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

The Equivalent Representation of the Breadth-One D-Invariant Polynomial Subspace and Its Discretization

引用

Journal of Systems Science & Complexity 2016年第5期29卷 1436-1445页

作者： JIANG Xue ZHANG Shugong Institute of Mathematics Key Laboratory of Symbolic Computation and Knowledge Engineering (Ministry of Education) Jilin University

This paper demonstrates the equivalence of two classes of D-invariant polynomial subspaces, i.e., these two classes of subspaces are different representations of the breadth-one D-invariant subspace. Moreover, the authors solve the discrete approximation problem in ideal interpolation for the breadth-one D-invariant subspace. Namely, the authors find the points, such that the limiting space of the evaluation functionals at these points is the functional space induced by the given D-invariant subspace, as the evaluation points all coalesce at one point.

关键词： Breadth-one D-invariant polynomial subspace discrete approximation problem idealinterpolation.

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

HVIS: A Human-like Vision and Inference System for Human Motion Prediction

arXiv

引用

arXiv 2025年

作者： Lyu, Kedi Chen, Haipeng Liu, Zhenguang Yin, Yifang Lin, Yukang Jiao, Yingying College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Institute of Blockchain and Data Security Hangzhou China A*STAR Singapore Tsinghua Shenzhen International Graduate School Nanshan District Shenzhen China

Grasping the intricacies of human motion, which involve perceiving spatio-temporal dependence and multi-scale effects, is essential for predicting human motion. While humans inherently possess the requisite skills to navigate this issue, it proves to be markedly more challenging for machines to emulate. To bridge the gap, we propose the Human-like Vision and Inference System (HVIS) for human motion prediction, which is designed to emulate human observation and forecast future movements. HVIS comprises two components: the human-like vision encode (HVE) module and the human-like motion inference (HMI) module. The HVE module mimics and refines the human visual process, incorporating a retina-analog component that captures spatiotemporal information separately to avoid unnecessary crosstalk. Additionally, a visual cortex-analogy component is designed to hierarchically extract and treat complex motion features, focusing on both global and local features of human poses. The HMI is employed to simulate the multi-stage learning model of the human brain. The spontaneous learning network simulates the neuronal fracture generation process for the adversarial generation of future motions. Subsequently, the deliberate learning network is optimized for hard-to-train joints to prevent misleading learning. Experimental results demonstrate that our method achieves new state-of-the-art performance, significantly outperforming existing methods by 19.8% on Human3.6M, 15.7% on CMU Mocap, and 11.1% on G3D. © 2025, CC BY.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

A Survey on Performance Optimization of High-Level Synthesis Tools

引用

Journal of Computer Science & Technology 2020年第3期35卷 697-720页

作者： Lan Huang Da-Lin Li Kang-Ping Wang Teng Gao Adriano Tavares College of Computer Science and Technology Jilin UniversityChangchun 130012China Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun 130012China Zhuhai Laboratory of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Zhuhai College of Jilin University Zhuhai 519041China Algorithm Center University of MinhoGuimaraes 4800058Portugal

Field-programmable gate arrays(FPGAs)have recently evolved as a valuable component of the heterogeneous *** register transfer level(RTL)design flows demand the designers to be experienced in hardware,resulting in a possible failure of ***-level synthesis(HLS)permits designers to work at a higher level of abstraction through synthesizing high-level language programs to RTL *** provides a promising approach to solve these ***,the performance of HLS tools still has *** example,designers remain exposed to various aspects of hardware design,development cycles are still time consuming,and the quality of results(QoR)of HLS tools is far behind that of RTL *** this paper,we survey the literature published since 2014 focusing on the performance optimization of HLS *** with previous work,we extend the scope of the performance of HLS tools,and present a set of three-level evaluation criteria,covering from ease of use of the HLS tools to promotion on specific metrics of *** also propose performance evaluation equations for describing the relation between the performance optimization and the *** find that it needs more efforts on the ease of use for efficient HLS *** suggest that it is better to draw an analogy between the HLS development process and the embedded system design process,and to provide more elastic HLS methodology which integrates FPGAs virtual machines.

