检索结果-内蒙古大学图书馆

Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding

学校读者我要写书评

暂无评论

Rethinking the Video Sampling and Reasoning Strategies for T...

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Zhu, Jiahao Liu, Daizong Zhou, Pan Di, Xing Cheng, Yu Yang, Song Xu, Wenzheng Xu, Zichuan Wan, Yao Sun, Lichao Xiong, Zeyu Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology China ProtagoLabs Inc Microsoft Research Wangxuan Institute of Computer Technology Peking University China Beijing Institute of Technology China School of Sichuan University China Dalian University of Technology China Lehigh University United States School of Computer Sci. & Tech. Huazhong University of Science and Technology China

Temporal sentence grounding (TSG) aims to identify the temporal boundary of a specific segment from an untrimmed video by a sentence query. All existing works first utilize a sparse sampling strategy to extract a fixed number of video frames and then conduct multimodal interactions with query sentence for reasoning. However, we argue that these methods have overlooked two indispensable issues: 1) Boundary-bias: The annotated target segment generally refers to two specific frames as corresponding start and end timestamps. The video downsampling process may lose these two frames and take the adjacent irrelevant frames as new boundaries. 2) Reasoning-bias: Such incorrect new boundary frames also lead to the reasoning bias during frame-query interaction, reducing the generalization ability of model. To alleviate above limitations, in this paper, we propose a novel Siamese Sampling and Reasoning Network (SSRN) for TSG, which introduces a siamese sampling mechanism to generate additional contextual frames to enrich and refine the new boundaries. Specifically, a reasoning strategy is developed to learn the inter-relationship among these frames and generate soft labels on boundaries for more accurate frame-query reasoning. Such mechanism is also able to supplement the absent consecutive visual semantics to the sampled sparse frames for fine-grained activity understanding. Extensive experiments demonstrate the effectiveness of SSRN on three challenging datasets. © 2022 Association for Computational Linguistics.

关键词： Semantics

Learning Adaptive and View-Invariant Vision Transformer with Multi-Teacher Knowledge Distillation for Real-Time UAV Tracking

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, You Li, Yongxin Liu, Mengyuan Wang, Xucheng Yang, Xiangyang Ye, Hengzhou Zeng, Dan Zhao, Qijun Li, Shuiwang College of Computer Science and Engineering Guilin University of Technology Guilin541006 China Guangxi Key Laboratory of Embedded Technology and Intelligent System Guilin541006 China School of Computer Science Fudan University Shanghai200082 China School of Artificial Intelligence Sun Yat-sen University Zhuhai510275 China College of Computer Science Sichuan University Chengdu610017 China

Visual tracking has made significant strides due to the adoption of transformer-based models. Most state-of-the-art trackers struggle to meet real-time processing demands on mobile platforms with constrained computing resources, particularly for real-time unmanned aerial vehicle (UAV) tracking. To achieve a better balance between performance and efficiency, we introduce AVTrack, an adaptive computation framework designed to selectively activate transformer blocks for real-time UAV tracking. The proposed Activation Module (AM) dynamically optimizes the ViT architecture by selectively engaging relevant components, thereby enhancing inference efficiency without significant compromise to tracking performance. Furthermore, to tackle the challenges posed by extreme changes in viewing angles often encountered in UAV tracking, the proposed method enhances ViTs’ effectiveness by learning view-invariant representations through mutual information (MI) maximization. Two effective design principles are proposed in the AVTrack. Building on it, we propose an improved tracker, dubbed AVTrack-MD, which introduces the novel MI maximization-based multi-teacher knowledge distillation (MD) framework. It harnesses the benefits of multiple teachers, specifically the off-the-shelf tracking models from the AVTrack, by integrating and refining their outputs, thereby guiding the learning process of the compact student network. Specifically, we maximize the MI between the softened feature representations from the multi-teacher models and the student model, leading to improved generalization and performance of the student model, particularly in noisy conditions. Extensive experiments on multiple UAV tracking benchmarks demonstrate that AVTrack-MD not only achieves performance comparable to the AVTrack baseline but also reduces model complexity, resulting in a significant 17% increase in average tracking speed. Codes is be available at https://***/wuyou3474/AVTrack. Copyright © 2024, The

