检索结果-内蒙古大学图书馆

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

作者： Yuheng Yang Haipeng Chen College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Skeleton-based action recognition has long been a fundamental and intriguing problem in machine intelligence. This task is challenging due to pose occlusion and rapid motion, which typically results in incomplete or noisy skeleton data. State-of-the-art methods tend to learn human motion directly from these corrupted skeletons as if they were reliable. Unfortunately, this might lead to unsatisfactory results when key regions of the skeleton are occluded or disturbed. To tackle the problem, we propose a novel framework that integrates auxiliary tasks into a motion modeling network. These auxiliary tasks corrupt partial human skeletons with masking or noise and then force the network to recover the corrupted data, explicitly facilitating robust feature representation learning. We further propose supervising the auxiliary tasks with mutual information losses, mathematically ensuring feature consistency and spatial alignment between the recovered and original skeleton data. Empirically, our approach sets the new state-of-the-art performance on three benchmark datasets.

关键词： Representation learning Noise Speech recognition Benchmark testing Skeleton Mathematical models Reliability Noise measurement Speech processing Mutual information

来源：评论

学校读者我要写书评

暂无评论

Structure-Based Uncertainty Estimation for Source-Free Active Domain Adaptation

引用

IET Computer Vision 2025年第1期19卷

作者： Ouyang, Jihong Zhang, Zhengjie Meng, Qingyi Chi, Jinjin 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

Active domain adaptation (active DA) provides an effective solution by selectively labelling a limited number of target samples to significantly enhance adaptation performance. However, existing active DA methods often struggle in real-world scenarios where, due to data privacy concerns, only a pre-trained source model is available, rather than the source samples. To address this issue, we propose a novel method called the structure-based uncertainty estimation model (SUEM) for source-free active domain adaptation (SFADA). To be specific, we introduce an innovative active sample selection strategy that combines both uncertainty and diversity sampling to identify the most informative samples. We assess the uncertainty in target samples using structure-wise probabilities and implement a diversity selection method to minimise redundancy. For the selected samples, we not only apply standard-supervised loss but also conduct interpolation consistency training to further explore the structural information of the target domain. Extensive experiments across four widely used datasets demonstrate that our method is comparable to or outperforms current UDA and active DA methods. © 2025 The Author(s). IET Computer Vision published by John Wiley & Sons Ltd on behalf of The Institution of engineering and Technology.

关键词： computer vision convolutional neural nets image classification

来源：评论

学校读者我要写书评

暂无评论

Task-oriented Multi-domain Adversarial Network for fake news detection

引用

Applied Soft Computing 2025年 177卷

作者： Zeqi, Guo Jihong, Ouyang Ximing, Li Changchun, Li 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 proliferation of fake news on online social media has severely misled public perception of event authenticity. To combat this, various Fake News Detection (FND) methods have been developed for specific domains, typically requiring large amounts of labeled data for effective training. However, in some domains, labeled data remains scarce. Multi-domain Fake News Detection (MFND) provides a solution by training a model with data from multiple domains to identify news veracity across domains. Despite its potential, discrepancies in feature distributions across domains, known as domain shift, can negatively impact the effectiveness of joint training. To mitigate this, we propose the Task-oriented Multi-domain Adversarial Network (TMDA-NET), a novel MFND model designed to align feature distributions across domains within a unified feature space using domain adversarial learning. This approach enhances generalization in data-scarce domains. Given that FND is domain-dependent, we also propose a fusion mechanism with adjustable weights to incorporate domain-specific characteristics. Additionally, we introduce two task-oriented auxiliary classification tasks to efficiently align and integrate features, ultimately improving FND accuracy. Extensive experiments on publicly available Chinese and English datasets validate the effectiveness of our proposed model. © 2025

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Hybrid Parameter Update: Alleviating Imbalance Impacts for Distributed Deep Learning 24

Hybrid Parameter Update: Alleviating Imbalance Impacts for D...

