古大学图书馆

Vision-based Semantic Communications for Metaverse Services: A Contest Theoretic Approach

学校读者我要写书评

暂无评论

Vision-based Semantic Communications for Metaverse Services:...

IEEE Conference on Global Communications (GLOBECOM)

作者： Guangyuan Liu Hongyang Du Dusit Niyato Jiawen Kang Zehui Xiong Boon Hee Soong Energy Research Institute@NTU Interdisciplinary Graduate Program School of Computer Science and Engineering Nanyang Technological University Singapore School of Computer Science and Engineering Nanyang Technological University Singapore School of Automation Guangdong University of Technology China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore Department of Electrical and Electronic Engineering Nanyang Technological University Singapore

The popularity of Metaverse as an entertainment, social, and work platform has led to a great need for seamless avatar integration in the virtual world. In Metaverse, avatars must be updated and rendered to reflect users' behaviour. Achieving real-time synchronization between the virtual bilocation and the user is complex, placing high demands on the Metaverse Service Provider (MSP)'s rendering resource allocation scheme. To tackle this issue, we propose a semantic communication framework that leverages contest theory to model the interactions between users and MSPs and determine optimal resource allocation for each user. To reduce the consumption of network resources in wireless transmission, we use the semantic communication technique to reduce the amount of data to be transmitted. Under our simulation settings, the encoded semantic data only contains 51 bytes of skeleton coordinates instead of the image size of 8.243 megabytes. Moreover, we implement Deep Q-Network to optimize reward settings for maximum performance and efficient resource allocation. With the optimal reward setting, users are incentivized to select their respective suitable uploading frequency, reducing down-sampling loss due to rendering resource constraints by 66.076% compared with the traditional average distribution method. The framework provides a novel solution to resource allocation for avatar association in VR environments, ensuring a smooth and immersive experience for all users.

关键词：

Multiscale Numerical Modeling for Near-Field Microwave Impedance Microscopy

学校读者我要写书评

暂无评论

Multiscale Numerical Modeling for Near-Field Microwave Imped...

Conference on Lasers and Electro-Optics (CLEO)

作者： Diego Tami Douglas A. A. Ohlberg Jhonattan C. Ramirez Cássio Gonçalves Do Rego Gilberto Medeiros-Ribeiro Graduate Program in Electrical Engineering Universidade Federal de Minas Gerais Brazil Microscopy Center Universidade Federal de Minas Gerais Brazil Department of Electronic Engineering Universidade Federal de Minas Gerais Brazil Computer Science Department Universidade Federal de Minas Gerais Brazil

In this work, we analyzed numerically a multiscale nanosystem based on sMIM on TBG. Spontaneous formation of a water-meniscus by the approximation between the tip-sample concentrates the microwave fields, reaching res... 详细信息

ISBN: (数字)9781957171050

ISBN: (纸本)9781665466660

关键词： Microscopy Masers Lasers and electrooptics Laser modes Numerical models Impedance Electrooptical waveguides

Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jin, Peng Huang, Jinfa Xiong, Pengfei Tian, Shangxuan Liu, Chang Ji, Xiangyang Yuan, Li Chen, Jie School of Electronic and Computer Engineering Peking University Shenzhen China Peng Cheng Laboratory Shenzhen China -Preferred Program Peking University Shenzhen Graduate School Shenzhen China Shopee Shenzhen China Department of Automation BNRist Tsinghua University Beijing China

Contrastive learning-based video-language representation learning approaches, e.g., CLIP, have achieved outstanding performance, which pursue semantic interaction upon pre-defined video-text pairs. To clarify this coarse-grained global interaction and move a step further, we have to encounter challenging shell-breaking interactions for fine-grained cross-modal learning. In this paper, we creatively model video-text as game players with multivariate cooperative game theory to wisely handle the uncertainty during fine-grained semantic interaction with diverse granularity, flexible combination, and vague intensity. Concretely, we propose Hierarchical Banzhaf Interaction (HBI) to value possible correspondence between video frames and text words for sensitive and explainable cross-modal contrast. To efficiently realize the cooperative game of multiple video frames and multiple text words, the proposed method clusters the original video frames (text words) and computes the Banzhaf Interaction between the merged tokens. By stacking token merge modules, we achieve cooperative games at different semantic levels. Extensive experiments on commonly used text-video retrieval and video-question answering benchmarks with superior performances justify the efficacy of our HBI. More encouragingly, it can also serve as a visualization tool to promote the understanding of cross-modal interaction, which have a far-reaching impact on the community. Project page is available at https://***/HBI/. Copyright © 2023, The Authors. All rights reserved.