关键词： Teaching

Accident Impact Prediction based on a deep convolutional and recurrent neural network model

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sajadi, Pouyan Qorbani, Mahya Moosavi, Sobhan Hassannayebi, Erfan Department of Industrial Engineering Sharif University of Technology Tehran Iran School of Industrial and System Engineering Georgia Institute of Technology AtlantaGA United States Department of Computer Science and Engineering Ohio State University ColumbusOH United States

Traffic accidents pose a significant threat to public safety, resulting in numerous fatalities, injuries, and a substantial economic burden each year. The development of predictive models capable of real-time forecasting of post-accident impact using readily available data can play a crucial role in preventing adverse outcomes and enhancing overall safety. However, existing accident predictive models encounter two main challenges: first, reliance on either costly or non-real-time data, and second the absence of a comprehensive metric to measure post-accident impact accurately. To address these limitations, this study proposes a deep neural network model known as the cascade model. It leverages readily available real-world data from Los Angeles County to predict post-accident impacts. The model consists of two components: Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN). The LSTM model captures temporal patterns, while the CNN extracts patterns from the sparse accident dataset. Furthermore, an external traffic congestion dataset is incorporated to derive a new feature called the "accident impact" factor, which quantifies the influence of an accident on surrounding traffic flow. Extensive experiments were conducted to demonstrate the effectiveness of the proposed hybrid machine learning method in predicting the post-accident impact compared to state-of-the-art baselines. The results reveal a higher precision in predicting minimal impacts (i.e., cases with no reported accidents) and a higher recall in predicting more significant impacts (i.e., cases with reported accidents). Copyright © 2024, The Authors. All rights reserved.

关键词： Traffic congestion

Auto-scalable and fault-tolerant load balancing mechanism for cloud computing based on the proof-of-work election

学校读者我要写书评

暂无评论

science China(Information sciences) 2022年第1期65卷 131-146页

作者： Xiaoqin FENG Jianfeng MA Shaobin LIU Yinbin MIAO Ximeng LIU School of Cyber Engineering Xidian University State Key Laboratory of Cryptology Shaanxi Key Laboratory of Network and System Security Xidian University College of Mathematics and Computer Science Fuzhou University

Load balancing mechanism in technologies such as cloud computing has provided a huge opportunity for the development of large-scale projects. Although the conventional view is to build mechanisms that adopt a dynamic load balancing strategy, existing strategies cannot automatically scale platform(network) servers(nodes) to adapt for dynamic requests, but only guarantee load balancing for the pre-deployed nodes, thereby increasing resource consumption and decreasing networks' efficiency. We contend that existing load balancing mechanisms are inadequate for deploying dynamic applications. In this regard, we first adopt both load balancing and cloud computing virtualization technologies to modularly design a load balancing mechanism that provides a dynamically auto-scalable solution for large-scale and dynamic computing scenarios. Furthermore, we adopt the proof-of-work consensus, for a novel use during the lifecycle of master nodes in case of system failure caused by a failed master node, to demonstrate a fault-tolerant load balancing mechanism. We theoretically evaluate the security requirement of our mechanism and analyze its performance. Experimental results show that the mechanism supports auto-scalability and has a better performance compared to existing mechanisms such as the ordinary cluster.

关键词： cloud computing load balancing auto-scalable proof-of-work fault-tolerant

Up to 320-GBaud Coherent Optical system Based on Broadband Segmented TFLN I/Q Modulator

学校读者我要写书评

暂无评论

Up to 320-GBaud Coherent Optical System Based on Broadband S...

