检索结果-内蒙古大学图书馆

FASTEN: Video Event Localization based on Audio-Visual Feature Alignment and Multi-Scale Temporal Enhancement

IEEE Signal Processing Letters 2025年 32卷 2010-2014页

作者： Liu, Yin Wu, Qin Zeng, Mingyong Liu, Yahan Pan, Yuying Jiangnan University School of Artificial Intelligence and Computer Science Wuxi 214122 China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi 214083 China Jiangnan University School of Internet of Things Engineering Wuxi 214122 China

The audio-visual event localization task investigates how audio and visual modalities can mutually enhance video event localization. Current methods often rely on single-modality features or lack effective initial alignment between modalities. Although feature pyramids with multiple resolutions are commonly used, the effective and efficient mining of cross-modal and cross-level semantics remains a challenge. In this letter, we propose FASTEN, which stands for audio-visual Feature Alignment and multi-Scale Temporal ENhancement. Novel features derived from an initially aligned multimodal model are introduced and have been shown to be remarkably beneficial. We design an efficient encoder by sharing weights across all pyramid levels and propose a weighted cross-modal attention module to facilitate interaction between modalities. Additionally, global and local pyramids are fused to jointly capture multi-scale temporal dependencies. Evaluated on UnAV-100 and AVE, our method significantly outperforms competing solutions while reducing parameters and computational FLOPs greatly. © 1994-2012 IEEE.

关键词： Audio-visual event localization cross-modal fusion multi-scale enhancement

来源：评论

学校读者我要写书评

暂无评论

WiViPose: A Video-aided Wi-Fi Framework for Environment-Independent 3D Human Pose Estimation

引用

IEEE Transactions on Multimedia 2025年

作者： Zhang, Lei Ning, Haoran Tang, Jiaxin Chen, Zhenxiang Zhong, Yaping Han, Yahong Tianjin University College of Intelligence and Computing the Tianjin Key Laboratory of Advanced Network Technology and Application Tianjin300050 China Key Laboratory of Computing Power Network and Information Security Ministry of Education China University of Jinan Shandong Provincial Key Laboratory of Ubiquitous Intelligent Computing the School of Information Science and Engineering Jinan250022 China Wuhan Sports University Sports Big-data Research Center Wuhan430079 China Tianjin University College of Intelligence and Computing the Tianjin Key Laboratory of Machine Learning Tianjin300350 China

The inherent complexity of Wi-Fi signals makes video-aided Wi-Fi 3D pose estimation difficult. The challenges include the limited generalizability of the task across diverse environments, its significant signal heterogeneity, and its inadequate ability to analyze local and geometric information. To overcome these challenges, we introduce WiViPose, a video-aided Wi-Fi framework for 3D pose estimation, which attains enhanced cross-environment generalization through cross-layer optimization. Bilinear temporal-spectral fusion (BTSF) is initially used to fuse the time-domain and frequency-domain features derived from Wi-Fi. Video features are derived from a multiresolution convolutional pose machine and enhanced by local self-attention. Cross-modality data fusion is facilitated through an attention-based transformer, with the process further refined under a supervisory mechanism. WiViPose demonstrates effectiveness by achieving an average percentage of correct keypoints (PCK)@50 of 91.01% across three typical indoor environments. © 2025 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Non-Markovian effect enhanced quantum noises in a coherent Ising machine

引用

Optics Express 2025年第11期33卷 22208-22221页

作者： Chen-Rui Fan Bo Lu Yi-Xuan Yao Qing Ai Chuan Wang School of Artificial Intelligence Beijing Normal University Beijing 100875 China Laboratory for Advanced Computing and Intelligence Engineering Zhengzhou 450001 China lubo@*** School of Physics and Astronomy Applied Optics Beijing Area Major Laboratory Beijing 100875 China Key Laboratory of Multiscale Spin Physics Ministry of Education Beijing Normal University Beijing 100875 China wangchuan@***

