检索结果-内蒙古大学图书馆

Enhanced quantum state preparation via stochastic predictions of neural networks

Physical Review A 2023年第5期108卷 052418-052418页

作者： Chao-Chao Li Run-Hong He Zhao-Ming Wang College of Physics and Optoelectronic Engineering Ocean University of China Qingdao 266100 China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Science Beijing 101408 China

In pursuit of enhancing the prediction capabilities of neural networks, it has been a longstanding objective to create datasets encompassing a diverse array of samples. The purpose is to broaden the horizons of the neural network and continually strive for improved prediction accuracy during the training process, which serves as the ultimate evaluation metric. However, in this paper, we explore an intriguing avenue for enhancing algorithm effectiveness through exploiting the knowledge blindness of the neural network. Our approach centers around a machine learning algorithm utilized for preparing arbitrary quantum states in a semiconductor double quantum dot system, a system characterized by highly constrained control degrees of freedom. We artificially define the characteristics of local optima in the state preparation task. When the optimization falls into a local optimum, disturbances are introduced through stochastic prediction, which gives a chance to escape from the local optimum. Notably, unlike previous methodologies that employ reinforcement learning to identify pulse patterns, we adopt a training approach akin to supervised learning, using it to dynamically design the pulse sequence. This approach has broad applicability and improves the efficiency of the algorithm.

关键词： Quantum algorithms & computation Quantum control Quantum information processing Machine learning

来源：评论

学校读者我要写书评

暂无评论

UW-Adapter: Adapting Monocular Depth Estimation Model in Underwater Scenes

引用

IEEE Transactions on Multimedia 2025年

作者： Ye, Xinchen Chang, Yue Xu, Rui Li, Haojie DUT-RU International School of Information Science & Engineering Dalian University of Technology Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province Liaoning China Shandong University of Science and Technology College of Computer Science and Engineering China

Estimating depth maps from monocular underwater images poses one of the most challenging problems in underwater applications. Due to the lack of large-scale paired underwater color-depth datasets for effective training, existing style transfer-based and self-supervision-based approaches can improve the performance of depth estimation to some extent, but they remain unsatisfactory. Leveraging the power of massive training datasets, foundation models designed for terrestrial monocular depth estimation have demonstrated superior performance across various scenes. These models provide rich prior knowledge of 3D perception, which can be valuable for underwater depth estimation. Upon this, we introduce tunable adapters (UW-Adapter) that tailor a pre-trained foundation model specifically for underwater depth estimation, customizing it to the unique characteristics of underwater imagery. Our approach involves freezing the parameters of the pre-trained model and updating only the adapters through self-supervision. To address the complex degradation of underwater images, we propose two adapters: the transmission adapter and the high-frequency adapter. These adapters incorporate depth clues and high-frequency information as prior knowledge, thereby enhancing the performance of pre-trained model in underwater depth estimation. Experimental results demonstrate that by integrating lightweight adapters into off-the-shelf depth estimation foundation models, our method achieves superior performance across multiple datasets. © 2025 IEEE.

关键词： Underwater photography

来源：评论

学校读者我要写书评

暂无评论

The research of human interaction recognition based on fusion features of key frame feature library

引用

International Journal of Information and Communication Technology 2021年第1期18卷 57-69页

作者： Zhang, Haiyan Gao, Shangbing Faculty of Computer and Software Engineering Huaiyin Institute of Technology Huai'an China Nanjing Key Laboratory of Trusted Cloud Computing and Big Data Analysis Nanjing Xiaozhuang University Nanjing China

Some issues such as computational complexity and low recognition accuracy still exist in human interaction recognition. In order to solve the problem, the paper has proposed innovative and effective method based on fixed features of key frame feature library. Firstly, GIST feature and HOG feature were extracted from the pre-processed videos. Secondly, training videos with different kinds of actions were clustered by the K-means algorithm respectively to get key frame feature of each action for constructing key frame feature library. And similarity measure was utilised to calculate the frequency of different key frames in every interactive video, and statistical histogram representation of interactive videos were obtained. Finally, the decision level fusion was achieved by using SVM classifier based on histogram intersection kernel to obtain impressive results on UT-interaction dataset. The correct recognition rate of the proposed algorithm is 85%, which indicates that the proposed algorithm is simple and effective than others. © 2021 Inderscience Enterprises Ltd.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

