检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Deng, Xiaozhi Huang, Dong Chen, Ding-Hua Wang, Chang-Dong Lai, Jian-Huang The College of Mathematics and Informatics South China Agricultural University Guangzhou China The School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Deep clustering has attracted increasing attention in recent years due to its capability of joint representation learning and clustering via deep neural networks. In its latest developments, the contrastive learning has emerged as an effective technique to substantially enhance the deep clustering performance. However, the existing contrastive learning based deep clustering algorithms mostly focus on some carefully-designed augmentations (often with limited transformations to preserve the structure), referred to as weak augmentations, but cannot go beyond the weak augmentations to explore the more opportunities in stronger augmentations (with more aggressive transformations or even severe distortions). In this paper, we present an endto-end deep clustering approach termed Strongly Augmented Contrastive Clustering (SACC), which extends the conventional two-augmentation-view paradigm to multiple views and jointly leverages strong and weak augmentations for strengthened deep clustering. Particularly, we utilize a backbone network with triply-shared weights, where a strongly augmented view and two weakly augmented views are incorporated. Based on the representations produced by the backbone, the weak-weak view pair and the strong-weak view pairs are simultaneously exploited for the instance-level contrastive learning (via an instance projector) and the cluster-level contrastive learning (via a cluster projector), which, together with the backbone, can be jointly optimized in a purely unsupervised manner. Experimental results on five challenging image datasets have shown the superiority of our SACC approach over the state-of-the-art. The code is available at https://***/dengxiaozhi/SACC. © 2022, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition

arXiv

引用

arXiv 2024年

作者： Zhou, Jiaming Liang, Junwei Lin, Kun-Yu Yang, Jinrui Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Hong Kong University of Science and Technology Guangzhou China AI Thrust Hong Kong University of Science and Technology Guangzhou China CSE Hong Kong University of Science and Technology Hong Kong Computer Science and Engineering Department University of California Santa Cruz United States The School of Computer Science and Engineering The Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Sun Yat-sen University Guangzhou510275 China The Peng Cheng Laboratory Shenzhen518005 China

Zero-shot action recognition (ZSAR) aims to learn an alignment model between videos and class descriptions of seen actions that is transferable to unseen actions. There is a rich diversity in video content, including complex scenes, dynamic human motions, etc. The text queries (class descriptions) used in existing ZSAR works, however, are often short action names that fail to capture the rich semantics in the videos, leading to misalignment. With the intuition that video content descriptions (e.g., video captions) can provide rich contextual information of visual concepts in videos, which helps model understand human actions from text modality, we propose to utilize human annotated video descriptions to enrich the semantics of the class descriptions of each action. However, all existing action video description datasets are limited in terms of the number of actions, the diversity of actions, the semantics of video descriptions, etc. To this end, we collect a large-scale action video descriptions dataset named ActionHub, which covers a total of 1,211 common actions and provides 3.6 million action video descriptions. With the proposed ActionHub dataset, we find that the semantics of human actions can be better captured from the textual modality, such that the cross-modality diversity gap between videos and texts in ZSAR is alleviated, and a transferable alignment is learned for recognizing unseen actions. To achieve this, we further propose a novel Cross-modality and Cross-action Modeling (CoCo) framework for ZSAR, which consists of a Dual Cross-modality Alignment module and a Cross-action Invariance Mining module. Specifically, the Dual Cross-modality Alignment module utilizes both action labels and video descriptions from ActionHub to obtain rich class semantic features for feature alignment. The Cross-action Invariance Mining module exploits a cycle-reconstruction process between the class semantic feature spaces of seen actions and unseen actions, aiming to guide

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Deterministic Algorithms for the Hidden Subgroup Problem

arXiv

引用

arXiv 2021年

作者： Ye, Zekun Li, Lvzhou Institute of Quantum Computing and Computer Theory School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

We consider deterministic algorithms for the well-known hidden subgroup problem (HSP): for a finite group G and a finite set X, given a function f: G → X and the promise that for any g1, g2 ∈ G, f(g1) = f(g2) iff g1H = g2H for a subgroup H ≤ G, the goal of the decision version is to determine whether H is trivial or not, and the goal of the identification version is to identify H. An algorithm for the problem should query f(g) for g ∈ G at least as possible. Nayak [25] asked whether there exist deterministic algorithms with O(√|G|/|H|) query complexity for HSP. We answer this problem by proving the following results, which also extend the main results of Ref. [30], since here the algorithms do not rely on any prior knowledge of H. (i) When G is a general finite Abelian group, there exist an algorithm with O(√|G|/|H| |) queries to decide the triviality of H and an algorithm to identify H with O(√|G|/|H| log |H| + log |H|) queries. (ii) In general there is no deterministic algorithm for the identification version of HSP with query complexity of O(√|G|/|H|), since there exists an instance of HSP that needs ω(√|G|/|H|) queries to identify H.1 On the other hand, there exist instances of HSP with query complexity far smaller than O(√|G|/|H|), whose query complexity is O(log |G|/|H|) and even O(1). © 2021, CC BY.