关键词： Game theory

Time Series Mining Approach for Noninvasive Intracranial Pressure Assessment: An Investigation of Different Regularization Techniques

学校读者我要写书评

暂无评论

Time Series Mining Approach for Noninvasive Intracranial Pre...

computer Science and Information engineering, CSIE, WRI World Congress on FLAGGED

作者： Shaozhi Wu Peng Xu Shadnaz Asgari Marvin Bergsneider Xiao Hu Biomedical Engineering Graduate Program Henry Samueli School of Engineering and Applied Science University of California Los Angeles USA Neural Systems and Dynamics Laboratory Department of Neurosurgery the David Geffen School of Medicine University of California Los Angeles USA School of Computer Science and Engineering University of Electronic Science and Technology Chengdu China

A data mining framework has been proposed to estimate intracranial pressure (ICP) non-invasively in our previous work. In the corresponding approach, the feature vector extracted from arterial blood pressure (ABP) and flow velocity (FV) is translated to the estimated errors by the mapping function for each entry in the database. In this paper, three different mapping function solutions, linear least squares (LLS), truncated singular value decomposition (TSVD) and standard Tikhonov regularization (STR) are systemically tested to compare the possible effects of different solutions on the non-invasive ICP estimation. The conducted comparison demonstrated that the selection of mapping function solution actually influences the estimation. Among the tested three solutions for mapping function, TSVD and STR show better ICP estimation performance with smaller ICP errors than LLS.

关键词： Cranial pressure Data mining Biomedical engineering Data engineering Spatial databases computer science Feature extraction Arterial blood pressure Biomedical measurements Laboratories

Enabling AI-Generated Content (AIGC) Services in Wireless Edge Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Du, Hongyang Li, Zonghang Niyato, Dusit Kang, Jiawen Xiong, Zehui Shen, Xuemin Kim, Dong In The School of Computer Science and Engineering The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The School of Information and Communication Engineering University of Electronic Sciences and Technology of China Chengdu China The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The Department of Electrical and Computer Engineering University of Waterloo Canada The Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of

Artificial Intelligence-Generated Content (AIGC) refers to the use of AI to automate the information creation process while fulfilling the personalized requirements of users. However, due to the instability of AIGC models, e.g., the stochastic nature of diffusion models, the quality and accuracy of the generated content can vary significantly. In wireless edge networks, the transmission of incorrectly generated content may unnecessarily consume network resources. Thus, a dynamic AIGC service provider (ASP) selection scheme is required to enable users to connect to the most suited ASP, improving the users’ satisfaction and quality of generated content. In this article, we first review the AIGC techniques and their applications in wireless networks. We then present the AIGC-as-a-service (AaaS) concept and discuss the challenges in deploying AaaS at the edge networks. Yet, it is essential to have performance metrics to evaluate the accuracy of AIGC services. Thus, we introduce several image-based perceived quality evaluation metrics. Then, we propose a general and effective model to illustrate the relationship between computational resources and user-perceived quality evaluation metrics. To achieve efficient AaaS and maximize the quality of generated content in wireless edge networks, we propose a deep reinforcement learning-enabled algorithm for the optimal ASP selection. Simulation results show that the proposed algorithm can provide a higher quality of generated content to users and achieve fewer crashed tasks by comparing with four benchmarks, i.e., overloading-avoidance, random, round-robin policies, and the upper-bound schemes. © 2023, CC BY.

关键词： Reinforcement learning

Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation

学校读者我要写书评

暂无评论

Out-of-Candidate Rectification for Weakly Supervised Semanti...

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Zesen Cheng Pengchong Qiao Kehan Li Siheng Li Pengxu Wei Xiangyang Ji Li Yuan Chang Liu Jie Chen School of Electronic and Computer Engineering Peking University Shenzhen China AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School China Peng Cheng Laboratory Shenzhen China Tsinghua University Sun Yat-Sen University

Weakly supervised semantic segmentation is typically inspired by class activation maps, which serve as pseudo masks with class-discriminative regions highlighted. Although tremendous efforts have been made to recall precise and complete locations for each class, existing methods still commonly suffer from the unsolicited Out-of-Candidate (OC) error predictions that do not belong to the label candidates, which could be avoidable since the contradiction with image-level class tags is easy to be detected. In this paper, we develop a group ranking-based Out-of-f;Candidate Rectification (OCR) mechanism in a plug-and-play fashion. Firstly, we adaptively split the semantic categories into In-Candidate (IC) and OC groups for each OC pixel according to their prior annotation correlation and posterior prediction correlation. Then, we derive a differentiable rectification loss to force OC pixels to shift to the IC group. Incorporating OCR with seminal baselines (e.g., AffinityNet, SEAM, MCTformer), we can achieve remarkable performance gains on both Pascal VOC (+3.2%, +3.3%, +0.8% mIoU) and MS COCO (+1.0%, +1.3%, +0.5% mIoU) datasets with negligible extra training overhead, which jus-tifies the effectiveness and generality of OCR. † † Ŋ ***/sennnnn/Out-of-Candidate-Rectification

