检索结果-内蒙古大学图书馆

Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition 24

学校读者我要写书评

暂无评论

Generating Action-conditioned Prompts for Open-vocabulary Vi...

32nd ACM International Conference on Multimedia, MM 2024

作者： Jia, Chengyou Luo, Minnan Chang, Xiaojun Dang, Zhuohang Han, Mingfei Wang, Mengmeng Dai, Guang Dang, Sizhe Wang, Jingdong School of Computer Science and Technology MOEKLINNS Lab Xi'an Jiaotong University Shaanxi Xi'an China University of Science and Technology of China Anhui Hefei China School of Computer Science and Technology Xi'an Jiaotong University Shaanxi Xi'an China ReLER Lab AAII University of Technology Sydney SydneyNSW Australia Zhejiang University of Technology College of Computer Science and Technology China SGIT AI Lab State Grid Corporation of China Beijing China Baidu Inc Beijing China United Arab Emirates Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an710049 China SGIT AI Lab State Grid Corporation of China China School of Computer Science and Technology Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University Xi'an710049 China

ISBN: (纸本)9798400706868

Exploring open-vocabulary video action recognition is a promising venture, which aims to recognize previously unseen actions within any arbitrary set of categories. Existing methods typically adapt pretrained image-text models to the video domain, capitalizing on their inherent strengths in generalization. A common thread among such methods is the augmentation of visual embeddings with temporal information to improve the recognition of seen actions. Yet, they compromise with standard less-informative action descriptions, thus faltering when confronted with novel actions. Drawing inspiration from human cognitive processes, we argue that augmenting text embeddings with human prior knowledge is pivotal for open-vocabulary video action recognition. To realize this, we innovatively blend video models with Large Language Models (LLMs) to devise Action-conditioned Prompts. Specifically, we harness the knowledge in LLMs to produce a set of descriptive sentences that contain distinctive features for identifying given actions. Building upon this foundation, we further introduce a multi-modal action knowledge alignment mechanism to align concepts in video and textual knowledge encapsulated within the prompts. Extensive experiments on various video benchmarks, including zero-shot, few-shot, and base-to-novel generalization settings, demonstrate that our method not only sets new SOTA performance but also possesses excellent interpretability. © 2024 ACM.

关键词： Embeddings

Chirality-2 fermion induced Anti-Klein tunneling in 2D checkerboard lattice

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hua, Jiannan Wang, Z.F. Zhu, W. Chen, Weiwei Department of Physics School of Science Westlake University Zhejiang Hangzhou310024 China Institute of Natural Sciences Westlake Institute for Advanced Study Zhejiang Hangzhou310024 China Hefei National Research Center for Physical Sciences at the Microscale CAS Key Laboratory of Strongly-Coupled Quantum Matter Physics Department of Physics University of Science and Technology of China Anhui Hefei230026 China Hefei National Laboratory University of Science and Technology of China Anhui Hefei230088 China Key Laboratory of Intelligent Manufacturing Quality Big Data Tracing and Analysis of Zhejiang Province College of Science China Jiliang University Hangzhou310018 China

The quantum tunneling effect in the two-dimensional (2D) checkerboard lattice is investigated. By analyzing the pseudospin texture of the states in a 2D checkerboard lattice based on the low-energy effective Hamiltonian, we find that this system has a chiral symmetry with chirality equal to 2. Although compared to regular chiral fermions, its pseudospin orientation does not vary uniformly. This suggests that the perfect reflection chiral tunneling, also known as the anti-Klein tunneling, is expected to appear in checkerboard lattice as well. In order to verify the conjecture, we calculate the transmission probability and find that normally incident electron states can be perfectly reflected by the barrier with hole states inside, and vice versa. Furthermore, we also numerically calculate the tunneling conductance of the checkerboard nanotube using the recursive Green’s function method. The results show that a perfect on-off ratio can be achieved by confining the energy of the incident states within a certain range. It also suggests that, by tuning the barrier, the checkerboard nanotube is able to work as a perfect "band filter" or "tunneling field effect transistor", which transmits electrons selectively with respect to the pseudospin of the incident electrons. Copyright © 2024, The Authors. All rights reserved.

