检索结果-内蒙古大学图书馆

International Conference on computer Vision (ICCV)

作者： Runyi Yu Zhennan Wang Yinhuai Wang Kehan Li Chang Liu Haoyi Duan Xiangyang Ji 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 Department of Automation and BNRist Tsinghua University Beijing China School of Computer Science and Technology Zhejiang University Zhejiang China

Position information is critical for Vision Transformers (VTs) due to the permutation-invariance of self-attention operations. A typical way to introduce position information is adding the absolute Position Embedding (PE) to patch embedding before entering VTs. However, this approach operates the same Layer Normalization (LN) to token embedding and PE, and delivers the same PE to each layer. This results in restricted and monotonic PE across layers, as the shared LN affine parameters are not dedicated to PE, and the PE cannot be adjusted on a per-layer basis. To overcome these limitations, we propose using two independent LNs for token embeddings and PE in each layer, and progressively delivering PE across layers. By implementing this approach, VTs will receive layer-adaptive and hierarchical PE. We name our method as Layer-adaptive Position Embedding, abbreviated as LaPE, which is simple, effective, and robust. Extensive experiments on image classification, object detection, and semantic segmentation demonstrate that LaPE significantly outperforms the default PE method. For example, LaPE improves +1.06% for CCT on CIFAR100, +1.57% for DeiT-Ti on ImageNet-1K, +0.7 box AP and +0.5 mask AP for ViT-Adapter-Ti on COCO, and +1.37 mIoU for tiny Segmenter on ADE20K. This is remarkable considering LaPE only increases negligible parameters, memory, and computational cost.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of teaching materials for improving motivation to learn electromagnetics using ict

引用

IEEJ Transactions on Fundamentals and Materials 2020年第4期140卷 171-178页

作者： Ohtaki, Yu Ohchi, Masashi Master's Program in Electrical Electronics and Computer Engineering Graduate School of Engineering Chiba Institute of Technology 2-17-1 Tsudanuma Narashino275-0016 Japan Department of Electrical and Electronic Engineering Faculty of Engineering Chiba Institute of Technology 2-17-1 Tsudanuma Narashino275-0016 Japan

In this research, we have been developed teaching materials for electromagnetics that demonstrate theories using real-world actual applications (capacitors, coils, piezoelectric elements, Wireless Power Transfer(WPT), WiFi, direct-current motor, etc.) presented as animations and video data via Web services. Hypertext Markup Language (HTML) and JavaScript were used to create the Web services for teaching materials. Recently, the lack of academic ability of Japanese engineering course students has become a large social problem at Japanese higher education. In particular, in the field of electrical engineering education, the visualization and mathematical abilities of students have been declining remarkably. In addition, today's teaching materials for educational institutions in Japan tend to reply primarily on rote learning. However, we consider that rote learning is not the primary method for university education. We tested our new developed materials on students learning motivation of electromagnetics and evaluated their effectiveness with some questionnaires. It was clear that the new teaching method has effectiveness for increasing learning motivation of Electromagnetics. © 2020 The Institute of Electrical Engineers of Japan.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

IoT–based tire pressure monitoring system for air and temperature pressure using MPX5500D and LM35 sensor

IoT–based tire pressure monitoring system for air and tempe...

引用

International Conference on Computing, engineering, and Design (ICCED)

作者： Agung Pangestu Iing Sodikin Muhammad Yusro Rum Sapundani Rosyid Ridlo Al Hakim Sinka Wilyanti Electrical Engineering Department Faculty of Engineering and Computer Science Jakarta Global University Depok Indonesia Department of Electronic Engineering Faculty of Engineering State University of Jakarta Jakarta Indonesia Electromedical Engineering Technology Faculty of Health Science University of Muhammadiyah Purwokerto Purwokerto Indonesia Graduate Program in Electrical Engineering Faculty of Engineering and Computer Science Jakarta Global University Depok Indonesia

