检索结果-内蒙古大学图书馆

Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction 39

学校读者我要写书评

暂无评论

Rethinking Pseudo-Label Guided Learning for Weakly Supervise...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Quan Qi, Yuxin Tang, Xi Yuan, Rui Lin, Xi Zhang, Ke Yuan, Chun Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory of Integrated Administration Technologies for Information Security Shanghai China School of Computer Science and Technology Soochow University Suzhou China

ISBN: (纸本)157735897X

Pseudo-label learning methods have been widely applied in weakly-supervised temporal action localization. Existing works directly utilize weakly-supervised base model to generate instance-level pseudo-labels for training the fully-supervised detection head. We argue that the noise in pseudo-labels would interfere with the learning of fully-supervised detection head, leading to significant performance leakage. Issues with noisy labels include:(1) inaccurate boundary localization;(2) undetected short action clips;(3) multiple adjacent segments incorrectly detected as one segment. To target these issues, we introduce a two-stage noisy label learning strategy to harness every potential useful signal in noisy labels. First, we propose a frame-level pseudo-label generation model with a context-aware denoising algorithm to refine the boundaries. Second, we introduce an online-revised teacher-student framework with a missing instance compensation module and an ambiguous instance correction module to solve the short-action-missing and many-to-one problems. Besides, we apply a high-quality pseudo-label mining loss in our online-revised teacher-student framework to add different weights to the noisy labels to train more effectively. Our model outperforms the previous state-of-the-art method in detection accuracy and inference speed greatly upon the THUMOS14 and ActivityNet v1.2 benchmarks. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Semi-supervised learning

A Blockchain-Integrated AI Framework for Enhancing Energy Efficiency and Sustainability in Smart Grids

学校读者我要写书评

暂无评论

Procedia computer science 2025年 258卷 2302-2311页

作者： Kajal Singh S.B. Goyal Anand Singh Rajawat Hayyan Nassar Waked Business Analyst Barclays Bank 400 Jefferson Park Whippany NJ 07981 USA Faculty of Information Technology City University Petaling Jaya 46100 Malaysia School of Computer Science & Engineering Sandip University Nashik Maharashtra India City Graduate School City University Petaling Jaya 46100 Malaysia

In the pursuit of energy efficiency and sustainability in smart grids, leveraging blockchain integration with artificial intelligence could provide a disruptive paradigm that offers numerous benefits. In this paper, a new framework is presented using blockchain with AI in order to provide optimal energy management and sustainable smart grid. The new model combines blockchain, which provides a secure an unchangeable log of transactions; with algorithms based on AI in order to analyse and predict patterns of electricity consumption as well as provide demand response control (the ability needed by users who want to be active prosumers) accompanied by optimization of the energy delivery chain. Blockchain enforces transparency and trust among multiple stakeholders, it helps verify data integrity across entities involved in a transaction to prevent any kind of tampering or fraud. At the same time, AI-driven insights allow real-time data to inform energy systems and lead with scheduling dynamic changes in order to prevent grid losses that would result in wasted energy. The inclusion of these technologies is what helps to solve the major problems such as energy theft, data security and also reduce inefficient use of power. Indeed, this integration helps reduce operational costs and enables a shift towards cleaner and sustainable sources of energy. Simulations and real-world use cases are performed to evaluate the effectiveness of the proposed framework in improving energy efficiency for smart grid towards more sustainability.

关键词： Blockchain Technology Artificial Intelligence (AI) Smart Grids Energy Efficiency Sustainability Decentralized Systems

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

A Review of Human Emotion Synthesis Based on Generative Technology

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Fei Li, Yukan Xie, Yifan He, Ying Zhang, Yi Ren, Hongwei Liu, Zhou Yao, Wei Ren, Fuji Yu, Fei Richard Ni, Shiguang Shenzhen China Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangzhou China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen China School of Information Technology Carleton University Canada