关键词： Group theory

来源：评论

学校读者我要写书评

暂无评论

Syntax-enhanced pre-trained model 59

Syntax-enhanced pre-trained model

引用

Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021

作者： Xu, Zenan Guo, Daya Tang, Duyu Su, Qinliang Shou, Linjun Gong, Ming Zhong, Wanjun Quan, Xiaojun Jiang, Daxin Duan, Nan School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Microsoft Research Asia Beijing China Microsoft Search Technology Center Asia Beijing China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Key Lab. of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (纸本)9781954085527

We study the problem of leveraging the syntactic structure of text to enhance pre-trained models such as BERT and RoBERTa. Existing methods utilize syntax of text either in the pre-training stage or in the fine-tuning stage, so that they suffer from discrepancy between the two stages. Such a problem would lead to the necessity of having human-annotated syntactic information, which limits the application of existing methods to broader scenarios. To address this, we present a model that utilizes the syntax of text in both pre-training and fine-tuning stages. Our model is based on Transformer with a syntax-aware attention layer that considers the dependency tree of the text. We further introduce a new pre-training task of predicting the syntactic distance among tokens in the dependency tree. We evaluate the model on three downstream tasks, including relation classification, entity typing, and question answering. Results show that our model achieves state-of-the-art performance on six public benchmark datasets. We have two major findings. First, we demonstrate that infusing automatically produced syntax of text improves pre-trained models. Second, global syntactic distances among tokens bring larger performance gains compared to local head relations between contiguous tokens. © 2021 Association for Computational Linguistics

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Analysis of Artifactual Components Rejection Threshold towards Enhanced Characterization of Neural Activity in Post-Stroke Survivor

Analysis of Artifactual Components Rejection Threshold towar...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Mojisola Grace Asogbon Yaping Huai Oluwarotimi Williams Samuel Zhengxiang Jing Yixin Ma Jingyu Liu Yibo Jiang Yunfa Fu Guanglin Li Yongcheng Li CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology (SIAT) Chinese Academy of Sciences (CAS) Shenzhen Guangdong China Department of Rehabilitation Medicine Shenzhen Longhua District Central Hospital Shenzhen Guangdong China School of Computing and Engineering University of Derby Derby United Kingdom Department of Information Engineering and Automation Kunming University of Science and Technology Yunnan China

Research advancement has spurred the usage of electroencephalography (EEG)-based neural oscillatory rhythms as a biomarker to complement clinical rehabilitation strategies for the recovery of motor functions in stroke survivors. However, the inevitable contamination of EEG signals with artifacts from various sources limits its utilization and effectiveness. Thus, the integration of Independent Component Analysis (ICA) and Independent Component Label (ICLabel) has been widely employed to separate neural activity from artifacts. A crucial step in the ICLabel preprocessing pipeline is the artifactual ICs rejection threshold (TH) parameter, which determines the overall signal's quality. For instance, selecting a high TH will cause many ICs to be rejected, thereby leading to signal over-cleaning, and choosing a low TH may result in under-cleaning of the signal. Toward determining the optimal TH parameter, this study investigates the effect of six different TH groups (NO-TH and TH1-TH6) on EEG signals recorded from post-stroke patients who performed four distinct motor imagery (MI) tasks including wrist and grasping movements. Utilizing the EEG-beta band signal at the brain's sensorimotor cortex, the performance of the TH groups was evaluated using three notable EEG quantifiers. Overall, the obtained result shows that the considered THs will significantly alter neural oscillatory patterns. Comparing the performance of the TH-groups, TH-3 with a confidence level of 60% showed consistently stronger signal desynchronization and lateralization. The correlation result shows that most of the electrode pairs with high correlation values are replicable across all the MI tasks. It also revealed that brain activity correlates linearly with distance, and a strong correlation between electrode pairs is independent of the different brain cortices. The study outcome may facilitate adequate therapeutic intervention for stroke *** Relevance: This study indicated that optimal s

关键词：

来源：评论

学校读者我要写书评

暂无评论

Genetic and phenotypic relationships between coronary atherosclerotic heart disease and electrocardiographic traits

Genetic and phenotypic relationships between coronary athero...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xinfeng Wang Haoyang Zhang Xuehao Xiu Mengling Qi Yuedong Yang Huiying Zhao Key Laboratory of Machine Intelligence and Advanced Computing of MOE School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation Department of Medical Research Center Sun Yat-sen Memorial Hospital Guangzhou China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Observational studies have revealed that Coronary Atherosclerotic Heart Disease (CAHD) is associated with abnormal electrocardiogram (ECG) traits. However, it remains unclear whether there are genetic correlations between ECG and CAHD. Here, we explored genetic correlations and putative causal relationships between CAHD and ECG by performing Mendelian randomization (MR) and Polygenic risk score (PRS) analyses on the summary statistics from a large-scale genome-wide association study (GWAS) for CAHD (FinnGen: Ncase 23363, Ncontrol 187840) and ECG traits (UK Biobank: Ncase=1137, Ncontrol=40823). Results showed a causal genetic relationship between CAHD and six ECG traits in the lead V6. These ECG traits combining with age and gender have predicted CAHD risk with an AUC of 0.76. Further summary data-based Mendelian randomization (SMR) analysis identified 11 risk genes associated with the causality between CAHD and ECG. Thus, the revealed putative causal effects of CAHD on ECG traits provide genetic evidence to support the importance of monitoring CAHD risk through the ECG.

