检索结果-内蒙古大学图书馆

Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Daizong Fang, Xiang Hu, Wei Zhou, Pan Wangxuan Institute of Computer Technology Peking University No. 128 Zhongguancun North Street Beijing China Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China

Temporal sentence grounding aims to localize a target segment in an untrimmed video semantically according to a given sentence query. Most previous works focus on learning frame-level features of each whole frame1 in the entire video, and directly match them with the textual information. Such frame-level feature extraction leads to the obstacles of these methods in distinguishing ambiguous video frames with complicated contents and subtle appearance differences, thus limiting their performance. In order to differentiate fine-grained appearance similarities among consecutive frames, some state-of-the-art methods additionally employ a detection model like Faster R-CNN to obtain detailed object-level features in each frame for filtering out the redundant background contents. However, these methods suffer from missing motion analysis since the object detection module in Faster R-CNN lacks temporal modeling. To alleviate the above limitations, in this paper, we propose a novel Motion- and Appearance-guided 3D Semantic Reasoning Network (MA3SRN), which incorporates optical-flow-guided motion-aware, detection-based appearance-aware, and 3D-aware object-level features to better reason the spatial-temporal object relations for accurately modelling the activity among consecutive frames. Specifically, we first develop three individual branches for motion, appearance, and 3D encoding separately to learn fine-grained motion-guided, appearance-guided, and 3D-aware object features, respectively. Then, both motion and appearance information from corresponding branches are associated to enhance the 3D-aware features for the final precise grounding. Extensive experiments on three challenging datasets (ActivityNet Caption, Charades-STA and TACoS) demonstrate that the proposed MA3SRN model achieves a new state-of-the-art. Copyright © 2022, The Authors. All rights reserved.

关键词： Optical flows

GM-DF: Generalized Multi-Scenario Deepfake Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lai, Yingxin Yu, Zitong Yang, Jing Li, Bin Kang, Xiangui Shen, Linlin The School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen University Shenzhen518060 China The Guangdong Key Laboratory of Information Security The School of Computer Science and Engineering Sun Yat-sen University Guangzhou510080 China Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China

Existing face forgery detection usually follows the paradigm of training models in a single domain, which leads to limited generalization capacity when unseen scenarios and unknown attacks occur. In this paper, we elaborately investigate the generalization capacity of deepfake detection models when jointly trained on multiple face forgery detection datasets. We first find a rapid degradation of detection accuracy when models are directly trained on combined datasets due to the discrepancy across collection scenarios and generation methods. To address the above issue, a Generalized Multi-Scenario Deepfake Detection framework (GM-DF) is proposed to serve multiple real-world scenarios by a unified model. First, we propose a hybrid expert modeling approach for domain-specific real/forgery feature extraction. Besides, as for the commonality representation, we use CLIP to extract the common features for better aligning visual and textual features across domains. Meanwhile, we introduce a masked image reconstruction mechanism to force models to capture rich forged details. Finally, we supervise the models via a domain-aware meta-learning strategy to further enhance their generalization capacities. Specifically, we design a novel domain alignment loss to strongly align the distributions of the meta-test domains and meta-train domains. Thus, the updated models are able to represent both specific and common real/forgery features across multiple datasets. In consideration of the lack of study of multi-dataset training, we establish a new benchmark leveraging multi-source data to fairly evaluate the models' generalization capacity on unseen scenarios. Both qualitative and quantitative experiments on five datasets conducted on traditional protocols as well as the proposed benchmark demonstrate the effectiveness of our approach. The codes will be available on https://***/laiyingxin2/GM-DF. Copyright © 2024, The Authors. All rights reserved.

关键词： Image reconstruction

RobNODDI: Robust NODDI Parameter Estimation with Adaptive Sampling Under Continuous Representation 15th

学校读者我要写书评

暂无评论

RobNODDI: Robust NODDI Parameter Estimation with Adaptive S...