引用

24th IEEE International Conference on High Performance Computing and Communications, 8th IEEE International Conference on Data Science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Li, Hongliang Xu, Dong Xu, Zhewen Li, Xiang College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education Changchun China

ISBN: (纸本)9798350319934

Nowadays, data parallelism has been widely applied to train large datasets on distributed deep learning clusters, but it has suffered from costly global parameter updates at batch barriers. Performance imbalance among worker instances, introduced by uneven workload partitioning or biased resource allocation, can cause straggly workers, which can lead to severe impacts on both training speed and result accuracy. This paper studies the issue focusing on the tradeoff between training speed and result accuracy. We propose Cooperate Grouping Parallel (CGP), a hybrid parameter update solution that allows the flexibility of both synchronous and asynchronous update schemes. We introduce a novel Cooperate Worker Grouping Problem (CWGP) that seeks a task grouping configuration that leads to maximum model accuracy and holds customized training speed guarantees. We propose an evolution-based Pareto local searching algorithm to compute efficient worker grouping configurations. Comprehensive evaluation results are presented to demonstrate the effectiveness of CGP under both persistent and fluctuant imbalances. The proposed method alleviates the imbalance impacts without introducing extra adjustment over-heads. © 2022 IEEE.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

In-context decision transformer: reinforcement learning via hierarchical chain-of-thought 24

In-context decision transformer: reinforcement learning via ...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Sili Huang Jifeng Hu Hechang Chen Lichao Sun Bo Yang School of Artificial Intelligence and Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China School of Artificial Intelligence Jilin University China Lehigh University Bethlehem Pennsylvania Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China

In-context learning is a promising approach for offline reinforcement learning (RL) to handle online tasks, which can be achieved by providing task prompts. Recent works demonstrated that in-context RL could emerge with self-improvement in a trial-and-error manner when treating RL tasks as an across-episodic sequential prediction problem. Despite the self-improvement not requiring gradient updates, current works still suffer from high computational costs when the across-episodic sequence increases with task horizons. To this end, we propose an In-context Decision Transformer (IDT) to achieve self-improvement in a high-level trial-and-error manner. Specifically, IDT is inspired by the efficient hierarchical structure of human decision-making and thus reconstructs the sequence to consist of high-level decisions instead of low-level actions that interact with environments. As one high-level decision can guide multi-step low-level actions, IDT naturally avoids excessively long sequences and solves online tasks more efficiently. Experimental results show that IDT achieves state-of-the-art in long-horizon tasks over current in-context RL methods. In particular, the online evaluation time of our IDT is 36× times faster than baselines in the D4RL benchmark and 27× times faster in the Grid World benchmark.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Automatic Solution in Security Inspection

An Automatic Solution in Security Inspection

引用

International Conference on Machine Vision and Information Technology (CMVIT)

作者： Hui Zhang Xiaoli Zhang Key Laboratory of Symbolic Computation and Knowledge Engineer Ministry of Education Changchun China

In this paper, we present a brand new dataset named cellphone buttery defects in X-ray(CBDx). CBDx consists of 300 X-ray images and 250 of them are anomaly free. We name them ‘good’. Others have some defects in the area of buttery. We name them ‘anomaly’, as Fig. 1. It raises a new task of detecting anomaly defects of cellphone butteries. But the challenge is how to distinguish the anomaly in the case of only training the ‘good’ cellphone. We define this task as an anomaly detection task. We propose an approach to deal with the task from the perspective of unbalanced classification. Specifically, we propose a data augmentation strategy that creates an anomaly sample mimic to the real defects. It helps the classifier to learn self-supervised deep representations and then make it an one-class classifier based on the representations. The classifier is well designed to discriminate the defect samples from the good ones. We evaluate different data augmentation strategies on CBDx. Our approach is more significant in this scenario with no defect training samples, which can be applied in real-world security inspection someday. Also, it can be used on the industrial texture anomaly detection, such as MVTec_AD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Multi-label Learning with Balanced Binary Angular Margin Loss 38

Semi-supervised Multi-label Learning with Balanced Binary An...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Li, Ximing Liang, Silong Li, Changchun Wang, Pengfei Gu, Fangming College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China Computer Network Information Center Chinese Academy of Sciences China University of Chinese Academy of Sciences Chinese Academy of Sciences China

Semi-supervised multi-label learning (SSMLL) refers to inducing classifiers using a small number of samples with multiple labels and many unlabeled samples. The prevalent solution of SSMLL involves forming pseudo-labels for unlabeled samples and inducing classifiers using both labeled and pseudo-labeled samples in a self-training manner. Unfortunately, with the commonly used binary type of loss and negative sampling, we have empirically found that learning with labeled and pseudo-labeled samples can result in the variance bias problem between the feature distributions of positive and negative samples for each label. To alleviate this problem, we aim to balance the variance bias between positive and negative samples from the perspective of the feature angle distribution for each label. Specifically, we extend the traditional binary angular margin loss to a balanced extension with feature angle distribution transformations under the Gaussian assumption, where the distributions are iteratively updated during classifier training. We also suggest an efficient prototype-based negative sampling method to maintain high-quality negative samples for each label. With this insight, we propose a novel SSMLL method, namely Semi-Supervised Multi-Label Learning with Balanced Binary Angular Margin loss (S2ML2-BBAM). To evaluate the effectiveness of S2ML2-BBAM, we compare it with existing competitors on benchmark datasets. The experimental results validate that S2ML2-BBAM can achieve very competitive performance. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Structure-and Logic-Aware Heterogeneous Graph Learning for Recommendation 40

Structure-and Logic-Aware Heterogeneous Graph Learning for R...