XRL-SHAP-Cache:an explainable reinforcement learning approach for intelligent edge service caching in content delivery networks

引用

Science China(Information Sciences) 2024年第7期67卷 46-71页

作者： Xiaolong XU Fan WU Muhammad BILAL Xiaoyu XIA Wanchun DOU Lina YAO Weiyi ZHONG School of Software Nanjing University of Information Science and Technology School of Computing and Communications Lancaster University School of Computing Technologies Royal Melbourne Institute of Technology State Key Laboratory for Novel Software Technology Nanjing University School of Computer Science and Engineering University of New South Wales Data 61 Commonwealth Scientific and Industrial Research Organization School of Computer Science Qufu Normal University

Content delivery networks(CDNs) play a pivotal role in the modern internet infrastructure by enabling efficient content delivery across diverse geographical regions. As an essential component of CDNs, the edge caching scheme directly influences the user experience by determining the caching and eviction of content on edge servers. With the emergence of 5G technology, traditional caching schemes have faced challenges in adapting to increasingly complex and dynamic network environments. Consequently, deep reinforcement learning(DRL) offers a promising solution for intelligent zero-touch network governance. However, the blackbox nature of DRL models poses challenges in understanding and making trusting decisions. In this paper,we propose an explainable reinforcement learning(XRL)-based intelligent edge service caching approach,namely XRL-SHAP-Cache, which combines DRL with an explainable artificial intelligence(XAI) technique for cache management in CDNs. Instead of focusing solely on achieving performance gains, this study introduces a novel paradigm for providing interpretable caching strategies, thereby establishing a foundation for future transparent and trustworthy edge caching solutions. Specifically, a multi-level cache scheduling framework for CDNs was formulated theoretically, with the D3QN-based caching scheme serving as the targeted interpretable model. Subsequently, by integrating Deep-SHAP into our framework, the contribution of each state input feature to the agent's Q-value output was calculated, thereby providing valuable insights into the decision-making process. The proposed XRL-SHAP-Cache approach was evaluated through extensive experiments to demonstrate the behavior of the scheduling agent in the face of different environmental *** results demonstrate its strong explainability under various real-life scenarios while maintaining superior performance compared to traditional caching schemes in terms of cache hit ratio, quality of service(QoS),a

关键词： deep reinforcement learning (DRL) explainable artificial intelligence (XAI) multi-level cache content delivery network (CDN) D3QN algorithm Deep-SHAP

来源：评论

学校读者我要写书评

暂无评论

A Deep Understanding Video Q&A System for Film Education in Acting Department

A Deep Understanding Video Q&A System for Film Education in ...

引用

Intelligent Education and Intelligent Research (IEIR), International Conference on

作者： Zhengqian Wu Ruizhe Li Jiahao Guo Zhongyuan Wang Chao Liang Hubei Key Laboratory of Multimedia and Network Communication Engineering National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University

Recently, advancements in artificial intelligence technology have greatly influenced the field of education, particularly in the area of intelligent homework assistance. However, current approaches are primarily designed for procedural and logical tasks and often lack comprehension abilities. This limitation is particularly evident when it comes to multi-hop and continuous tasks. To address this challenge, the integration of Large Language Model (LLM) has significantly enhanced the capability of AI systems to handle multi-hop and highly interconnected inputs. In this study, we focus on the learning needs of students in Acting Department, specifically their study of movies and the significance of classic movie videos in their learning process. However, assessing deep comprehension of classic movies poses its own challenges. To overcome these challenges, we develop a quiz system utilizing Knowledge Graphs (KG) and LLM to facilitate a deeper understanding of classic films. The generation of video quiz pairs is achieved through the use of Automatic Speech Recognition (ASR) technology, which leverages movie subtitles for question generation. For answering these questions, we employ techniques KG and LLM to process questions and retrieve corresponding answers. The proposed method achieves good performance in Deep Video Understanding (DVU) task of NIST TRECVID, demonstrating its effectiveness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detecting Memory Errors in Python Native Code by Tracking Object Lifecycle with Reference Count

Detecting Memory Errors in Python Native Code by Tracking Ob...

