检索结果-内蒙古大学图书馆

Mamba Adapter: Efficient Multi-Modal Fusion for Vision-Language Tracking

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Shi, Liangtao Zhong, Bineng Liang, Qihua Hu, Xiantao Mo, Zhiyi Song, Shuxiang Ministry of Education Guangxi Normal University Key Laboratory of Education Blockchain and Intelligent Technology Guilin541004 China Guangxi Normal University Guangxi Key Lab of Multi-Source Information Mining and Security Guilin541004 China Wuzhou University School of Data Science and Software Engineering Wuzhou543002 China

Utilizing the high-level semantic information of language to compensate for the limitations of vision information is a highly regarded approach in single-object tracking. However, most existing vision-language (VL) trackers employ full-parameter fine-tuning, which can easily lead to catastrophic forgetting. Therefore, they fail to fully exploit the prior knowledge of pre-trained models from upstream tasks, resulting in unsatisfactory tracking performance. To alleviate the above problem, we propose a simple yet effective Vision-Language Tracking pipeline based on Mamba Adapter, named MAVLT, which adopts the idea of parameter-efficient fine-tuning (PEFT) to realize the interaction between vision-language modalities. This novel approach offers the following advantages: (1)The knowledge of the upstream pre-trained model is efficiently inherited by freezing its parameters. This ensures that the VL tracking framework only learns the modules for vision and language interaction, with a focus on the fusion between modalities. (2)The modal interaction between language and vision encoders is flexibly bridged in each encoder layer via proposed mamba adapter, enabling efficient interaction of visual and language information at multiple levels. Extensive experiments on five popular vision-language tracking benchmarks validate the effectiveness of the proposed MAVLT. Particularly, the MAVLT achieves 73.4% AUC score on the LaSOT benchmarks with only 0.18%(0.32M) of the total parameters updates. Code and models are available at https://***/GXNU-ZhongLab/MAVLT. © 1991-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

High-gain long-time coherent integration for tones from moving targets via time warping

引用

Journal of the Acoustical Society of America 2025年第5期157卷 3793-3805页

作者： Chen, Yu Qiu, Longhao Li, Ying Liang, Guolong Gao, Yongshuai Du, Zhiyao National Key Laboratory of Underwater Acoustic Technology Harbin Engineering University Harbin 150001 China Key Laboratory of Marine Information Acquisition and Security Ministry of Industry and Information Technology Harbin Engineering University Harbin 150001 China College of Underwater Acoustic Engineering Harbin Engineering University Harbin 150001 China

The radiated noise from ships is notably characterized by their tonal properties, making tone detection essential for passive sonar systems. The fast Fourier transform plays a crucial role in this process, but Doppler shifts can significantly diminish the integration gain. To address this issue, time warping is applied to modify the time axis of the signal, stabilizing the tonal frequency to a constant value. Traditionally, the warping operator, which determines how to modify the time axis, is designed by estimating motion parameters. In contrast, this study presents a method that eliminates the estimation step by using a set of pre-designed warping operators. The designing process involves preprocessing and clustering the delay vectors corresponding to various motion scenarios. The enhanced gain of the proposed algorithm, in comparison to the existing methods, has been validated through both simulation and experimental data. © 2025 Acoustical Society of America.

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation

arXiv

引用

arXiv 2025年

作者： Chen, Haipeng Wu, Sifan Wang, Zhigang Yin, Yifang Jiao, Yingying Lyu, Yingda Liu, Zhenguang College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China College of Computer Science and Technology Zhejiang Gongshang University China A*STAR Singapore Public Computer Education and Research Center Jilin University China The State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China

Video-based human pose estimation has long been a fundamental yet challenging problem in computer vision. Previous studies focus on spatio-temporal modeling through the enhancement of architecture design and optimization strategies. However, they overlook the causal relationships in the joints, leading to models that may be overly tailored and thus estimate poorly to challenging scenes. Therefore, adequate causal reasoning capability, coupled with good interpretability of model, are both indispensable and prerequisite for achieving reliable results. In this paper, we pioneer a causal perspective on pose estimation and introduce a causal-inspired multitask learning framework, consisting of two stages. In the first stage, we try to endow the model with causal spatio-temporal modeling ability by introducing two self-supervision auxiliary tasks. Specifically, these auxiliary tasks enable the network to infer challenging keypoints based on observed keypoint information, thereby imbuing causal reasoning capabilities into the model and making it robust to challenging scenes. In the second stage, we argue that not all feature tokens contribute equally to pose estimation. Prioritizing causal (keypoint-relevant) tokens is crucial to achieve reliable results, which could improve the interpretability of the model. To this end, we propose a Token Causal Importance Selection module to identify the causal tokens and non-causal tokens (e.g., background and objects). Additionally, non-causal tokens could provide potentially beneficial cues but may be redundant. We further introduce a non-causal tokens clustering module to merge the similar non-causal tokens. Extensive experiments show that our method outperforms state-of-the-art methods on three large-scale benchmark datasets. Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Accurate, Secure, and Efficient Semi-Constrained Navigation Over Encrypted City Maps