15th International Workshop on Computational Diffusion MRI, CDMRI 2024, held in conjunction with 27th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2024

作者： Xiao, Taohui Cheng, Jian Fan, Wenxin Yang, Jing Li, Cheng Dong, Enqing Wang, Shanshan School of Mechanical Electrical and Information Engineering Shandong University Weihai264209 China State Key Laboratory of Software Development Environment Beihang University Beijing China Key Laboratory of Data Science and Intelligent Computing Institute of International Innovation Beihang University Zhejiang Hangzhou China Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China Peng Cheng Laboratory Guangdong Shenzhen China

ISBN: (纸本)9783031869198

Neurite Orientation Dispersion and Density Imaging (NODDI) is an important imaging technology used to evaluate the microstructure of brain tissue, which is of great significance for the discovery and treatment of various neurological diseases. Current deep learning-based methods perform parameter estimation through diffusion magnetic resonance imaging (dMRI) with a small number of diffusion gradients. These methods speed up parameter estimation and improve accuracy. However, the diffusion directions used by most existing deep learning models during testing needs to be strictly consistent with the diffusion directions during training. This results in poor generalization and robustness of deep learning models in dMRI parameter estimation. In this work, we first verify that the parameter estimation performance of current mainstream methods will significantly decrease when the testing diffusion directions and the training diffusion directions are inconsistent. A robust NODDI parameter estimation method with adaptive sampling under continuous representation (RobNODDI) is proposed. Furthermore, long short-term memory (LSTM) units and fully connected layers are selected to learn continuous representation signals. To this end, we use a total of 100 subjects to conduct experiments based on the Human Connectome Project (HCP) dataset, of which 60 are used for training, 20 are used for validation, and 20 are used for testing. The test results indicate that RobNODDI improves the generalization performance and robustness of the deep learning model, enhancing the stability and flexibility of deep learning NODDI parameter estimatimation applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

MSONoC: A Metasurface-assisted Hybrid Waveguide/FSO Network-on-Chip Architecture

学校读者我要写书评

暂无评论

IEEE Transactions on Green Communications and Networking

IEEE Transactions on Green Communications and Networking 2024年

作者： Sun, Wei Li, Jingsi Guo, Pengxing He, Xiangyu Wang, Zimo Hu, Cong Liu, Weichen Hou, Weigang Guo, Lei School of Communications and Information Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China Institute of Intelligent Communications and Network Security Chongqing University of Posts and Telecommunications Chongqing400065 China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing400065 China Guangxi Key Laboratory of Automatic Detecting Technology and Instruments Guilin University of Electronic Technology Guilin541004 China School of Computer Science and Engineering Nanyang Technological University Singapore

Optical networks-on-chips (ONoCs) have emerged as the most promising solution for on-chip interconnection networks, offering distinct advantages such as high bandwidth and low latency. However, traditional wired-based ONoCs often suffer from a high average number of hops, leading to challenges such as increased insertion loss, crosstalk noise, and energy consumption. Therefore, this paper presents a novel ONoC structure known as the metasurface ONoC (MSONoC), which integrates wired waveguide and free-space optical (FSO) transmission with the assistance of metasurfaces. Specifically, this work encompasses the design of a passive metasurface structure tailored for ONoCs, a virtual network cluster partitioning method, an optical metasurface access points select strategy, and a shortest-path routing algorithm. Performance verification is conducted using a modified Noxim simulator. The simulation results demonstrate that the proposed MSONoC offers advantages over traditional NoCs, radio frequency (RF)-based hybrid wired/wireless NoCs, and wired-based ONoCs in terms of throughput, delay, energy consumption, and signal-to-noise ratio under both synthetic traffic and real traffic models. These improvements proves the effectiveness of the MSONoC architecture in optimizing network performance, making it a promising solution for high-performance, energy-efficient communication in on-chip networks. © 2017 IEEE.