关键词： Nanotubes

A Service Composition Evolution Method that Combines Deep Clustering and a Service Requirement Context Model

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Xiao, Gang Lu, Jiawei Zheng, Jiahong Chen, Zhenbo Wang, Qibing Li, Duanni School of Computer Science and Technology Zhejiang University of Technology Hangzhou China College of Mechanical and Electrical Engineering China Jiliang University Hangzhou China Key Laboratory of Intelligent Manufacturing Quality Big Data Tracing and Analysis of Zhejiang Province China Jiliang University Hangzhou China

Service composition can quickly build new value-added composite services by combining existing Web services. However, with the complex and changeable Internet environment, composite services need to effectively understand and manage requirements in a flexible and adaptive manner, and also be able to quickly and proactively provide high-quality services through a series of dynamic evolution models. In response to these challenges, in this study, we propose a service composition evolution method that can adaptively select the appropriate service to improve user satisfaction and service quality. First, we introduce a deep clustering method based on the topic model and auto-encoder, which considers the function description documents and parameter information of the services to reduce the search space of the candidate services. Furthermore, we describe a requirement-oriented context-sensitive task model to integrate functional and non-functional user requirements by connecting the context of Web subtasks. Then, we present a dynamic service matching method with QoS threshold judgement to filter and rank the services. We applied the proposed evolution method to the datasets of real-world Web services and measured the performance using standard measurement metrics. The prototype implementation and results of simulation experiments verified the effectiveness of each part of our method. © 2022, The Authors. All rights reserved.

关键词： Web services

FaceBench: A Multi-View Multi-Level Facial Attribute VQA dataset for Benchmarking Face Perception MLLMs

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Xiaoqin Ma, Xusen Hou, Xianxu Ding, Meidan Li, Yudong Chen, Junliang Chen, Wenting Peng, Xiaoyang Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China AIAC Xi’an Jiaotong-Liverpool University China Tsinghua University China The Hong Kong Polytechnic University Hong Kong City University of Hong Kong Hong Kong Sun Yat-sen University China

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in various tasks. However, effectively evaluating these MLLMs on face perception remains largely unexplored. To address this gap, we introduce FaceBench, a dataset featuring hierarchical multi-view and multi-level attributes specifically designed to assess the comprehensive face perception abilities of MLLMs. Initially, we construct a hierarchical facial attribute structure, which encompasses five views with up to three levels of attributes, totaling over 210 attributes and 700 attribute values. Based on the structure, the proposed FaceBench consists of 49,919 visual question-answering (VQA) pairs for evaluation and 23,841 pairs for fine-tuning. Moreover, we further develop a robust face perception MLLM baseline, Face-LLaVA, by training with our proposed face VQA data. Extensive experiments on various mainstream MLLMs and Face-LLaVA are conducted to test their face perception ability, with results also compared against human performance. The results reveal that, the existing MLLMs are far from satisfactory in understanding the fine-grained facial attributes, while our Face-LLaVA significantly outperforms existing open-source models with a small amount of training data and is comparable to commercial ones like GPT-4o and Gemini. The dataset will be released at https://***/CVI-SZU/FaceBench. Copyright © 2025, The Authors. All rights reserved.