引用

IEEE International Conference on Automated software engineering (ASE)

作者： Xutong Ma Jiwei Yan Hao Zhang Jun Yan Jian Zhang State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences Technology Center of Software Engineering Institute of Software Chinese Academy of Sciences

Third-party Python modules are usually implemented as binary extensions by using native code (C/C++) to provide additional features and runtime acceleration. In native code, the heap-allocated PyObjects are managed by the reference counting mechanism provided in Python/C APIs for automatic reclaiming. Hence, improper refcount manipulations can lead to memory leaks and use-after-free problems, and cannot be detected by simply pairing the occurrence of source and sink points. To detect such problems, state-of-the-art approaches have made groundbreaking contributions to identifying inappropriate final refcount values before returning from native code to Python. However, not all problems can be exposed at the end of a path. To detect those hidden in the middle of a path in native code, it is also crucial to track the lifecycle state of PyObjects through the refcount and lifecycle operations in API calls. To achieve this goal, we propose the PyObject State Transition Model (PSTM) recording the lifecycle states and refcount values of PyObjects to describe the effects of Python/C API calls and pointer operations. We track state transitions of PyObjects with symbolic execution based on the model, and report problems when a statement triggers a transition to buggy states. The program state is also expanded to handle pointer nullity checks and smart pointers of PyObjects. We conduct experiments on 12 open-source projects and detect 259 real problems out of 280 reports, which is twice as many bugs as state-of-the-art approaches. We submit 168 real bugs to those active projects, and 106 issues are either confirmed or resolved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TRANSFORMER-PATCHER: ONE MISTAKE WORTH ONE NEURON 11

TRANSFORMER-PATCHER: ONE MISTAKE WORTH ONE NEURON

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Huang, Zeyu Shen, Yikang Zhang, Xiaofeng Zhou, Jie Rong, Wenge Xiong, Zhang State Key Laboratory of Software Development Environment Beihang University China Sino-French Engineer School Beihang University China School of Computer Science and Engineering Beihang University China Mila University of Montreal Canada WeChat AI Tencent Inc. China

Large Transformer-based Pretrained Language Models (PLMs) dominate almost all Natural Language Processing (NLP) tasks. Nevertheless, they still make mistakes from time to time. For a model deployed in an industrial environment, fixing these mistakes quickly and robustly is vital to improve user experiences. Previous works formalize such problems as Model Editing (ME) and mostly focus on fixing one mistake. However, the one-mistake-fixing scenario is not an accurate abstraction of the real-world challenge. In the deployment of AI services, there are ever-emerging mistakes, and the same mistake may recur if not corrected in time. Thus a preferable solution is to rectify the mistakes as soon as they appear nonstop. Therefore, we extend the existing ME into Sequential Model Editing (SME) to help develop more practical editing methods. Our study shows that most current ME methods could yield unsatisfying results in this scenario. We then introduce Transformer-Patcher, a novel model editor that can shift the behavior of transformer-based models by simply adding and training a few neurons in the last Feed-Forward Network layer. Experimental results on both classification and generation tasks show that Transformer-Patcher can successively correct up to thousands of errors (Reliability) and generalize to their equivalent inputs (Generality) while retaining the model's accuracy on irrelevant inputs (Locality). Our method outperforms previous fine-tuning and HyperNetwork-based methods and achieves state-of-the-art performance for Sequential Model Editing (SME). The code is available at https://***/ZeroYuHuang/Transform er-Patcher. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

SJA: Server-driven Joint Adaptation of Loss and Bitrate for Multi-Party Realtime Video Streaming 42

SJA: Server-driven Joint Adaptation of Loss and Bitrate for ...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Shen, Kai Zhang, Dayou Zhu, Zi Zhang, Lei Wang, Fangxin Wang, Dan The Chinese University of HongKong The Future Network of Intelligence Institute Shenzhen China The Chinese University of HongKong School of Science and Engineering Shenzhen China Shenzhen University College of Computer Science and Software Engineering China Peng Cheng Laboratory China The Guangdong Provincial Key Laboratory of Future Networks of Intelligence China The Hong Kong Polytechnic University Department of Computing Hong Kong

