检索结果-内蒙古大学图书馆

Reconsidering Feature Structure Information and Latent Space Alignment in Partial Multi-label Feature Selection

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Pan, Hanlin Liu, Kunpeng Gao, Wanfu College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China Department of Computer Science Portland State University PortlandOR97201 United States

The purpose of partial multi-label feature selection is to select the most representative feature subset, where the data comes from partial multi-label datasets that have label ambiguity issues. For label disambiguation, previous methods mainly focus on utilizing the information inside the labels and the relationship between the labels and features. However, the information existing in the feature space is rarely considered, especially in partial multi-label scenarios where the noises is considered to be concentrated in the label space while the feature information is correct. This paper proposes a method based on latent space alignment, which uses the information mined in feature space to disambiguate in latent space through the structural consistency between labels and features. In addition, previous methods overestimate the consistency of features and labels in the latent space after convergence. We comprehensively consider the similarity of latent space projections to feature space and label space, and propose new feature selection term. This method also significantly improves the positive label identification ability of the selected features. Comprehensive experiments demonstrate the superiority of the proposed method. Copyright © 2025, The Authors. All rights reserved.

关键词： Feature extraction

Hyponymy Graph Model for Word Semantic Similarity Measurement

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2015年第1期24卷 96-101页

作者： WANG Junhua ZUO Wanli PENG Tao College of Computer Science and Technology Jilin University Key Laboratory of Symbol Computation and Knowledge Engineering attached to the Ministry of Education

Measuring word semantic similarity is a generic problem with a broad range of applications such as ontology mapping, computational linguistics and artificial intelligence. Previous approaches to computing word semantic similarity did not consider concept occurrence frequency and word’s sense number. This paper introduced Hyponymy graph, and based on which proposed a novel word semantic similarity model. For two words to be compared, we first retrieve their related concepts; then produce lowest common ancestor matrix and distance matrix between concepts; finally calculate distance-based similarity and information-based similarity, which are integrated to get final semantic similarity. The main contribution of our method is that both concept occurrence frequency and word’s sense number are taken into account. This similarity measurement more closely fits with human rating and effectively simulates human thinking process. Our experimental results on benchmark dataset M&C and R&G with Word Net2.1 as platform demonstrate roughly 0.9%–1.2%improvements over existing best approaches.

关键词： Word semantic similarity Concept semantic similarity Semantic similarity Hyponymy graph model Word Net.

Dilated Convolutional Pixels Affinity Network for Weakly Supervised Semantic Segmentation

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2021年第6期30卷 1120-1130页

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

This paper studies semantic segmentation primarily under image-level weak-supervision. Most stateof-the-art technologies have recently used deep classification networks to create small and sparse discriminatory seed regions of each interest target as pseudo-labels for training segmentation networks, which achieve inferior performance compared with the fully supervised *** propose a Dilated convolutional pixels affinity network(DCPAN) to localize and expand the seed regions of objects to bridge this gap. Although introduced dilated convolutional units enable capture of additional location information of objects, it falsely highlighted true negative regions as dilated rate enlarge. To address this problem,we properly integrate dilated convolutional units with different dilated rates and self-attention mechanisms to obtain pixel affinity measure matrix for promoting classification network to generate high-quality object seed regions as pseudo-labels; thus, the performance of the segmentation network is boosted. Furthermore,although our approach seems simple, our method obtains a competitive performance, and experiments show that the performance of DCPAN outperforms other state-ofart approaches in weakly-supervised settings, which only use image-level labels on the Pascal VOC 2012 dataset.

关键词： weakly supervised semantic segmentation pseudolabels deep classification networks high-quality object seed regions pattern classification image segmentation weakly-supervised settings dilated convolutional pixels affinity network image-level weak-supervision image classification DCPAN self-attention mechanism object recognition feature extraction object detection sparse discriminatory seed regions pixel affinity measure matrix Pascal VOC 2012 dataset

A Novel Iterative Velocity Control Algorithm and Its FPGA Implementation Based on Trigonometric Function

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2019年第2期28卷 237-245页

作者： WEN Quangang LIANG Yanchun Adriano Tavares Ricardo Teixeira WU Chunguo Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Zhuhai Laboratory of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Zhuhai College of Jilin University Department of Industrial Electronics University of Minho Campus de Azurm

The servo motor’s flexible acceleration/deceleration(acc/dec) control is an emerging research topic in the automation field. A velocity control algorithm based on trigonometric function is proposed in this *** required parameters, it transforms trigonometric calculations into elementary mathematical operations and calculates the velocity controlling values iteratively, which could avoid trigonometric calculation and reduce the computation time. Experimental results show that the proposed algorithm is suitable for implementation on field programmable gate arrays and achieves a flexible controlling, enhancing both the equipment’s stability and reliability. It is promising to significantly improve the high-speed computerized numerical control equipment’s controlling accuracy, without a huge hardware resource consumption.

关键词： Acceleration Velocity control Algorithm design and analysis Field programmable gate arrays Servomotors

Deep-Learning-Based Integration of Sequence and Structure Information for Efficiently Predicting miRNA-Drug Associations

学校读者我要写书评

暂无评论

Journal of Chemical Information and Modeling 2025年 2025 May 17页

作者： Sheng, Nan Liu, Yunzhi Gao, Ling Wang, Lei Si, Chenxu Huang, Lan Wang, Yan Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education College of Computer Science and Technology Jilin University ChangChun 130012 China

Extensive research has shown that microRNAs (miRNAs) play a crucial role in cancer progression, treatment, and drug resistance. They have been recognized as promising potential therapeutic targets for overcoming drug resistance in cancer treatment. However, limited attention has been paid to predicting the association between miRNAs and drugs by computational methods. Existing approaches typically focus on constructing miRNA-drug interaction graphs, which may result in their performance being limited by interaction density. In this work, we propose a novel deep learning method that integrates sequence and structural information to infer miRNA-drug associations (MDAs), called DLST-MDA. This approach innovates by utilizing attribute information on miRNAs and drugs instead of relying on the commonly used interaction graph information. Specifically, considering the sequence lengths of miRNAs and drugs, DLST-MDA employs multiscale convolutional neural network (CNN) to learn sequence embeddings at different granularity levels from miRNA and drug sequences. Additionally, it leverages the power of graph neural networks to capture structural information from drug molecular graphs, providing a more representational analysis of the drug features. To evaluate DLST-MDA’s effectiveness, we manually constructed a benchmark data set for various experiments based on the latest databases. Results indicate that DLST-MDA performs better than other state-of-the-art methods. Furthermore, case studies of three common anticancer drugs can evidence their usefulness in discovering novel MDAs. The data and source code are released at https://***/sheng-n/DLST-MDA. © 2025 American Chemical Society.

关键词： Drug interactions

Optimizing Human Pose Estimation Through Focused Human and Joint Regions

学校读者我要写书评

暂无评论

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

Intelligent CPSS and its application to health care computing

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2016年第5期59卷 10-12页

作者： Dayou LIU Bo YANG Shang GAO Yungang ZHU Yong LAI College of Computer Science and Technology Jilin University Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Jilin University

The rapid development of cyber-physical systems(CPS)had a tremendous impact on human behavior and *** human involvement,CPS has naturally evolved into cyberphysical social systems(CPSS)[1].The top five technology brea... 详细信息

关键词： CPSS net

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

学校读者我要写书评

暂无评论

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

SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos

学校读者我要写书评

暂无评论

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