关键词： Network-on-chip

Edge Perception: intelligent Wireless Sensing at Network Edge

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Cui, Yuanhao Cao, Xiaowen Zhu, Guangxu Nie, Jiali Xu, Jie Southern University of Science and Technology Shenzhen China College of Electronics and Information Engineering Shenzhen University Shenzhen518060 China Shenzhen Research Institute of Big Data Shenzhen518172 China Beijing University of Posts and Telecommunications Beijing China Shenzhen518172 China

Future sixth-generation (6G) networks are envisioned to support intelligent applications across various vertical scenarios, which have stringent requirements on high-precision sensing as well as ultra-low-latency data processing and decision making. Towards this end, a new paradigm of edge perception networks emerges, which integrates wireless sensing, communication, computation, and artificial intelligence (AI) capabilities at network edge for intelligent sensing and data processing. This article provides a timely overview on this emerging topic. We commence by discussing wireless edge perception, including physical layer transceiver design, network-wise cooperation, and application-specific data analytics, for which the prospects and challenges are emphasized. Next, we discuss the interplay between edge AI and wireless sensing in edge perception, and present various key techniques for two paradigms, namely edge AI empowered sensing and task-oriented sensing for edge AI, respectively. Finally, we emphasize interesting research directions on edge perception to motivate future works. Copyright © 2024, The Authors. All rights reserved.

关键词： Wireless sensor networks

Rore: robust and efficient antioxidant protein classification via a novel dimensionality reduction strategy based on learning of fewer features

学校读者我要写书评

暂无评论

Genomics and Informatics 2024年第1期22卷 1-10页

作者： Meng, Chaolu Hou, Yongqi Zou, Quan Shi, Lei Su, Xi Ju, Ying College of Computer and Information Engineering Inner Mongolia Agricultural University Hohhot China Inner Mongolia Autonomous Region Key Laboratory of Big Data Research and Application of Agriculture and Animal Husbandry Hohhot China School of Computer Science Inner Mongolia University Hohhot China Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of China Chengdu China Department of Spine Surgery Changzheng Hospital Naval Medical University Huangpu District No. 415 Fengyang Road Shanghai China Foshan Women and Children Hospital Foshan China School of Informatics Xiamen University Xiamen China

In protein identification, researchers increasingly aim to achieve efficient classification using fewer features. While many feature selection methods effectively reduce the number of model features, they often cause information loss caused by merely selecting or discarding features, which limits classifier performance. To address this issue, we present Rore, an algorithm based on a feature-dimensionality reduction strategy. By mapping the original features to a latent space, Rore retains all relevant feature information while using fewer representations of the latent features. This approach significantly preserves the original information and overcomes the information loss problem associated with previous feature selection. Through extensive experimental validation and analysis, Rore demonstrated excellent performance on an antioxidant protein dataset, achieving an accuracy of 95.88% and MCC of 91.78%, using vectors including only 15 features. The Rore algorithm is available online at http://112.124.26.17:8021/Rore. © The Author(s) 2024.

关键词： Dimensionality reduction Protein classifier Protein sequence Robust feature

Communication-Efficient Federated Learning by Quantized Variance Reduction for Heterogeneous Wireless Edge Networks

学校读者我要写书评

暂无评论

IEEE Transactions on Mobile Computing 2025年

作者： Wang, Shuai Xu, Yanqing You, Chaoqun Shao, Mingjie Quek, Tony Q.S. University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications Chengdu611731 China The Chinese University of HongKong Shenzhen Research Institute of Big Data School of Science and Engineering Shenzhen518172 China Fudan University School of Computer Science and Technology 200433 China Beijing100149 China Singapore University of Technology and Design Information Systems Technology and Design 487372 Singapore

Federated learning (FL) has been recognized as a viable solution for local-privacy-aware collaborative model training in wireless edge networks, but its practical deployment is hindered by the high communication overhead caused by frequent and costly server-device synchronization. Notably, most existing communication-efficient FL algorithms fail to reduce the significant inter-device variance resulting from the prevalent issue of device heterogeneity. This variance severely decelerates algorithm convergence, increasing communication overhead and making it more challenging to achieve a well-performed model. In this paper, we propose a novel communication-efficient FL algorithm, named FedQVR, which relies on a sophisticated variance-reduced scheme to achieve heterogeneity-robustness in the presence of quantized transmission and heterogeneous local updates among active edge devices. Comprehensive theoretical analysis justifies that FedQVR is inherently resilient to device heterogeneity and has a comparable convergence rate even with a small number of quantization bits, yielding significant communication savings. Besides, considering non-ideal wireless channels, we propose FedQVR-E which enhances the convergence of FedQVR by performing joint allocation of bandwidth and quantization bits across devices under constrained transmission delays. Extensive experimental results are also presented to demonstrate the superior performance of the proposed algorithms over their counterparts in terms of both communication efficiency and application performance. © 2025 IEEE.