Combinatorial optimization problems (COPs) constitute a fundamental class of computational challenges with extensive applications across scientific and industrial domains. The emergence of the coherent Ising machine (CIM) as a computational paradigm has demonstrated exceptional capabilities in rapidly generating arbitrary spin configurations and effectively solving large-scale COPs. Despite its promising potential, the CIM framework encounters an inherent limitation related to amplitude heterogeneity. Current approaches to this limitation primarily rely on Gaussian approximations to model quantum noise in the system’s amplitude dynamics within the original CIM framework. However, these methods generally fail to account for the temporal and periodic non-Markovian characteristics of pulses in practical environments. In this study, we introduce temporally correlated non-Markovian noise into the dynamics of both conventional and spiking neural network-based CIM systems, investigating their performance through comprehensive hyperparameter analysis. Our method incorporates a detailed examination of hyperparameter selection and its influence on algorithmic efficiency. Through extensive numerical simulations, we demonstrate that the integration of non-Markovian noise significantly accelerates variance evolution in both canonical coordinates and amplitude dynamics over time. The proposed approach not only exhibits enhanced computational performance but also shows superior scalability for large-scale problem instances. These findings suggest that our approach offers distinct advantages in addressing complex COPs, potentially opening new avenues for efficient optimization in various applications.

关键词： Neural networks Nonlinear optical fibers Numerical simulation Optical parametric oscillators Optical systems Quantum noise

来源：评论

学校读者我要写书评

暂无评论

Quantum Multi-Path Communication Protocol Based on Maximum Flow Theory

Quantum Multi-Path Communication Protocol Based on Maximum F...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jihao Fan Liang Huang Jun Li Long Shi Yuwen Qian School of Cyber Science and Engineering Nanjing University of Science and Technology Jiangyin China Laboratory for Advanced Computing and Intelligence Engineering Wuxi China School of Electronic and Optical Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Quantum networks are an actively researched and promising field, aiming to achieve efficient quantum information transmission by interconnecting quantum nodes. In large-scale quantum networks, end-to-end throughput is a critical factor that affects the overall performance of the network. The maximum flow problem, extensively studied in classical network theory, identifies a set of paths between the source and destination nodes that maximizes the total flow. This study extends the maximum flow problem to quantum networks, focusing on coordinating multiple paths for multi-path quantum communication. We propose a Quantum Multi-Path Communication Protocol (QMCP) that employs maximum flow theory to allocate transmission resources across multiple nodes efficiently, thus maximizing the total transmission capacity from the source to the destination. Our evaluation demonstrates that QMCP significantly enhances end-to-end throughput in quantum networks.

关键词： Quantum entanglement Simulation Signal processing algorithms Focusing Information processing Signal processing Throughput Routing protocols Quantum networks Speech processing

来源：评论

学校读者我要写书评

暂无评论

The Modified Sparrow Search Algorithm with Brown Motion and Levy Flight Strategy for the Class Integration Test Order Generation Problem

引用

Biomimetics 2025年第4期10卷 195-195页

作者： Jiao, Chongyang Zhou, Qinglei Zhang, Wenning Zhang, Chunyan Laboratory for Advanced Computing and Intelligence Engineering Information Engineering University Zhengzhou450001 China Henan Information Engineering School Zhengzhou Vocational College of Industrial Safety Zhengzhou450011 China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou450001 China Software College Zhongyuan University of Technology Zhengzhou450007 China

Software testing identifies potential errors and defects in software. A crucial component of software testing is integration testing, and the generation of class integration test orders (CITOs) is a critical topic in integration testing. The research shows that search-based algorithms can solve this problem effectively. As a novel search-based algorithm, the sparrow search algorithm (SSA) is good at finding the optimal to optimization problems, but it has drawbacks like weak population variety later on and the tendency to easily fall into the local optimum. To overcome its shortcomings, a modified sparrow search algorithm (MSSA) is developed and applied to the CITO generation issue. The algorithm is initialized with a good point set strategy, which distributes the sparrows evenly in the solution space. Then, the discoverer learning strategy of Brownian motion is introduced and the Levy flight is utilized to renew the positions of the followers, which balances the global search and local search of the algorithm. Finally, the optimal solution is subjected to random wandering to increase the probability of the algorithm jumping out of the local optimum. Using the overall stubbing complexity as a fitness function to evaluate different class test sequences, experiments are conducted on open-source Java systems, and the experimental results demonstrate that the MSSA generates test orders with lower stubbing cost in a shorter time than other novel intelligent algorithms. The superiority of the proposed algorithm is verified by five evaluation indexes: the overall stubbing complexity, attribute complexity, method complexity, convergence speed, and running time. The MSSA has shown significant advantages over the BSSA in all aspects. Among the nine systems, the total overall stubbing complexity of the MSSA is 13.776% lower than that of the BSSA. Total time is reduced by 23.814 s. © 2025 by the authors.