引用

IEEE Transactions on Dependable and Secure Computing 2025年第3期22卷 2642-2658页

作者： Li, Meng Chen, Yifei Gao, Jianbo Wu, Jingyu Zhang, Zijian He, Jialing Zhu, Liehuang Conti, Mauro Lin, Xiaodong Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei230002 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230002 China Hefei University of Technology Anhui Province Key Laboratory of Industry Safety and Emergency Technology Intelligent Interconnected Systems Laboratory of Anhui Province Hefei230002 China Beijing Institute of Technology School of Cyberspace Science and Technology Beijing100811 China University of Science and Technology of China School of Computer Science and Technology Hefei230026 China Beijing Institute of Technology Southeast Institute of Information Technology Fujian Putian351100 China Chongqing University College of Computer Science Chongqing400044 China University of Padua Department of Mathematics HIT Center Padua35131 Italy Delft University of Technology Faculty of Electrical Engineering Mathematics and Computer Science Delft2628 CD Netherlands University of Guelph School of Computer Science GuelphONN1G 2W1 Canada

Navigation services enable users to find the shortest path from a starting point S to a destination D, reducing time, gas, and traffic congestion. Still, navigation users risk the exposure of their sensitive location data. Our motivation arises from how users can accurately, securely, and efficiently navigate from S to Dwhile passing through k unordered stops, i.e., midway locations with a non-fixed visiting order. In this work, we formally define Semi-Constrained Navigation (SCN) and present a novel scheme Hermestoachieveaccurate,secure, andefficient SCN. Specifically, weproposeadivide-and-conquerapproachtostrikeagoodbalance betweenaccuracyandefficiency. It recursively depth-first-searches the whole area (a navigation tree) and invokes five carefully-crafted strategies stop-by-stop to compute three subpaths in three se quential subareas. We construct a path-distance oracle to encrypt the road graph and securely implement the strategies by using homomorphic encryption and garble circuits. We formally prove the security in the random oracle model and analyze the search complexity to be less than O(k2). We experiment over a real-world city map and compare with six baselines. Results show that path search with k = 4 among N = 1000 intersections requires 5.58 seconds with a 3.2% distance deviation rate and an 82.5% path similarity. © 2004-2012 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

A data Association Method Based on Azimuth Inverse Cotangent Value

A Data Association Method Based on Azimuth Inverse Cotangent...

引用

International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE)

作者： Nan Zou Muze Yin Guangpu Zhang Zhenqi Yang Pengbo Ma Dongyu Li National Key Laboratory of Underwater Acoustic Technology Harbin Engineering University Harbin China Key Laboratory of Marine Information Acquisition and Security (Harbin Engineering University) Ministry of Industry and Information Technology Harbin China College of Underwater Acoustic Engineering Harbin Engineering University Harbin China Science and Technology on Electronic Information Control Laboratory Chengdu China

ISBN: (数字)9798331531836

ISBN: (纸本)9798331531843

In this paper, we address the challenge of data association in scenarios involving multiple observers for underwater non-cooperative localization, where it is unclear how measurement data from different stations corresponds to the same target. We propose a novel data association method that leverages the inverse cotangent of azimuthal sequence features. The method first calculates the sequence of cotangent values measured by each station's bearing in a limited time. Linearly analyzes the sequence to obtain the slope, and finally realizes the data association according to the characteristic that the inverse cotangent value of the slope corresponds to the target's motion heading. The simulation results show that the proposed method has better association localization ability compared with the traditional method, overcomes the problem of the conventional method that the computational volume is too large when the number of observation stations and targets is large, and ensures the association correctness under a certain error.

关键词： Location awareness Power engineering Accuracy Azimuth Simulation Noise Observers Time measurement

来源：评论

学校读者我要写书评

暂无评论

Research on DOA Estimation Method of Vector Hydrophone Array in Low SNR Based on CNN

Research on DOA Estimation Method of Vector Hydrophone Array...

