检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Jiao, Yingying Wang, Zhigang Liu, Zhenguang Fan, Shaojing Wu, Sifan Wu, Zheqi Xu, Zhuoyue 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 The State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China School of Computing National University of Singapore Singapore

Human pose estimation has given rise to a broad spectrum of novel and compelling applications, including action recognition, sports analysis, as well as surveillance. However, accurate video pose estimation remains an open challenge. One aspect that has been overlooked so far is that existing methods learn motion clues from all pixels rather than focusing on the target human body, making them easily misled and disrupted by unimportant information such as background changes or movements of other people. Additionally, while the current Transformer-based pose estimation methods has demonstrated impressive performance with global modeling, they struggle with local context perception and precise positional identification. In this paper, we try to tackle these challenges from three aspects: (1) We propose a bilayer Human-keypoint Mask module that performs coarse-to-fine visual token refinement, which gradually zooms in on the target human body and keypoints while masking out unimportant figure regions. (2) We further introduce a novel deformable cross attention mechanism and a bidirectional separation strategy to adaptively aggregate spatial and temporal motion clues from constrained surrounding contexts. (3) We mathematically formulate the deformable cross attention, constraining that the model focuses solely on the regions centered at the target person body. Empirically, our method achieves state-of-the-art performance on three large-scale benchmark datasets. A remarkable highlight is that our method achieves an 84.8 mean Average Precision (mAP) on the challenging wrist joint, which significantly outperforms the 81.5 mAP achieved by the current state-of-the-art method on the PoseTrack2017 dataset. Copyright © 2025, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos

arXiv

引用

arXiv 2025年

作者： Jiao, Yingying Wang, Zhigang Wu, Sifan Fan, Shaojing Liu, Zhenguang Xu, Zhuoyue Wu, Zheqi 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 School of Computing National University of Singapore Singapore The State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China

Human pose estimation in videos remains a challenge, largely due to the reliance on extensive manual annotation of large datasets, which is expensive and labor-intensive. Furthermore, existing approaches often struggle to capture long-range temporal dependencies and overlook the complementary relationship between temporal pose heatmaps and visual features. To address these limitations, we introduce STDPose, a novel framework that enhances human pose estimation by learning spatiotemporal dynamics in sparsely-labeled videos. STDPose incorporates two key innovations: 1) A novel Dynamic-Aware Mask to capture long-range motion context, allowing for a nuanced understanding of pose changes. 2) A system for encoding and aggregating spatiotemporal representations and motion dynamics to effectively model spatiotemporal relationships, improving the accuracy and robustness of pose estimation. STDPose establishes a new performance benchmark for both video pose propagation (i.e., propagating pose annotations from labeled frames to unlabeled frames) and pose estimation tasks, across three large-scale evaluation datasets. Additionally, utilizing pseudo-labels generated by pose propagation, STDPose achieves competitive performance with only 26.7% labeled data. Copyright © 2025, The Authors. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Boosting Short Text Classification with Multi-Source Information Exploration and Dual-Level Contrastive Learning

arXiv

引用

arXiv 2025年

作者： Liu, Yonghao Li, Mengyu Pang, Wei Giunchiglia, Fausto Huang, Lan Feng, Xiaoyue Guan, Renchu Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education College of Computer Science and Technology Jilin University China Mathematical and Computer Sciences Heriot-Watt University United Kingdom University of Trento Italy

Short text classification, as a research subtopic in natural language processing, is more challenging due to its semantic sparsity and insufficient labeled samples in practical scenarios. We propose a novel model named MI-DELIGHT for short text classification in this work. Specifically, it first performs multi-source information (i.e., statistical information, linguistic information, and factual information) exploration to alleviate the sparsity issues. Then, the graph learning approach is adopted to learn the representation of short texts, which are presented in graph forms. Moreover, we introduce a dual-level (i.e., instance-level and cluster-level) contrastive learning auxiliary task to effectively capture different-grained contrastive information within massive unlabeled data. Meanwhile, previous models merely perform the main task and auxiliary tasks in parallel, without considering the relationship among tasks. Therefore, we introduce a hierarchical architecture to explicitly model the correlations between tasks. We conduct extensive experiments across various benchmark datasets, demonstrating that MI-DELIGHT significantly surpasses previous competitive models. It even outperforms popular large language models on several datasets. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

UAV-assisted Joint Mobile Edge Computing and data Collection via Matching-enabled Deep Reinforcement Learning

arXiv

引用

arXiv 2025年

作者： Wang, Boxiong Kang, Hui Li, Jiahui Sun, Geng Sun, Zemin Wang, Jiacheng Niyato, Dusit College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China College of Computing and Data Science Nanyang Technological University 639798 Singapore College of Computing and Data Science Nanyang Technological University Singapore

Unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) and data collection (DC) have been popular research issues. Different from existing works that consider MEC and DC scenarios separately, this paper investigates a multi-UAV-assisted joint MEC-DC system. Specifically, we formulate a joint optimization problem to minimize the MEC latency and maximize the collected data volume. This problem can be classified as a non-convex mixed integer programming problem that exhibits long-term optimization and dynamics. Thus, we propose a deep reinforcement learning-based approach that jointly optimizes the UAV movement, user transmit power, and user association in real time to solve the problem efficiently. Specifically, we reformulate the optimization problem into an action space-reduced Markov decision process (MDP) and optimize the user association by using a two-phase matching-based association (TMA) strategy. Subsequently, we propose a soft actor-critic (SAC)-based approach that integrates the proposed TMA strategy (SAC-TMA) to solve the formulated joint optimization problem collaboratively. Simulation results demonstrate that the proposed SAC-TMA is able to coordinate the two subsystems and can effectively reduce the system latency and improve the data collection volume compared with other benchmark algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

A Clustering-Based Color Reordering Method for Reversible data Hiding in Palette Images

引用

IET Image Processing 2025年第1期19卷

作者： Deng, Jianxuan Chen, Yi Wang, Hongxia Guo, Chun Cui, Yunhe Shen, Guowei State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education Guizhou University Guiyang China School of Cyber Science and Engineering Sichuan University Chengdu China

A recent research work pointed out that the reversible data hiding algorithms proposed for gray-scale images can be implemented on the reconstructed palette images to improve embedding capacity and visual quality by reordering the color table. However, the reordering effect has a significant impact on performance improvement. Therefore, we propose a clustering-based color reordering method for reversible data hiding in palette images to improve the reordering effect and further enhance the performance. In this method, we first design a centroid initialization method to select the initial centroids and then exploit the K-means algorithm to generate (Formula presented.) clusters for the colors in the original color table. In the following, our proposed method, respectively, reorders the colors of these clusters by a greedy strategy and concatenates them into the reordered color table. Based on the relationship between the original and the reordered color tables, a novel index matrix can be reconstructed. Finally, state-of-the-art reversible data hiding algorithms can be implemented on the reconstructed index matrix for performance improvement. Since our proposed method improves the reordering effect, enhances the correlation of the reconstructed index matrix, and reduces the length of the encoded location map, the maximal embedding capacities and the visual quality under the fixed embedding capacities are improved. We conducted experiments on two image datasets and six standard images to verify that the performance improvement of our proposed reordering method is better than that of the state-of-the-art methods. © 2025 The Author(s). IET Image Processing published by John Wiley & Sons Ltd on behalf of The Institution of engineering and Technology.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Preference Completion with Ranked and Unranked Preferences

引用

Cognitive Computation 2025年第3期17卷 1-21页

作者： Li, Lei Liu, Pan Zhang, Renjie Tao, Zhenchao Wu, Xindong Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China Department of Radiation Oncology The First Affiliated Hospital of USTC Division of Life Sciences and Medicine University of Science and Technology of China Hefei China Department of Radiation Oncology Anhui Provincial Cancer Hospital Hefei China

As for social choice, all alternatives are ranked by agents to form preferences as linear orders. However, in applications, sometimes some alternatives cannot be ranked, or it is unnecessary to rank them, which leads to unranked alternatives. Hence, without loss of generality, by dividing the set of alternatives into three ranked and unranked subsets, including top-k alternatives, intermediate-r alternatives, and last-l alternatives, the Mallows model on ranked and unranked preferences can be analyzed systematically. Technically, a repeated insertion model is adopted during sampling, and probability distributions are derived for ranked and unranked preferences of alternatives. Experimental results verify the accuracy of the probability distributions for different ranked and unranked preferences of alternatives. Furthermore, in order to solve the preference completion problem where agents have multiple partial rankings, a fuzzy preference completion algorithm, Fuzzy-Multi-Rankings, is proposed, which introduces a fuzzy ranking to complete the target agent’s preference in addition to the traditional nearest-neighbor-based methods. Based on the three ranked and unranked preferences, seven cases can be classified and analyzed for fuzzy preference completion. Experiments on the synthetic datasets and MovieLens dataset confirm the effectiveness and efficiency of our proposed Fuzzy-Multi-Rankings algorithm and also verify the accuracy of the evaluated probability distributions for the proposed seven cases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SwimVG: Step-wise Multimodal Fusion and Adaption for Visual Grounding

arXiv

引用

arXiv 2025年

作者： Shi, Liangtao Liu, Ting Hu, Xiantao Hu, Yue Yin, Quanjun Hong, Richang Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Hefei230009 China Ministry of Education and School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China School of systems engineering National University of Defense Technology Hunan Province Changsha410073 China Department of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210014 China