ISBN: (纸本)9781665453905

Research has been carried out to monitor vehicle tires before they are used and can reduce damage, including overcoming vehicle fuel waste because air pressure is continuously monitored. This research aims to utilize the MPX5500DP sensor as an air pressure device, the LM35 sensor as a temperature reader, and a buzzer based on IoT to build a tire pressure monitoring system (TPMS). The MPX5500DP and LM35 sensor inputs to the Arduino Uno microcontroller are distributed by the NodeMCU, fitted with a Wi-Fi module. The Blynk application sends and displays the data on a smartphone using the IoT-based. Based on this research, data on the percentage of errors in monitoring air pressure and tire temperature on vehicles were obtained by comparing the data to the pressure gauge and thermometer: 1—the results of the average reading of the sensor error value. MPX5500DP air pressure against pressure gauge is 5.3%. 2—the average reading of the LM35 sensor error value on the temperature thermometer is 6.8%. With this research, the air pressure and temperature in the tires can be monitored in real-time via a smartphone using the IoT-based.

关键词： Temperature measurement Temperature distribution Thermometers Microcontrollers Tire pressure Real-time systems Pressure gauges

来源：评论

学校读者我要写书评

暂无评论

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

Video-Text as Game Players: Hierarchical Banzhaf Interaction...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Peng Jin Jinfa Huang Pengfei Xiong Shangxuan Tian Chang Liu Xiangyang Ji Li Yuan Jie Chen School of Electronic and Computer Engineering Peking University Shenzhen China AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School Shenzhen China Shopee Shenzhen China Department of Automation and BNRist Tsinghua University Beijing China Peng Cheng Laboratory Shenzhen 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 bench-marks 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/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation

ACSeg: Adaptive Conceptualization for Unsupervised Semantic ...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Kehan Li Zhennan Wang Zesen Cheng Runyi Yu Yian Zhao Guoli Song Chang Liu Li Yuan Jie Chen School of Electronic and Computer Engineering Peking University Shenzhen China AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School Shenzhen China Peng Cheng Laboratory Shenzhen China Dalian University of Technology Department of Automation and BNRist Tsinghua University Beijing China

Recently, self-supervised large-scale visual pre-training models have shown great promise in representing pixel-level 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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diffusion-based Reinforcement Learning for Edge-enabled AI-Generated Content Services

TechRxiv

引用

TechRxiv 2023年

作者： Du, Hongyang Li, Zonghang Niyato, Dusit Kang, Jiawen Xiong, Zehui Huang, Huawei Mao, Shiwen School of Computer Science and Engineering The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore School of Information and Communication Engineering University of Electronic Sciences and Technology of China Chengdu China School of Automation Guangdong University of Technology China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore School of Software Engineering Sun Yat-Sen University Zhuhai China Department of Electrical and Computer Engineering Auburn University Auburn United States

As Metaverse emerges as the next-generation Internet paradigm, the ability to efficiently generate content is paramount. AI-Generated Content (AIGC) emerges as a key solution, yet the resource-intensive nature of large Generative AI (GAI) models presents challenges. To address this issue, we introduce an AIGC-as-a-Service (AaaS) architecture, which deploys AIGC models in wireless edge networks to ensure broad AIGC services accessibility for Metaverse users. Nonetheless, an important aspect of providing personalized user experiences requires carefully selecting AIGC Service Providers (ASPs) capable of effectively executing user tasks, which is complicated by environmental uncertainty and variability. Addressing this gap in current research, we introduce the AI-Generated Optimal Decision (AGOD) algorithm, a diffusion model-based approach for generating the optimal ASP selection decisions. Integrating AGOD with Deep Reinforcement Learning (DRL), we develop the Deep Diffusion Soft Actor-Critic (D2SAC) algorithm, enhancing the efficiency and effectiveness of ASP selection. Our comprehensive experiments demonstrate that D2SAC outperforms seven leading DRL algorithms. Furthermore, the proposed AGOD algorithm has the potential for extension to various optimization problems in wireless networks, positioning it as a promising approach for future research on AIGC-driven services. The implementation of our proposed method is available at: https://***/Lizonghang/AGOD. © 2023, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Diffusion-based Reinforcement Learning for Edge-enabled AI-Generated Content Services

arXiv

引用

arXiv 2023年

作者： Du, Hongyang Li, Zonghang Niyato, Dusit Kang, Jiawen Xiong, Zehui Huang, Huawei Mao, Shiwen 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 School of Software Engineering Sun Yat-Sen University Zhuhai China The Department of Electrical and Computer Engineering Auburn University Auburn United States