关键词： Integration testing

来源：评论

学校读者我要写书评

暂无评论

RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Images

arXiv

引用

arXiv 2025年

作者： Xiao, Junjin Zhang, Qing Nie, Yonewei Zhu, Lei Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China South China University of Technology China China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

This paper presents RoGSplat, a novel approach for synthesizing high-fidelity novel views of unseen human from sparse multi-view images, while requiring no cumbersome per-subject optimization. Unlike previous methods that typically struggle with sparse views with few overlappings and are less effective in reconstructing complex human geometry, the proposed method enables robust reconstruction in such challenging conditions. Our key idea is to lift SMPL vertices to dense and reliable 3D prior points representing accurate human body geometry, and then regress human Gaussian parameters based on the points. To account for possible misalignment between SMPL model and images, we propose to predict image-aligned 3D prior points by leveraging both pixel-level features and voxel-level features, from which we regress the coarse Gaussians. To enhance the ability to capture high-frequency details, we further render depth maps from the coarse 3D Gaussians to help regress fine-grained pixel-wise Gaussians. Experiments on several benchmark datasets demonstrate that our method outperforms state-of-the-art methods in novel view synthesis and cross-dataset generalization. Our code is available at https: //***/iSEE-laboratory/RoGSplat. Copyright © 2025, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Graph Prompt Clustering

引用

IEEE Transactions on Pattern Analysis and Machine intelligence 2025年 PP卷 PP页

作者： Chen, Man-Sheng Lai, Pei-Yuan Liao, De-Zhang Wang, Chang-Dong Lai, Jian-Huang Sun Yat-sen University School of Computer Science and Engineering Guangzhou China Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing China Guangdong University of Technology School of Information Engineering Guangzhou China South China Technology Commercialization Center Guangzhou China

Due to the wide existence of unlabeled graph-structured data (e.g. molecular structures), the graph-level clustering has recently attracted increasing attention, whose goal is to divide the input graphs into several disjoint groups. However, the existing methods habitually focus on learning the graphs embeddings with different graph reguralizations, and seldom refer to the obvious differences in data distributions of distinct graph-level datasets. How to characteristically consider multiple graph-level datasets in a general well-designed model without prior knowledge is still challenging. In view of this, we propose a novel Graph Prompt Clustering (GPC) method. Within this model, there are two main modules, i.e., graph model pretraining as well as prompt and finetuning. In the graph model pretraining module, the graph model is pretrained by a selected source graph-level dataset with mutual information maximization and self-supervised clustering regularization. In the prompt and finetuning module, the network parameters of the pretrained graph model are frozen, and a groups of learnable prompt vectors assigned to each graph-level representation are trained for adapting different target graph-level datasets with various data distributions. Experimental results across six benchmark datasets demonstrate the impressive generalization capability and effectiveness of GPC compared with the state-of-the-art methods. © 1979-2012 IEEE.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Progressive Human Motion Generation Based on Text and Few Motion Frames

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Zeng, Ling-An Wu, Gaojie Wu, Ancong Hu, Jian-Fang Zheng, Wei-Shi Sun Yat-sen University School of Artificial Intelligence Guangdong Zhuhai519082 China Sun Yat-sen University School of Computer Science and Engineering Guangdong Guangzhou510275 China Sun Yat-sen University School of Computer Science and Engineering China Guangdong Key Laboratory of Information Security Technology China Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing China Peng Cheng Laboratory China