关键词：

ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Kehan Wang, Zhennan Cheng, Zesen Yu, Runyi Zhao, Yian Song, Guoli Liu, Chang Yuan, Li Chen, Jie School of Electronic and Computer Engineering Peking University Shenzhen China Peng Cheng Laboratory Shenzhen China -Preferred Program Peking University Shenzhen Graduate School Shenzhen China Department of Automation BNRist Tsinghua University Beijing China Dalian University of Technology China

Recently, self-supervised large-scale visual pre-training models have shown great promise in representing pixellevel semantic relationships, significantly promoting the development of unsupervised dense prediction tasks, e.g., unsupervised semantic segmentation (USS). The extracted relationship among pixel-level representations typically contains rich class-aware information that semantically identical pixel embeddings in the representation space gather together to form sophisticated concepts. However, leveraging the learned models to ascertain semantically consistent pixel groups or regions in the image is non-trivial since over/ under-clustering overwhelms the conceptualization procedure under various semantic distributions of different images. In this work, we investigate the pixel-level semantic aggregation in self-supervised ViT pre-trained models as image Segmentation and propose the Adaptive Conceptualization approach for USS, termed ACSeg. Concretely, we explicitly encode concepts into learnable prototypes and design the Adaptive Concept Generator (ACG), which adaptively maps these prototypes to informative concepts for each image. Meanwhile, considering the scene complexity of different images, we propose the modularity loss to optimize ACG independent of the concept number based on estimating the intensity of pixel pairs belonging to the same concept. Finally, we turn the USS task into classifying the discovered concepts in an unsupervised manner. Extensive experiments with state-of-the-art results demonstrate the effectiveness of the proposed ACSeg. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantic Segmentation

Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jin, Peng Huang, Jinfa Liu, Fenglin Wu, Xian Ge, Shen Song, Guoli Clifton, David A. Chen, Jie School of Electronic and Computer Engineering Peking University China Peng Cheng Laboratory Shenzhen China -Preferred Program Peking University Shenzhen Graduate School China Department of Engineering Science University of Oxford United Kingdom Tencent JARVIS Lab China Oxford-Suzhou Centre for Advanced Research Suzhou China

Most video-and-language representation learning approaches employ contrastive learning, e.g., CLIP [53], to project the video and text features into a common latent space according to the semantic similarities of text-video pairs. However, such learned shared latent spaces are not often optimal, and the modality gap between visual and textual representation can not be fully eliminated. In this paper, we propose Expectation-Maximization Contrastive Learning (EMCL) to learn compact video-and-language representations. Specifically, we use the Expectation-Maximization algorithm to find a compact set of bases for the latent space, where the features could be concisely represented as the linear combinations of these bases. Such feature decomposition of video-and-language representations reduces the rank of the latent space, resulting in increased representing power for the semantics. Extensive experiments on three benchmark text-video retrieval datasets prove that our EMCL can learn more discriminative video-and-language representations than previous methods, and significantly outperform previous state-of-the-art methods across all metrics. More encouragingly, the proposed method can be applied to boost the performance of existing approaches either as a jointly training layer or an out-of-the-box inference module with no extra training, making it easy to be incorporated into any existing methods‡ Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

Fuzzy Positive Learning for Semi-Supervised Semantic Segmentation

学校读者我要写书评

暂无评论

Fuzzy Positive Learning for Semi-Supervised Semantic Segment...

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Pengchong Qiao Zhidan Wei Yu Wang Zhennan Wang Guoli Song Fan Xu Xiangyang Ji Chang Liu Jie Chen School of Electronic and Computer Engineering Peking University Shenzhen China Peng Cheng Laboratory Shenzhen China AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School China Department of Automation and BNRist Tsinghua University Beijing China

Semi-supervised learning (SSL) essentially pursues class boundary exploration with less dependence on human annotations. Although typical attempts focus on ameliorating the inevitable error-prone pseudo-labeling, we think differently and resort to exhausting informative semantics from multiple probably correct candidate labels. In this paper, we introduce Fuzzy Positive Learning (FPL) for accurate SSL semantic segmentation in a plug-and-play fashion, targeting adaptively encouraging fuzzy positive predictions and suppressing highly-probable negatives. Being conceptually simple yet practically effective, FPL can remarkably alleviate interference from wrong pseudo labels and progressively achieve clear pixel-level semantic discrimination. Concretely, our FPL approach consists of two main components, including fuzzy positive assignment (FPA) to provide an adaptive number of labels for each pixel and fuzzy positive regularization (FPR) to restrict the predictions of fuzzy positive categories to be larger than the rest under different perturbations. Theoretical analysis and extensive experiments on Cityscapes and VOC 2012 with consistent performance gain justify the superiority of our approach. Codes are provided in https://***/qpc1611094/FPL.

关键词：