关键词： Federated learning

Fairness-aware Multiobjective Evolutionary Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Qingquan Liu, Jialin Yao, Xin The Research Institute of Trustworthy Autonomous System Southern University of Science and Technology Shenzhen518055 China The Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China The School of Data Science Lingnan University Hong Kong

Multiobjective evolutionary learning (MOEL) has demonstrated its advantages of training fairer machine learning models considering a predefined set of conflicting objectives, including accuracy and different fairness measures. Recent works propose to construct a representative subset of fairness measures as optimisation objectives of MOEL throughout model training. However, the determination of a representative measure set relies on dataset, prior knowledge and requires substantial computational costs. What's more, those representative measures may differ across different model training processes. Instead of using a static predefined set determined before model training, this paper proposes to dynamically and adaptively determine a representative measure set online during model training. The dynamically determined representative set is then used as optimising objectives of the MOEL framework and can vary with time. Extensive experimental results on 12 well-known benchmark datasets demonstrate that our proposed framework achieves outstanding performance compared to state-of-the-art approaches for mitigating unfairness in terms of accuracy as well as 25 fairness measures although only a few of them were dynamically selected and used as optimisation objectives. The results indicate the importance of setting optimisation objectives dynamically during training. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

Characterization of heavy-chain antibody gene repertoires in Bactrian camels

学校读者我要写书评

暂无评论

Journal of Genetics and Genomics 2023年第1期50卷 38-45页

作者： Yuexing Liu Li Yi Yixue Li Zhen Wang Jirimutu CAS Key Laboratory of Computational Biology Shanghai Institute of Nutrition and HealthUniversity of Chinese Academy of SciencesChinese Academy of SciencesShanghai 200031China Key Laboratory of Dairy Biotechnology and Engineering Ministry of EducationCollege of Food Science and EngineeringInner Mongolia Agricultural UniversityHuhhotInner Mongolia 010018China Hangzhou Institute for Advanced Study University of Chinese Academy of SciencesHangzhouZhejiang 310024China School of Life Sciences and Biotechnology Shanghai Jiao Tong UniversityShanghai 200240China Guangzhou Laboratory GuangzhouGuangdong 510005China Bio-Med Big Data Center Shanghai Institute of Nutrition and HealthUniversity of Chinese Academy of SciencesChinese Academy of SciencesShanghai 200031China Collaborative Innovation Center for Genetics and Development Fudan UniversityShanghai 200433China Inner Mongolia Institute of Camel Research West AlaxInner Mongolia 737399China

Camelids are the only mammals that can produce functional heavy-chain antibodies(HCAbs).Although HCAbs were discovered over 30 years ago,the antibody gene repertoire of Bactrian camels remains largely *** characterize the diversity of variable genes of HCAbs(VHHs),germline and rearranged VHH repertoires are *** analysis shows that all camelid VHH genes are derived from a common ancestor and the nucleotide diversity of VHHs is similar across all camelid *** species-specific hallmark sites are identified,the non-canonical cysteines specific to VHHs are distinct in Bactrian camels and dromedaries compared with *** low divergence at the germline repertoire between wild and domestic Bactrian camels,higher expression of VHHs is observed in some wild Bactrian camels than that of domestic *** study not only adds our understanding of VHH repertoire diversity across camelids,but also provides useful resources for HCAb engineering.

关键词： Bactrian camel Heavy-chain antibody Nanobody Immune repertoire diversity Non-canonical cysteine