Asia Communications and Photonics Conference and Exhibition (ACP)

作者： Lingjun Zhou Xiansong Fang Yixiao Zhu Junbo Zhu Yunchen Li Xiaomin Nie Xian Zhou Chuanchuan Yang Lei Wang Weisheng Hu Ke Li Zhixue He Fan Zhang School of Electronic and Computer Engineering Peking University Shenzhen China Pengcheng Laboratory Shenzhen China State Key Laboratory of Advanced Optical Communication System and Networks School of Electronics Peking University Beijing China State Key Laboratory of Advanced Optical Communication System and Networks Shanghai Jiao Tong University Shanghai China School of Computer & Communication Engineering University of Science and Technology Beijing Beijing China

We demonstrate the record 320-GBd single-polarization QPSK and 300-GBd dual-polarization QPSK signal generation and intradyne coherent detection. This result is achieved with a novel broadband segmented TFLN I/Q modul... 详细信息

ISBN: (数字)9798350379266

ISBN: (纸本)9798350379273

关键词： Partial response signaling Phase shift keying Optical recording Optical device fabrication Lithium Optical fiber communication Encoding Broadband communication Optical modulation Photonics

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Xiaogeng Li, Minghui Wang, Haoyu Hu, Shengshan Ye, Dengpan Jin, Hai Wu, Libing Xiao, Chaowei School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab China School of Cyber Science and Engineering Wuhan University China Arizona State University United States

Deep neural networks are proven to be vulnerable to backdoor attacks. Detecting the trigger samples during the inference stage, i.e., the test-time trigger sample detection, can prevent the backdoor from being triggered. However, existing detection methods often require the defenders to have high accessibility to victim models, extra clean data, or knowledge about the appearance of backdoor triggers, limiting their practicality. In this paper, we propose the test-time corruption robustness consistency evaluation (TeCo)1, a novel test-time trigger sample detection method that only needs the hard-label outputs of the victim models without any extra information. Our journey begins with the intriguing observation that the backdoor-infected models have similar performance across different image corruptions for the clean images, but perform discrepantly for the trigger samples. Based on this phenomenon, we design TeCo to evaluate test-time robustness consistency by calculating the deviation of severity that leads to predictions' transition across different corruptions. Extensive experiments demonstrate that compared with state-of-the-art defenses, which even require either certain information about the trigger types or accessibility of clean data, TeCo outperforms them on different backdoor attacks, datasets, and model architectures, enjoying a higher AUROC by 10% and 5 times of stability. Copyright © 2023, The Authors. All rights reserved.

关键词： Crime

An Adaptive Deep Learning Model for Crop Yield Prediction

学校读者我要写书评

暂无评论

An Adaptive Deep Learning Model for Crop Yield Prediction

computer, Communication and Control (IC4), International Conference on

作者： Ashwin Gadupudi Rudra Yamini Rani B Jayaram Nipun Sharma Jotiram Krishna Deshmukh Pundru Chandra Shaker Reddy Computer Science California State University Fresno United States of America (USA) Information Technology VNR Vignana Jyothi Institute of Engineering and Technology Hyderabad India Computer Science and Business System RMK Engineering College Kavaraipettai Tamil Nadu India Electronics and Communication Engineering Presidency University Bangalore Karnataka India Instrumentation Engineering Bharati Vidyapeeth College of Engineering Navi Mumbai India School of Computer Science and Artificial Intelligence SR University Warangal Telangana India

Agriculture is the study and practice of raising plants and animals for human consumption. Approximately 60.45% of India’s land is devoted to farming, making it the country’s second largest economic sector. Agriculture and the related agro-industrial sector are crucial to India’s economy. Soil components (such as nitrogen-phosphorus &potassium), crop rotation, soil-moisture, air and soil-temperatures, rainfall, and other environmental factors all play important roles in successful farming. One piece of current evidence in this area is a technique that utilizes machine-learning (ML) strategies like Random-Forest (RF), Decision-Tree (DT), and ANN to pick the best crop. In this study, we employ deep learning approaches to improve the suggested model, and together with crop prediction, we obtain clear information regarding the quantities of soil attributes requisite, along with their individual costs. It’s more precise than the current model. By analyzing the data provided, it aids farmers in making informed business decisions. Predicting a proper yield requires thinking about the land’s climate and soil. The goal is to introduce a Python-based system that makes use of strategic thinking to anticipate the most productive harvest under specific conditions while keeping costs to a minimum. While LSTM &RNN are employed as deep-learning((DL)-strategies in this work, SVM is used as the ML-strategy.