关键词：

A BCS-GDE Multi-objective Optimization Algorithm for Combined Cooling, Heating and Power Model with Decision Strategies

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Sun, Jiaze Deng, Jiahui Li, Yang Han, Nan School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an710121 China Xi 'an Key Laboratory of Big Data and Intelligent Computing Xi’an710127 China School of Information Science and Technology Northwest University Xi’an710127 China School of Electrical Engineering Northeast Electric Power University Jilin132012 China

District energy systems can not only reduce energy consumption but also set energy supply dispatching schemes according to demand. In addition to economic cost, energy consumption and pollutant are more worthy of attention when evaluating combined cooling, heating and power (CCHP) models. In this paper, the CCHP model is established with the objective of economic cost, primary energy consumption, and pollutant emissions. The mathematical expression of the CCHP system is proposed, and a multi-objective optimization model with constraints is established. According to different usage requirements, two decision-making strategies are designed, which can adapt to different scenarios. Besides, a generalized differential evolution with the best compromise solution processing mechanism (BCS-GDE) algorithm is proposed to optimize the CCHP model for the first time. The algorithm provides the optimal energy scheduling scheme by optimizing the production capacity of different capacity equipment. The simulation is conducted in three application scenarios: hotels, offices, and residential buildings. The simulation results show that the model established in this paper can reduce economic cost by 72%, primary energy consumption by 73%, and pollutant emission by 88%. Concurrently, the Wilcoxon signed-rank test shows that BCS-GDE is significantly better than OMOPSO, NSGA-II, and SPEA2 with greater than 95% confidence. Copyright © 2022, The Authors. All rights reserved.

关键词： Evolutionary algorithms

CLSDRL:A routing optimization method for traffic feature extraction

学校读者我要写书评

暂无评论

CLSDRL:A routing optimization method for traffic feature ext...

International Conference on Networking and Network Applications (NaNA)

作者： Hong Xia Jianguo Li Yanping Chen Ning Lv ZhongMin Wang Qingyi Dong School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an Shaanxi China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an Shaanxi China Xi’an Key Laboratory of Big Data and Intelligent Computing Xi’an Shaanxi China

In order to solve the impact of the temporal and spatial characteristics of traffic on network routing optimization, this paper proposes convolution long-short memory neural network deep reinforcement learning (CLSDRL) model for routing optimization. The CLSDRL model consists of deep deterministic policy gradients (DDPG) deep couple with convolution neural network (CNN) and long-short memory neural network (LSTM). After extracting the spatial and temporal characteristics of network traffic with CNN and LSTM, routing decisions are made with DDPG algorithm. Experiments are conducted under different load intensities, and the network performance is evaluated by the average network delay and packet loss rate, experimental results show that this method can improve significantly network performance.

关键词： Training Convolution Neural networks Optimization methods Packet loss Reinforcement learning Telecommunication traffic

TEVA: Training-Efficient and Verifiable Aggregation for Federated Learning for Consumer Electronics in Industry 5.0

学校读者我要写书评

暂无评论

IEEE Transactions on Consumer Electronics 2024年

作者： Xia, Yuanjun Liu, Yining Chen, Jingxue Liang, Yangfan Khan, Fazlullah Alturki, Ryan Wang, Xiaopei Guilin University of Electronic Technology Guangxi Key Laboratory of Trusted Software School of Computer and Information Security Guilin541004 China Wenzhou University of Technology School of Data Science and Artificial Intelligence Wenzhou325027 China University of Technology School of Mathematical and Physical Sciences SydneyNSW2007 Australia Jiaxing University Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems The Key Laboratory of Medical Electronics and Digital Health of Zhejiang Province The Engineering Research Center of Intelligent Human Health Situation Awareness of Zhejiang Province Jiaxing314001 China University of Nottingham Ningbo China School of Computer Science Faculty of Science and Engineering Zhejiang Ningbo315104 China Umm AI-Qura University Makkah Department of Software Engineering College of Computing Saudi Arabia Riverside Department of Computer Science and Engineering University of California CA92521 United States