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Li, Anchen Yang, Bo Huo, Huan Hussain, Farookh Khadeer Xu, Guandong College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China Aalto University Espoo Finland School of Computer Science University of Technology Sydney Sydney Australia Education University of Hong Kong Hong Kong Hong Kong

ISBN: (纸本)9798350317152

Recently, there has been a surge in recommendations based on heterogeneous information networks (HINs), attributed to their ability to integrate complex and rich semantics. Despite this advancement, most HIN-based recommenders overlook two critical aspects. First, they often fail to consider HIN's heterophily nature, hindering the capture of non-local structures in HINs. Second, most methods lack the capability for logical reasoning. In this paper, we propose a novel structure-and logic-aware heterogeneous graph learning framework for recommender systems (SLHRec). Our SLHRec contains a structure-aware module and a logic-aware module. The former uses network geometry to construct non-local neighborhoods for nodes in HINs, and then introduces a graph neural network to integrate constructed neighbors for modeling the heterophily of HINs. The logic-aware module uses the Markov logic network (MLN) to infuse logic rules into heterogeneous graph learning, thereby boosting logic reasoning in recommendations. Furthermore, we utilize contrastive learning to model cooperative signals between modules, enabling them to complement each other. In the prediction stage, both modules contribute to generating recommendations. Compared with several strong recommender baselines, our SLHRec achieves superior performance on four real-world datasets. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Dilated Convolutional Pixels Affinity Network for Weakly Supervised Semantic Segmentation

引用

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

来源：评论

学校读者我要写书评

暂无评论

SMRI: A New Method for siRNA Design for COVID-19 Therapy

引用

Journal of Computer Science & Technology 2022年第4期37卷 991-1002页

作者： Meng-Xin Chen Xiao-Dong Zhu Hao Zhang Zhen Liu Yuan-Ning Liu College of Software Jilin UniversityChangchun 130012China Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education Jilin UniversityChangchun 130012China College of Computer Science and Technology Jilin UniversityChangchun 130012China Graduate School of Engineering Nagasaki Institute of Applied ScienceNagasaki 851-0193Japan

First discovered in Wuhan, China, SARS-CoV-2 is a highly pathogenic novel coronavirus, which rapidly spreads globally and becomes a pandemic with no vaccine and limited distinctive clinical drugs available till March 13th, 2020. Ribonucleic Acid interference (RNAi) technology, a gene-silencing technology that targets mRNA, can cause damage to RNA viruses effectively. Here, we report a new efficient small interfering RNA (siRNA) design method named Simple Multiple Rules Intelligent Method (SMRI) to propose a new solution of the treatment of COVID-19. To be specific, this study proposes a new model named Base Preference and Thermodynamic Characteristic model (BPTC model) indicating the siRNA silencing efficiency and a new index named siRNA Extended Rules index (SER index) based on the BPTC model to screen high-efficiency siRNAs and filter out the siRNAs that are difficult to take effect or synthesize as a part of the SMRI method, which is more robust and efficient than the traditional statistical indicators under the same circumstances. Besides, to silence the spike protein of SARS-CoV-2 to invade cells, this study further puts forward the SMRI method to search candidate high-efficiency siRNAs on SARS-CoV-2's S gene. This study is one of the early studies applying RNAi therapy to the COVID-19 treatment. According to the analysis, the average value of predicted interference efficiency of the candidate siRNAs designed by the SMRI method is comparable to that of the mainstream siRNA design algorithms. Moreover, the SMRI method ensures that the designed siRNAs have more than three base mismatches with human genes, thus avoiding silencing normal human genes. This is not considered by other mainstream methods, thereby the five candidate high-efficiency siRNAs which are easy to take effect or synthesize and much safer for human body are obtained by our SMRI method, which provide a new safer, small dosage and long efficacy solution for the treatment of COVID-19.

关键词： COVID-19 SARS-CoV-2 RibonucleicAcid interference

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：