Although existing text-to-motion (T2M) methods can produce realistic human motion from text description, it is still difficult to align the generated motion with the desired postures since using text alone is insufficient for precisely describing diverse postures. To achieve more controllable generation, an intuitive way is to allow the user to input a few motion frames describing precise desired postures. Thus, we explore a new Text-Frame-to-Motion (TF2M) generation task that aims to generate motions from text and very few given frames. Intuitively, the closer a frame is to a given frame, the lower the uncertainty of this frame is when conditioned on this given frame. Hence, we propose a novel Progressive Motion Generation (PMG) method to progressively generate a motion from the frames with low uncertainty to those with high uncertainty in multiple stages. During each stage, new frames are generated by a Text-Frame Guided Generator conditioned on frame-aware semantics of the text, given frames, and frames generated in previous stages. Additionally, to alleviate the train-test gap caused by multi-stage accumulation of incorrectly generated frames during testing, we propose a Pseudo-frame Replacement Strategy for training. Experimental results show that our PMG outperforms existing T2M generation methods by a large margin with even one given frame, validating the effectiveness of our PMG. Code is available here. © 1991-2012 IEEE.

关键词： Controllable Motion Generation Human Motion Text2Motion Generation

来源：评论

学校读者我要写书评

暂无评论

Augmenting Short Enrollment Speech via Synthesis for Target Speaker Extraction

Augmenting Short Enrollment Speech via Synthesis for Target ...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zikang Huang Jingru Lin Meng Ge Yu Jiang Xiaobao Wang Longbiao Wang Jianwu Dang Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen China Department of Electrical and Computer and Engineering National University of Singapore Huiyan Technology (Tianjin) Co. Ltd. Tianjin China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

A high-quality enrollment speech is crucial to target speaker extraction (TSE), since it provides essential cues for identifying the target speaker in the mixture. However, real applications usually only permit a short enrollment speech, e.g. a wakeup word for a mobile device, that provides limited cues. To address this issue, we propose an enrollment augmentation strategy that allows us to enrich the limited enrollment speech with massive text data through speech synthesis. By doing so, the extended enrollment speech contains enhanced speaker timbre and phonetic content which leads to better extraction quality. Furthermore, we propose a training data augmentation strategy to improve the model’s robustness and generalization in short enrollment speech scenarios. Experiments on Libri2Mix demonstrate that our proposed strategies bring a significant improvement in extreme scenarios where only 0.5s and 1-word enrollment speech is provided. We also release our code at https://***/HuangZikang-TJU/Aug4TSE.

关键词： Training data Speech enhancement Phonetics Signal processing Speech Robustness Mobile handsets Data models Timbre Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

ViSpeak: Visual Instruction Feedback in Streaming Videos

arXiv

引用

arXiv 2025年

作者： Fu, Shenghao Yang, Qize Li, Yuan-Ming Peng, Yi-Xing Lin, Kun-Yu Wei, Xihan Hu, Jian-Fang Xie, Xiaohua Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Tongyi Lab Alibaba Group China Peng Cheng Laboratory China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Guangdong Province Key Laboratory of Information Security Technology China China

Recent advances in Large Multi-modal Models (LMMs) are primarily focused on offline video understanding. Instead, streaming video understanding poses great challenges to recent models due to its time-sensitive, omni-modal and interactive characteristics. In this work, we aim to extend the streaming video understanding from a new perspective and propose a novel task named Visual Instruction Feedback in which models should be aware of visual contents and learn to extract instructions from them. For example, when users wave their hands to agents, agents should recognize the gesture and start conversations with welcome information. Thus, following instructions in visual modality greatly enhances user-agent interactions. To facilitate research, we define seven key subtasks highly relevant to visual modality and collect the ViSpeak-Instruct dataset for training and the ViSpeak-Bench for evaluation. Further, we propose the ViSpeak model, which is a SOTA streaming video understanding LMM with GPT-4o-level performance on various streaming video understanding benchmarks. After finetuning on our ViSpeak-Instruct dataset, ViSpeak is equipped with basic visual instruction feedback ability, serving as a solid baseline for future research. Copyright © 2025, The Authors. All rights reserved.

关键词： Video streaming

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：