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

GraCo: Granularity-Controllable Interactive Segmentation

GraCo: Granularity-Controllable Interactive Segmentation

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yian Zhao Kehan Li Zesen Cheng Pengchong Qiao Xiawu Zheng Rongrong Ji Chang Liu Li Yuan 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 Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China Department of Automation and BNRist Tsinghua University Beijing China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Interactive Segmentation (IS) segments specific objects or parts in the image according to user input. Current IS pipelines fall into two categories: single-granularity out-put and multi-granularity output. The latter aims to allevi-ate the spatial ambiguity present in the former. However, the multi-granularity output pipeline suffers from limited interaction flexibility and produces redundant results. In this work, we introduce Granularity-Controllable Interactive Segmentation (GraCo), a novel approach that allows precise control of prediction granularity by introducing ad-ditional parameters to input. This enhances the customization of the interactive system and eliminates redundancy while resolving ambiguity. Nevertheless, the exorbitant cost of annotating multi-granularity masks and the lack of avail-able datasets with granularity annotations make it difficult for models to acquire the necessary guidance to control out-put granularity. To address this problem, we design an any-granularity mask generator that exploits the semantic property of the pre-trained IS model to automatically gen-erate abundant mask-granularity pairs without requiring additional manual annotation. Based on these pairs, we propose a granularity-controllable learning strategy that efficiently imparts the granularity controllability to the IS model. Extensive experiments on intricate scenarios at ob-ject and part levels demonstrate that our GraCo has signifi-cant advantages over previous methods. This highlights the potential of GraCo to be a flexible annotation tool, capable of adapting to diverse segmentation scenarios. The project page: https://***/GraCo.

关键词： Image segmentation Adaptation models Annotations Interactive systems Pipelines Semantics Redundancy

来源：评论

学校读者我要写书评

暂无评论

Expectation-maximization contrastive learning for compact video-and-language representations 22

Expectation-maximization contrastive learning for compact vi...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Peng Jin Jinfa Huang Fenglin Liu Xian Wu Shen Ge Guoli Song David A. Clifton Jie Chen School of Electronic and Computer Engineering Peking University China and AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School China Department of Engineering Science University of Oxford UK Tencent JARVIS Lab China Peng Cheng Laboratory Shenzhen China Department of Engineering Science University of Oxford UK and Oxford-Suzhou Centre for Advanced Research Suzhou China School of Electronic and Computer Engineering Peking University China and Peng Cheng Laboratory Shenzhen China and AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School China

ISBN: (纸本)9781713871088

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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding

Chat-UniVi: Unified Visual Representation Empowers Large Lan...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Peng Jin Ryuichi Takanobu Wancai Zhang Xiaochun Cao Li Yuan 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 Shenzhen China Nari Technology Co. Ltd. China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University Shenzhen China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Large language models have demonstrated impressive universal capabilities across a wide range of open-ended tasks and have extended their utility to encompass multi-modal conversations. However, existing methods encounter challenges in effectively handling both image and video understanding, particularly with limited visual tokens. In this work, we introduce Chat-UniVi, a Unified Vision-language model capable of comprehending and engaging in conver-sations involving images and videos through a unified visual representation. Specifically, we employ a set of dynamic visual tokens to uniformly represent images and videos. This representation framework empowers the model to ef-ficiently utilize a limited number of visual tokens to simul-taneously capture the spatial details necessary for images and the comprehensive temporal relationship required for videos. Moreover, we leverage a multi-scale representation, enabling the model to perceive both high-level seman-tic concepts and low-level visual details. Notably, Chat-UniVi is trained on a mixed dataset containing both images and videos, allowing direct application to tasks involving both mediums without requiring any modifications. Exten-sive experimental results demonstrate that Chat- UniVi con-sistently outperforms even existing methods exclusively de-signed for either images or videos. Code is available at https://***/PKu-Yuan Group/Chat-UniVi.

关键词： Bridges Visualization computer vision Codes Large language models Computational modeling Oral communication

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：