引用

International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE)

作者： Nan Zou Yueming Li Jin Fu Guangpu Zang Zhiyao Du Yanhe Li National Key Laboratory of Underwater Acoustic Technology Key Laboratory of Marine Information Acquisition and Security(Harbin Engineering University) Ministry of Industry and Information Technology College of Underwater Acoustic Engineering Harbin Engineering University Harbin China College of Underwater Acoustic Engineering School of Electronic and Information EngineeringBeihang University Beijing China

ISBN: (数字)9798331531836

ISBN: (纸本)9798331531843

This paper presents a direction of arrival (DOA) estimation method for vector sensor arrays based on convolutional neural networks (CNN) to improve the estimation accuracy. The model consists of four convolutional layers and three fully connected layers. The network input is a three-channel data consisting of real part, imaginary part, and phase from the signal covariance matrix received by the array. Each node of the output stands for a presented directional grid, and the output value on that node indicates the probability of a signal locating in the neighborhood of the grid. The experimental results show that the neural network model can achieve 360-degree unambiguous estimation and is capable of acquiring precise and accurate estimation of DOA, especially in the cases of low signal-to-noise ratio (SNR).

关键词： Direction-of-arrival estimation Accuracy Azimuth Array signal processing Estimation Feature extraction Vectors Convolutional neural networks Signal to noise ratio Hydrophones

来源：评论

学校读者我要写书评

暂无评论

Exploiting Robust Model Watermarking Against the Model Fine-Tuning Attack via Flat Minima Aware Optimizers

Exploiting Robust Model Watermarking Against the Model Fine-...

引用

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

作者： Dongdong Lin Yue Li Bin Li Jiwu Huang Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen China SZU-AFS Joint Innovation Center for AI Technology Shenzhen University Shenzhen China Xiamen Key Laboratory of Data Security and Blockchain Technology Huaqiao University Xiamen China Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

With the rapid advancement of deep neural networks (DNNs), model watermarking has emerged as a widely adopted technique for safeguarding model copyrights. A prevalent method involves utilizing a watermark decoder to retrieve watermark bits from generated outputs, but such methods are often vulnerable to model fine-tuning attacks. Traditionally, this challenge is mitigated through adversarial training or data augmentation, both of which significantly increase the computational burden. In this paper, we present a solution employing Flat Minima Aware (FMA) optimizers to bolster the robustness of model watermarking without requiring additional training data. By optimizing the watermark loss with flat minima awareness, our approaches significantly enhance the robustness of watermarks against the model fine-tuning attack. Comprehensive experiments have demonstrated our method’s superior ability to preserve watermark integrity. These findings suggest that this innovative optimization strategy offers a robust and efficient pathway for protecting models, thereby contributing to more secure and reliable model copyright protection mechanisms.

关键词： Training Resistance Computational modeling Training data Watermarking Signal processing Diffusion models Robustness Speech processing Optimization

来源：评论

学校读者我要写书评

暂无评论

THC-DL: Three-Party Homomorphic Computing Delegation Learning for Secure Optimization

引用

IEEE Internet of Things Journal 2025年

作者： Yang, Ze Tian, Youliang Xiong, Jinbo Niu, Kun Li, Mengqian Zhang, Xinyu Ma, Jianfeng Guizhou University Guizhou Provincial Key Laboratory of Cryptography and Blockchain Technology College of Computer Science and Technology Guiyang550025 China Guizhou University College of Big Data and Information Engineering Guiyang550025 China Fujian Normal University Fujian Provincial Key Laboratory of Network Security and Cryptology College of Computer and Cyber Security Fuzhou350117 China Xidian University State Key Laboratory of Integrated Services Network Xi’an710071 China Xidian University State Key Laboratory of Integrated Services Network School of Cyber Engineering Xi’an710071 China

Delegation Learning(DL) flourishes data sharing, enabling agents to delegate data to the cloud for model training. To preserve privacy, homomorphic encryption (HE) offers an effective solution for privacy-preserving machine learning (PPML) in delegation learning, yet faces critical challenges in functionality (non-linear activation support), practicality (ciphertext blow-up from iterative computations), and security (data leakage risks caused by public knowledge of the mathematical principles applied in model training). To tackle these challenges, we propose THC-DL, a three-party HE framework addressing these challenges holistically for the first time. We elaborately design the ciphertext secure comparison (DL-CSC) protocol to satisfy secure comparison with private inputs, enabling efficient non-linear operations with O(1) communication complexity that reduces runtime to 12.5% of the DGK (Dolev-Greensmith-Kent protocol, the well-known comparison protocol). Second, we construct a Truncation-Mapping (Tru-Map) scheme, a mechanism that transforms input data by truncating and mapping it into a domain that facilitates more efficient processing, and the addition of truncated mapped data to resolve ciphertext blow-up by adaptively scaling ciphertexts during iterative training, ensuring correctness. Third, we formalize data leakage risks in HE-based quadratic convex optimization (standard in ML) and apply THC-DL to construct a secure optimization scheme. Theoretical analysis confirms THC-DL’s resilience against input recovery attacks, even when adversaries exploit public model parameters. Experiments on a real-world platform validate DL-CSC’s efficiency and scalability while reducing the computational complexity and communication complexity from O(n) to O(1) where n denotes the length of the input bits. © 2014 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Efficient Adaptive Label Refinement for label noise learning