ISBN: (纸本)9798350334142

The outbreak of COVID-19 has dramatically promoted the explosive proliferation of multi-party realtime video streaming (MRVS) services, represented by Zoom and Microsoft Teams. Different from Video-on-Demand (VoD) or live streaming, MRVS enables all-to-all realtime video communication, bringing significant challenges to service providing. First, unreliable network transmission can cause network loss, resulting in delay increase and visual quality degradation. Second, the transformation from two-party to multi-party communication makes resource scheduling much more difficult. Moreover, optimizing the overall QoE requires a global coordination, which is quite challenging given the various impact factors such as bitrate and *** this paper, we propose the SJA framework, which is, to our best knowledge, the first server-driven joint loss and bitrate adaptation framework in multi-party realtime video streaming services towards maximized QoE. We comprehensively design an appropriate QoE model for MRVS services to capture the interplay among perceptual quality, variations, bitrate mismatch, loss damage, and streaming delay. We mathematically formulate the QoE maximization problem in MRVS services. A Lyapunov-based relaxation and the SJA algorithm are further designed to address the optimization problem with close-to-optimal performance. Evaluations show that our framework can outperform the SOTA solutions by 18.4% ∼ 46.5%. © 2023 IEEE.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

SEMDA: Secure and Efficient Multidimensional Data Aggregation in Smart Grid without a Trusted Third Party

引用

Security and Communication Networks 2023年第1期2023卷

作者： Song, Zichao Zhong, Weidong Zhou, Tanping Chen, Dong Ding, Yujie Yang, Xiaoyuan College of Cryptography Engineering Engineering University of PAP Xi'an710086 China Key Laboratory of PAP for Cryptology and Information Security Xi'an710086 China TCA Laboratory State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing100080 China

Smart grids are a combination of traditional power system engineering as well as information and communications technology. Smart grid terminals provide convenient services to users by aggregating their data in real time. However, terminals can derive user privacy information from real-time data on smart devices. Therefore, security data aggregation has been widely studied in the field of smart grid. Most existing schemes are one-dimensional data aggregation or rely on a trusted third party. In reality, multidimensional data (such as a user's electricity consumption or user's main usage time, etc.) makes sense for terminals to flexibly adjust supply and demand strategies. In this paper, we propose an efficient and secure multidimensional data aggregation scheme that supports batch validation without a trusted third party. Firstly, we apply the Chinese remainder theorem to encode the user's multidimensional data and realize the independence of each dimension in terminal decryption. Secondly, we adopt a secure key negotiation protocol that does not require a trusted third party. Finally, based on paillier homomorphic encryption and bilinear pairing, we construct an encryption scheme that can reuse the key and blind factor and support batch verification. The analysis results show that our scheme is secure for users' privacy protection. Experimental results show that, compared with existing 1 dimensional aggregation schemes, our scheme has almost no growth in computational overhead for terminal decryption. © 2023 Zichao Song et al.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

WaterDiffusion: Learning a Prior-involved Unrolling Diffusion for Joint Underwater Saliency Detection and Visual Restoration 39

WaterDiffusion: Learning a Prior-involved Unrolling Diffusio...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Chang, Laibin Wang, Yunke Deng, Longxiang Du, Bo Xu, Chang School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China School of Computer Science The University of Sydney Sydney Australia

ISBN: (纸本)157735897X

Underwater salient object detection (USOD) plays a pivotal role in various vision-based marine exploration tasks. However, existing USOD techniques face the dilemma of object mislocalization and imprecise boundaries due to the complex underwater environment. The quality degradation of raw underwater images (caused by selective absorption and medium scattering) makes it challenging to perform instance detection directly. One conceivable approach involves initially removing visual disturbances through underwater image enhancement (UIE), followed by saliency detection. However, this two-stage approach neglects the potential positive impact of the restoration procedure on saliency detection due to it executes in a cascade. Based on this insight, we propose a generalized prior-involved diffusion model, called WaterDiffusion for collaborative underwater saliency detection and visual restoration. Specifically, we first propose a revised self-attention joint diffusion, which embeds dynamic saliency masks into the diffusive network as latent features. By extending the underwater degradation prior into the multiscale decoder, we innovatively exploit optical transmission maps to aid in localizing underwater salient objects. Then, we further design a gate-guided binary indicator to select either normalized or raw channels for improving feature generalization. Finally, the Half-quadratic Splitting is introduced into the unfolding sampling to refine saliency masks iteratively. Comprehensive experiments demonstrate the superior performance of WaterDiffusion over state-of-the-art methods in both quantitative and qualitative evaluations. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Underwater photography

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：