Human emotion synthesis is a crucial aspect of affective computing. It involves using computational methods to mimic and convey human emotions through various modalities, with the goal of enabling more natural and effective human-computer interactions. Recent advancements in generative models, such as Autoencoders, Generative Adversarial Networks, Diffusion Models, Large Language Models, and Sequence-to-Sequence Models, have significantly contributed to the development of this field. However, there is a notable lack of comprehensive reviews in this field. To address this problem, this paper aims to address this gap by providing a thorough and systematic overview of recent advancements in human emotion synthesis based on generative models. Specifically, this review will first present the review methodology, the emotion models involved, the mathematical principles of generative models, and the datasets used. Then, the review covers the application of different generative models to emotion synthesis based on a variety of modalities, including facial images, speech, and text. It also examines mainstream evaluation metrics. Additionally, the review presents some major findings and suggests future research directions, providing a comprehensive understanding of the role of generative technology in the nuanced domain of emotion synthesis. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

Security analysis on "EAKE-WC: Authenticated Key Exchange Protocol for Wearable Computing" 23

学校读者我要写书评

暂无评论

Security analysis on "EAKE-WC: Authenticated Key Exchange Pr...

Proceedings of the 2023 International Conference on Intelligent Computing and Its Emerging Applications

作者： Zahid Ghaffar Khalid Mahmood Muhammad Farooq Khalid Yahya Chien-Ming Chen Shehzad Ashraf Chaudhary Graduate School of Engineering Science and Technology National Yunlin University of Science and Technology Yunlin Taiwan Graduate School of Intelligent Data Science National Yunlin University of Science and Technology Yunlin Taiwan Department of Mathematics and Statistics Abu Dhabi University Abu Dhabi United Arab Emirates Department of Mechatronics Engineering Istanbul Gelisim University Istanbul Turkey College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China Department of Computer Science and Information Technology Abu Dhabi University Abu Dhabi United Arab Emirates

Exploring Collaborative Distributed Diffusion-Based AI-Generated Content (AIGC) in Wireless Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Du, Hongyang Zhang, Ruichen Niyato, Dusit Kang, Jiawen Xiong, Zehui Kim, Dong In Shen, Xuemin Poor, H. Vincent The School of Computer Science and Engineering The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The School of Computer Science and Engineering Nanyang Technological University Singapore The School of Computer and Information Technology Beijing Jiaotong University Beijing100044 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 Sungkyunkwan University Suwon16419 Korea Republic of The Department of Electrical and Computer Engineering University of Waterloo Canada The Department of Electrical and Computer Engineering Princeton University PrincetonNJ08544 United States

Driven by advances in generative artificial intelligence (AI) techniques and algorithms, the widespread adoption of AI-generated content (AIGC) has emerged, allowing for the generation of diverse and high-quality content. Especially, the diffusion model-based AIGC technique has been widely used to generate content in a variety of modalities. However, the real-world implementation of AIGC models, particularly on resource-constrained devices such as mobile phones, introduces significant challenges related to energy consumption and privacy concerns. To further promote the realization of ubiquitous AIGC services, we propose a novel collaborative distributed diffusion-based AIGC framework. By capitalizing on collaboration among devices in wireless networks, the proposed framework facilitates the efficient execution of AIGC tasks, optimizing edge computation resource utilization. Furthermore, we examine the practical implementation of the denoising steps on mobile phones, the impact of the proposed approach on the wireless network-aided AIGC landscape, and the future opportunities associated with its real-world integration. The contributions of this paper not only offer a promising solution to the existing limitations of AIGC services but also pave the way for future research in device collaboration, resource optimization, and the seamless delivery of AIGC services across various devices. Our code is available at https://***/HongyangDu/DistributedDiffusion. © 2023, CC BY.

关键词： Wireless networks

Hybrid Routing in FSO/RF Space-Air-Ground Integrated Network

学校读者我要写书评

暂无评论

Hybrid Routing in FSO/RF Space-Air-Ground Integrated Network

IEEE Conference on Global Communications (GLOBECOM)

作者： Qi Guo Fengxiao Tang Nei Kato Graduate School of Information Sciences (GSIS) Tohoku University Sendai Japan School of Computer Science and Engineering Central South University Changsha China GSIS Tohoku University Sendai Japan

Space-air-ground integrated network (SAGIN) is a promising network architecture for next-generation wireless networks, which combines satellite networks, aerial networks, and terrestrial networks to enable ubiquitous global network services to ground users and improve connectivity for wide deployment wireless applications. Also, free-space optical (FSO) communication with the advantages of low deployment cost, energy efficiency, and extremely high-speed data-delivering capability has attracted more attention recently. However, data transmission efficiency in SAGIN is still limited by the dynamic time-varying network topology and data transmission link connection. In this paper, we construct an FSO/radio frequency (RF) space-air-ground integrated network to enable large-scale and high-speed data transmission as well as degrade the burden of terrestrial networks. In addition, a deep-Q network-based reinforcement learning with an experience replay memory mechanism is proposed to execute dynamic hybrid routing by evaluated rewards. The simulation results show that the proposal achieves significant network performance compared with baseline methods.