Visual grounding aims to ground an image region through natural language, which heavily relies on cross-modal alignment. Most existing methods transfer visual/linguistic knowledge separately by fully fine-tuning uni-modal pre-trained models, followed by a simple stack of visual-language transformers for multimodal fusion. However, these approaches not only limit adequate interaction between visual and linguistic contexts, but also incur significant computational costs. Therefore, to address these issues, we explore a step-wise multimodal fusion and adaption framework, namely SwimVG. Specifically, SwimVG proposes step-wise multimodal prompts (Swip) and cross-modal interactive adapters (CIA) for visual grounding, replacing the cumbersome transformer stacks for multimodal fusion. Swip can improve the alignment between the vision and language representations step by step, in a token-level fusion manner. In addition, weight-level CIA further promotes multimodal fusion by cross-modal interaction. Swip and CIA are both parameter-efficient paradigms, and they fuse the cross-modal features from shallow to deep layers gradually. Experimental results on four widely-used benchmarks demonstrate that SwimVG achieves remarkable abilities and considerable benefits in terms of efficiency. Our code is available at https://***/liuting20/SwimVG. Copyright © 2025, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

DBMGNet: A Dual-Branch Mamba-GCN Network for Hyperspectral Image Classification

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Wang, Hao Zhuang, Peixian Zhang, Xiaochen Li, Jiangyun University of Science and Technology Beijing School of Automation and Electrical Engineering Beijing100083 China University of Science and Technology Beijing Key Laboratory of Knowledge Automation for Industrial Processes Ministry of Education the School of Automation and Electrical Engineering Beijing100083 China Shunde Graduate School of University of Science and Technology Beijing China

In hyperspectral image (HSI) classification, convolutional neural networks (CNNs) excel at local feature modeling but are limited to Euclidean space. Transformers offer long-range dependency modeling but suffer from high computational complexity. In contrast, graph convolutional networks (GCNs) can process information in non-Euclidean space, compensating for the limitations of CNNs. Meanwhile, the state space model Mamba, thanks to its linear complexity and strong long-range dependency modeling, shows great potential to offer an alternative to Transformers for HSI classification. To address the limitations of CNNs and Transformers while exploiting the potential of Mamba, we propose a dual-branch hybrid architecture named DBMGNet that combines Mamba with GCN for the HSI classification. In the Mamba branch, we design Band Selection Enhanced Bidirectional Mamba (BSEBM), which leverages Mamba’s long-range dependency modeling and sequential modeling capabilities to process spatial-spectral information. In the GCN branch, we apply reparameterized Chebyshev graph convolution to model similarity dependencies in non-Euclidean space, along with designing an adjacency matrix based on the intrinsic characteristics of HSIs. Extensive experiments demonstrate that our DBMGNet achieves the state-of-the-art performance of HSI classification against thirteen mainstream approaches. © 1980-2012 IEEE.

关键词： NP-hard

来源：评论

学校读者我要写书评

暂无评论

A Novel Privacy-Enhancing Framework for Low-Dose CT Denoising

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Yang, Ziyuan Huangfu, Huijie Ran, Maosong Wang, Zhiwen Yu, Hui Sun, Mengyu Zhang, Yi Sichuan University College of Computer Science Chengdu610065 China Sichuan University Key Laboratory of Data Protection and Intelligent Management Ministry of Education Chengdu610065 China Sichuan University School of Cyber Science and Engineering Chengdu610065 China

Deep learning (DL) has made significant advancements in tomographic imaging, particularly in low-dose computed tomography (LDCT) denoising. A recent trend involves servers training powerful models with enormous self-collected data and providing application programming interfaces (APIs) for users, such as Chat-GPT. To avoid model leakage, users are required to upload their data to the server. This approach is particularly advantageous for devices with limited computational capabilities, as it offloads computation to the server, easing the workload on the devices themselves. However, this way raises public concerns about the privacy disclosure risk. Hence, to alleviate related concerns, we propose to directly denoise LDCT in the encrypted domain to achieve privacy-preserving cloud services without exposing private data to the server. Concretely, we employ homomorphic encryption to encrypt private LDCT, which is then transferred to the server model trained with plaintext LDCT for further denoising. Since fundamental DL operations, such as convolution and linear transformation, cannot be directly used in the encrypted domain, we transform the fundamental mathematic operations in the plaintext domain into the operations in the encrypted domain. Moreover, we present two interactive frameworks for linear and nonlinear models, both of which can achieve lossless operating. In this way, the proposed methods can achieve two merits, the data privacy is well protected and the server model is free from the risk of model leakage. Moreover, we provide theoretical proof to validate the lossless property of our framework. Finally, experiments were conducted to demonstrate that the transferred contents are well protected and cannot be reconstructed.1 © 2020 IEEE.

关键词： Differential privacy

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

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

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：