关键词：

OneForecast: A Universal Framework for Global and Regional Weather Forecasting

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Gao, Yuan Wu, Hao Shu, Ruiqi Dong, Huanshuo Xu, Fan Chen, Rui Yan, Yibo Wen, Qingsong Hu, Xuming Wang, Kun Wu, Jiahao Li, Qing Xiong, Hui Huang, Xiaomeng Department of Earth System Science Ministry of Education Key Laboratory for Earth System Modeling Institute for Global Change Studies Tsinghua University China TEG Tencent China Department and Computer and Science University of Science and Technology of China China Institute for Interdisciplinary Information Sciences Tsinghua University China Department of Computer Science and Engineering The HongKong University of Science and Technology Hong Kong AI Thrust The Hong Kong University of Science and Technology Guangzhou China Squirrel Ai Learning China School of Computer Science and Engineering Nanyang Technological University Singapore Department of Computing The Hong Kong Polytechnic University Hong Kong

Accurate weather forecasts are important for disaster prevention, agricultural planning, and water resource management. Traditional numerical weather prediction (NWP) methods offer physically interpretable high-accuracy predictions but are computationally expensive and fail to fully leverage rapidly growing historical data. In recent years, deep learning methods have made significant progress in weather forecasting, but challenges remain, such as balancing global and regional high-resolution forecasts, excessive smoothing in extreme event predictions, and insufficient dynamic system modeling. To address these issues, this paper proposes a global-regional nested weather forecasting framework based on graph neural networks (GNNs). By combining a dynamic system perspective with multi-grid theory, we construct a multi-scale graph structure and densify the target region to capture local high-frequency features. We introduce an adaptive information propagation mechanism, using dynamic gating units to deeply integrate node and edge features for more accurate extreme event forecasting. For high-resolution regional forecasts, we propose a neural nested grid method to mitigate boundary information loss. Experimental results show that the proposed method performs excellently across global to regional scales and short-term to long-term forecasts, especially in extreme event predictions (e.g., typhoons), significantly improving forecast accuracy. Our codes are available at https://***/YuanGao-YG/OneForecast. Copyright © 2025, The Authors. All rights reserved.

关键词： Weather forecasting

Masked Transformer-based Multi-GAN for 5G Core Network KPI Anomaly Detection

学校读者我要写书评

暂无评论

Masked Transformer-based Multi-GAN for 5G Core Network KPI A...

International Conference on computer Supported Cooperative Work in Design

作者： Enze Zhao Peng Li Zhang Cheng Wenmao Liu Lei Nie Haizhou Bao Qin Liu Kai Zhang School of Computer Science and Technology Wuhan University of Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System China NSFOCUS Technologies Group Co. Ltd. School of Cyber Science and Engineering Wuhan University China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

The fifth generation (5G) network is a crucial foundation for the industrial Internet. Key performance indicator (KPI) anomaly detection in the 5G core network (5GC) plays a pivotal role in 5G applications. Some researchers have introduced Generative Adversarial Networks (GAN)-based techniques to detect anomalies. However, these methods remain limited, such as pattern collapse. In this paper, we propose MTMG, a Masked Transformer-based Multi-GAN model, to achieve highly accurate and robust anomaly detection. We use Transformer to learn the associations between data better. Specifically, MTMG employs multiple generators and a discriminator to deflect the pattern collapse dilemma. In addition, we introduce the mask mechanism to learn the normal distribution of data better and prevent the model degradation caused by anomalies in the training set. We also adopt a root cause strategy to locate the anomalies. Experimental results demonstrate that our model outperforms the baselines significantly in terms of detection performance.

关键词： 5G mobile communication Computational modeling Key performance indicator Transformer cores Gaussian distribution Transformers Generative adversarial networks