关键词： evaluation criterion field-programmable gate array(FPGA) high-level synthesis(HLS) performance optimization quality of results(QoR)

来源：评论

学校读者我要写书评

暂无评论

Attention Guided Enhancement Network for Weakly Supervised Semantic Segmentation

引用

Chinese Journal of Electronics 2023年第4期32卷 896-907页

作者： ZHANG Zhe WANG Bilin YU Zhezhou ZHAO Fengzhi College of Computer Science and Technology Jilin University Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry

Weakly supervised semantic segmentation using only image-level labels is critical since it alleviates the need for expensive pixel-level labels. Most cuttingedge methods adopt two-step solutions that learn to produce pseudo-ground-truth using only image-level labels and then train off-the-shelf fully supervised semantic segmentation network with these pseudo labels. Although these methods have made significant progress, they also increase the complexity of the model and training. In this paper, we propose a one-step approach for weakly supervised image semantic segmentation—attention guided enhancement network(AGEN), which produces pseudopixel-level labels under the supervision of image-level labels and trains the network to generate segmentation masks in an end-to-end manner. Particularly, we employ class activation maps(CAM) produced by different layers of the classification branch to guide the segmentation branch to learn spatial and semantic ***, the CAM produced by the lower layer can capture the complete object region but with many ***, the self-attention module is proposed to enhance object regions adaptively and suppress irrelevant object regions, further boosting the segmentation *** on the Pascal VOC 2012 dataset demonstrate that AGEN outperforms alternative state-of-the-art weakly supervised semantic segmentation methods exclusively relying on image-level labels.

关键词： Training Annotations Semantic segmentation Scalability Semantics Benchmark testing Boosting

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

Dual Space Representation Learning for Skeleton-based Action Recognition

引用

IEEE Signal Processing Letters 2025年

作者： Yang, Yuheng Chen, Haipeng Liu, Zhenguang Hu, Sihao Jiao, Yingying Jilin University College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun 130012 China Zhejiang University School of Cyber Science and Technology Hangzhou 310007 China Georgia Institute of Technology College of Computing GA United States

Skeleton-based action recognition is crucial for machine intelligence. Current methods generally learn from 3D articulated motion sequences in the straightforward Euclidean space. Yet, the vanilla Euclidean space may not be the optimal choice for modeling the intricate correlations among human body joints. This challenge arises from the non-Euclidean nature of human anatomy, where joint correlations often vary non-linearly during movement. To address this, we propose a dual space representation learning method. Specifically, we represent the motion sequences in Hyperbolic space, leveraging its intrinsic properties to capture the non-Euclidean latent anatomy of human motions. We then incorporate the motion features from both Hyperbolic and Euclidean spaces, allowing us to precisely model the non-linear joint correlations while effectively sketching human poses. The proposed method empirically achieves state-of-the-art performance on the NTU RGB+D 60, NTURGB+D 120, and NW-UCLA datasets. © 1994-2012 IEEE.

关键词： Hyperbolic space representation learning Skeleton-based action recognition

来源：评论

学校读者我要写书评

暂无评论

Relating brain structure images to personality characteristics using 3D convolution neural network

引用

CAAI Transactions on Intelligence Technology 2021年第3期6卷 338-346页

作者： Lixian Cao Yanchun Liang Wei Lv Kaechang Park Yasuhiro Miura Yuki Shinomiya Shinichi Yoshida Zhuhai Laboratory of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Zhuhai College of Jilin UniversityZhuhaiChina Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education College of Computer Science and TechnologyJilin UniversityChangchunChina School of Information&Research Institute Kochi University of TechnologyKochiJapan

The Keras deep learning framework is employed to study MRI brain data in a preliminary analysis of brain structure using a convolutional neural *** results obtained are matched with the content of personality *** Big Five personality traits provide easy differentiation for dividing personalities into different *** now,the highest accuracy obtained from the results of personality prediction from the analysis of brain structure is about 70%.Although there is still no effective evidence to prove a clear relationship between brain structure and personality,the obtained results could prove helpful in understanding the basic relationship between brain structure and personality characteristics.

关键词： convolution structure dividing

来源：评论

学校读者我要写书评

暂无评论

A Novel Method for Prediction of Protein Domain Using Distance-Based Maximal Entropy

引用

Journal of Bionic engineering 2008年第3期5卷 215-223页

作者： Shu-xue Zou Yan-xin Huang Yan Wang Chun-guang Zhou Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Changchun 130012 P. R. China

Detecting the boundaries of protein domains is an important and challenging task in both experimental and computational structural biology. In this paper, a promising method for detecting the domain structure of a protein from sequence information alone is presented. The method is based on analyzing multiple sequence alignments derived from a database search. Multiple measures are defined to quantify the domain information content of each position along the sequence. Then they are combined into a single predictor using support vector machine. What is more important, the domain detection is first taken as an imbal- anced data learning problem. A novel undersampling method is proposed on distance-based maximal entropy in the feature space of Support Vector Machine （SVM）. The overall precision is about 80%. Simulation results demonstrate that the method can help not only in predicting the complete 3D structure of a protein but also in the machine learning system on general im- balanced datasets.

关键词： protein domain boundary SVM imbalanced data learning distance-based maximal entropy

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：