引用

Neurocomputing 2025年 639卷

作者： Zhang, Wenzhen Cheng, Debo Lu, Guangquan Zhou, Bo Li, Jiaye Zhang, Shichao School of Computer Science and Engineering Guangxi Normal University Guangxi Guilin541004 China Guangxi Key Lab of Multi-Source Information Mining & Security Guangxi Normal University Guangxi Guilin541004 China Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guangxi Guilin541004 China School of Computer Science and Technology Hainan University Hainan Haikou570228 China Guangxi Collaborative Innovation Center of Modern Sericulture and Silk Hechi University Guangxi Hechi546300 China The State Key Laboratory of Blockchain and Data Security Zhejiang University Zhejiang Hangzhou310027 China

Deep neural networks are highly susceptible to overfitting noisy labels, which leads to degraded performance. Existing methods address this issue by employing complex manually designed strategies, aiming to achieve optimal partitioning in each iteration to avoid fitting noisy labels while thoroughly learning clean samples. However, this often results in models that are overly sensitive to hyperparameters and challenging to train. To address this issue, we decouple the tasks of avoiding fitting incorrect labels and thoroughly learning clean samples, proposing a simple yet highly applicable method called Adaptive Label Refinement (ALR). First, inspired by label refurbishment techniques, we update the original hard labels to soft labels using the model's predictions to reduce the risk of fitting incorrect labels. Then, by introducing entropy loss, the model adaptively ’harden’ the high-confidence soft labels based on the confidence differences, guiding the model to focus more on learning from clean samples. This approach is simple and efficient, requiring no auxiliary datasets and minimal hyperparameter tuning, making it more adaptable than existing methods that require careful adjustments for different datasets. We validate ALR's effectiveness through experiments on benchmark datasets with artificial label noise (CIFAR-10/100) and real-world datasets with inherent noise (ANIMAL-10N, Clothing1M, WebVision). The results show that ALR outperforms state-of-the-art methods. © 2025

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Animal Pose Estimation with Skeleton Anomaly-Aware Learning

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Han, Le Chen, Kaixuan Zhao, Lei Jiang, Yangbo Wang, Pengfei Zheng, Nenggan Zhejiang Hangzhou310007 China Zhejiang University College of Computer Science and Technology Zhejiang Hangzhou310007 China Zhejiang University State Key Laboratory of Blockchain and Data Security Zhejiang Hangzhou310007 China Institute of Blockchain and Data Security. China Zhejiang University School of Software Technology Ningbo China Zhejiang University State Key Lab of Brain-Machine Intelligence Hangzhou310007 China Zhejiang Provincial Government ZJU Collaborative Innovation Center for Artificial Intelligence by MOE Hangzhou310007 China Bengbu University School of Computer and Information Engineering Bengbu233030 China

Animal pose estimation is often constrained by the scarcity of annotations and the diversity of scenarios and species. The pseudo-label generation based unsupervised domain adaptation paradigm, which discriminates the predicted keypoints of unlabeled data based on the skeleton position consistency, has demonstrated effectiveness for such problems. However, existing methods generate pseudo-labels with massive false positives, because they cannot effectively distinguish sample pairs with the same errors. In this study, we propose a cross-domain animal pose estimation model from a novel perspective of skeleton anomaly learning. We construct a graph contrastive learning mechanism to acquire the skeleton anomaly-aware knowledge, which enables the generation of accurate pseudo-labels for target domain and imposes graph constraint on unlabeled data. And a skeleton anomaly-feedback based domain adaptation framework is designed to facilitate implicit alignment of object-specific features and joint training of cross-domain. Besides, we propose a novel rat pose dataset named UDARP-9.4K to address the gap of small-sized animal pose datasets encompassing diverse experimental scenarios. The related datasets are reviewed and evaluated in detail. Extensive experiments are conducted on UDARP-9.4K and two public datasets to demonstrate the superiority of the proposed model in cross-scenarios and cross-species animal pose estimation tasks. Further analysis reveals the effectiveness of the proposed model for skeleton structure feature learning. The UDARP-9.4K dataset is available here. © 1991-2012 IEEE.

关键词： Invertebrates

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：