Federated learning (FL) has been widely used for privacy-preserving model updates in Industry 5.0, facilitated by 6G networks. Despite FL's privacy-preserving advantages, it remains vulnerable to attacks where adversaries can infer private data from local models or manipulate the central server (CS) to deliver falsified global models. Current privacy-preserving approaches, primarily based on the FedAvg algorithm, fail to optimize training efficiency for non-independent and identically distributed (non-IID) data. This article proposes training-efficient and verifiable aggregation (TEVA) for FL to resolve these issues. This scheme combines threshold Paillier homomorphic encryption (TPHE), verifiable aggregation, and an optimized double momentum update mechanism (OdMum). TEVA not only leverages TPHE to protect the privacy of local models but also ensures the integrity of the global model through a verifiable aggregation mechanism. Additionally, TEVA integrates the OdMum algorithm to effectively address the challenges posed by non-IID data, promoting rapid model convergence and significantly enhancing overall training efficiency. Security analysis indicates that TEVA meets the requirements for privacy protection. Extensive experimental results demonstrate that TEVA can accelerate model convergence while incurring lower computational and communication overheads. © 1975-2011 IEEE.

关键词： Differential privacy

Multi-scale Contrastive Learning for Gastroenteroscopy Classification

学校读者我要写书评

暂无评论

Multi-scale Contrastive Learning for Gastroenteroscopy Class...

Annual IEEE Symposium on Computer-Based Medical Systems

作者： Dan Li Xuechen Li Zhibin Peng Wenting Chen Linlin Shen Guangyao Wu Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology ShenZhen University Shenzhen China City University of Hong Kong Hong Kong SAR China Shenzhen Institute of Artificial Intelligence & Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University General Hospital

In gastroenteroscopy image analysis, numerous CADs demonstrate that deep learning aids doctors' diagnosis. The shapes and sizes of the lesions are varied. And in the clinic, the dataset appears to be data imbalanced. However, existing methods directly classify by texture and ignore lesions with various shapes and sizes. To address the issue above, we propose a deep neural network, which consists of multi-scale feature extraction, contrastive feature learning and a multi-scale feature fusion module. We train the contrastive feature learning module and multi-scale feature fusion module simultaneously to alleviate the issue of data distribution differences. Thus, the proposed network can better identify various categories. Extensive experiments on the Hyper Kvasir dataset show that the proposed Hybrid-M2CL outperforms the benchmark proposed by the dataset with 5.0% Macro Precision, 3.3% Macro Recall, 3.4% Macro F1-score, 3.3% Micro Precision, 3.6% MCC. In addition, it outperforms the SOTA by 1.1% Macro F1-score, 2.6% MCC, and 2.0% B-ACC.

关键词：

The Security and Privacy of Mobile Edge computing: An Artificial Intelligence Perspective

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Cheng Yuan, Zenghui Zhou, Pan Xu, Zichuan Li, Ruixuan Wu, Dapeng Oliver Hubei Engineering Research Center on Big Data Security Key Laboratory of Distributed System Security of Hubei Province School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China School of Software The Key Laboratory for Ubiquitous Network Service Software of Liaoning Province Dalian University of Technology Dalian116024 China Intelligent and Distributed Computing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Department of Computer Science City University of Hong Kong Kowloon999077 Hong Kong

Mobile Edge computing (MEC) is a new computing paradigm that enables cloud computing and information technology (IT) services to be delivered at the network’s edge. By shifting the load of cloud computing to individual local servers, MEC helps meet the requirements of ultralow latency, localized data processing, and extends the potential of Internet of Things (IoT) for end-users. However, the crosscutting nature of MEC and the multidisciplinary components necessary for its deployment have presented additional security and privacy concerns. Fortunately, Artificial Intelligence (AI) algorithms can cope with excessively unpredictable and complex data, which offers a distinct advantage in dealing with sophisticated and developing adversaries in the security industry. Hence, in this paper we comprehensively provide a survey of security and privacy in MEC from the perspective of AI. On the one hand, we use European Telecommunications Standards Institute (ETSI) MEC reference architecture as our based framework while merging the Software Defined Network (SDN) and Network Function Virtualization (NFV) to better illustrate a serviceable platform of MEC. On the other hand, we focus on new security and privacy issues, as well as potential solutions from the viewpoints of AI. Finally, we comprehensively discuss the opportunities and challenges associated with applying AI to MEC security and privacy as possible future research directions. Copyright © 2024, The Authors. All rights reserved.

关键词： Network security