关键词：

Long-term Frame-Event Visual Tracking: Benchmark Dataset and Baseline

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Xiao Huang, Ju Wang, Shiao Tang, Chuanming Jiang, Bo Tian, Yonghong Tang, Jin Luo, Bin School of Computer Science and Technology Anhui University Hefei China University of Chinese Academy of Sciences Beijing China Institute of Optics and Electronics CAS Chengdu China Peng Cheng Laboratory Shenzhen China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China School of Electronic and Computer Engineering Shenzhen Graduate School Peking University China

Current event-/frame-event based trackers undergo evaluation on short-term tracking datasets, however, the tracking of real-world scenarios involves long-term tracking, and the performance of existing tracking algorithms in these scenarios remains unclear. In this paper, we first propose a new long-term and large-scale frame-event single object tracking dataset, termed FELT. It contains 742 videos and 1,594,474 RGB frames and event stream pairs and has become the largest frame-event tracking dataset to date. We re-train and evaluate 15 baseline trackers on our dataset for future works to compare. More importantly, we find that the RGB frames and event streams are naturally incomplete due to the influence of challenging factors and spatially sparse event flow. In response to this, we propose a novel associative memory Transformer network as a unified backbone by introducing modern Hopfield layers into multi-head self-attention blocks to fuse both RGB and event data. Extensive experiments on RGB-Event (FELT), RGB-Thermal (RGBT234, LasHeR), and RGB-Depth (DepthTrack) datasets fully validated the effectiveness of our model. The dataset and source code can be found at https://***/Event-AHU/FELT_SOT_Benchmark. Copyright © 2024, The Authors. All rights reserved.

关键词： Large datasets

Comparative analysis of deep learning models for detecting face mask 7

学校读者我要写书评

暂无评论

Comparative analysis of deep learning models for detecting f...

7th International Conference on computer science and Computational Intelligence, CSCI 2022

作者： Ramadhan, M. Vickya Muchtar, Kahlil Nurdin, Yudha Oktiana, Maulisa Fitria, Maya Maulina, Novi Elwirehardja, Gregorius Natanael Pardamean, Bens Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh23111 Indonesia Universitas Syiah Kuala Banda Aceh23111 Indonesia Microbiology Department School of Medicine Universitas Syiah Kuala Banda Aceh23111 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program-Master of Computer Science Program Bina Nusantara University Jakarta 11480 Indonesia

The spread of Corona Virus Disease 19 (COVID-19) in Indonesia is still relatively high and has not shown a significant decrease. One of the main reasons is due to the lack of supervision on the implementation of health protocols such as wearing masks in daily activities. Recently, state-of-The-Art algorithms were introduced to automate face mask detection. To be more specific, the researchers developed various kinds of architectures for the detection of masks based on computer vision methods. This paper aims to evaluate well-known architectures, namely the ResNet50, VGG11, InceptionV3, EfficientNetB4, and YOLO (You Only Look Once) to recommend the best approach in this specific field. By using the MaskedFace-Net dataset, the experimental results showed that the EfficientNetB4 architecture has better accuracy at 95.77% compared to the YOLOv4 architecture of 93.40%, InceptionV3 of 87.30%, YOLOv3 of 86.35%, ResNet50 of 84.41%, VGG11 of 84.38%, and YOLOv2 of 78.75%, respectively. It should be noted that particularly for YOLO, the model was trained using a collection of MaskedFace-Net images that had been pre-processed and labelled for the task. The model was initially able to train faster with pre-Trained weights from the COCO dataset thanks to transfer learning, resulting in a robust set of features expected for face mask detection and classification. © 2022 Elsevier B.V.. All rights reserved.

关键词： Face recognition