关键词： Heart Correlation Genomics Atherosclerosis Electrocardiography Lead Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Potential Indicator for Continuous Emotion Arousal by Dynamic Neural Synchrony 4th

Potential Indicator for Continuous Emotion Arousal by Dyna...

引用

4th International Workshop on Human Brain and Artificial intelligence, HBAI 2024

作者： Pan, Guandong Wu, Zhaobang Yang, Yaqian Wang, Xin Liu, Longzhao Zheng, Zhiming Tang, Shaoting School of Computer Science and Engineering Beihang University Beijing100191 China Institute of Artificial Intelligence Beihang University Beijing100191 China Key Laboratory of Mathematics Informatics and Behavioral Semantics Beihang University Beijing100191 China Institute of Medical Artificial Intelligence Binzhou Medical University Yantai264003 China Zhongguancun Laboratory Beijing100094 China Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beihang University Beijing100191 China PengCheng Laboratory Shenzhen518055 China State Key Lab of Software Development Environment Beihang University Beijing100191 China

ISBN: (纸本)9789819640003

The need for automatic and high-quality emotion annotation is paramount in applications such as continuous emotion recognition and video highlight detection, yet achieving this through manual human annotations is challenging. Inspired by inter-subject correlation (ISC) utilized in neuroscience, this study introduces a novel Electroencephalography (EEG) based ISC methodology that leverages a single-electrode and feature-based dynamic approach. Our contributions are three folds: Firstly, we reidentify two potent emotion features suitable for classifying emotions-first-order difference (FD) an differential entropy (DE). Secondly, through the use of overall correlation analysis, we demonstrate the heterogeneous synchronized performance of electrodes. This performance aligns with neural emotion patterns established in prior studies, thus validating the effectiveness of our approach. Thirdly, by employing a sliding window correlation technique, we showcase the significant consistency of dynamic ISCs across various features or key electrodes in each analyzed film clip. Our findings indicate the method’s reliability in capturing consistent, dynamic shared neural synchrony among individuals, triggered by evocative film stimuli. This underscores the potential of our approach to serve as an indicator of continuous human emotion arousal. The implications of this research are significant for advancements in affective computing and the broader neuroscience field, suggesting a streamlined and effective tool for emotion analysis in real-world applications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Electroencephalography (EEG) Emotion Annotation Inter-subject Correlation

来源：评论

学校读者我要写书评

暂无评论

Neural multi-objective combinatorial optimization with diversity enhancement 23

Neural multi-objective combinatorial optimization with diver...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Jinbiao Chen Zizhen Zhang Zhiguang Cao Yaoxin Wu Yining Ma Te Ye Jiahai Wang School of Computer Science and Engineering Sun Yat-sen University P.R. China School of Computing and Information Systems Singapore Management University Singapore Department of Industrial Engineering & Innovation Sciences Eindhoven University of Technology Netherlands Department of Industrial Systems Engineering & Management National University of Singapore Singapore School of Computer Science and Engineering Sun Yat-sen University P.R. China and Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Sun Yat-sen University P.R. China and Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou P.R. China

Most of existing neural methods for multi-objective combinatorial optimization (MOCO) problems solely rely on decomposition, which often leads to repetitive solutions for the respective subproblems, thus a limited Pareto set. Beyond decomposition, we propose a novel neural heuristic with diversity enhancement (NHDE) to produce more Pareto solutions from two perspectives. On the one hand, to hinder duplicated solutions for different subproblems, we propose an indicator-enhanced deep reinforcement learning method to guide the model, and design a heterogeneous graph attention mechanism to capture the relations between the instance graph and the Pareto front graph. On the other hand, to excavate more solutions in the neighborhood of each subproblem, we present a multiple Pareto optima strategy to sample and preserve desirable solutions. Experimental results on classic MOCO problems show that our NHDE is able to generate a Pareto front with higher diversity, thereby achieving superior overall performance. Moreover, our NHDE is generic and can be applied to different neural methods for MOCO.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Bi-directional Recommender System for Online Recruitment

A Bi-directional Recommender System for Online Recruitment

引用

IEEE International Conference on Data Mining (ICDM)

作者： Zhe-Rui Yang Zhen-Yu He Chang-Dong Wang Pei-Yuan Lai De-Zhang Liao Zhong-Zheng Wang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Computational Science Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China South China Technology Commercialization Center Guangzhou China School of Information Engineering Guangdong University of Technology Guangzhou China

Most existing recommendation research has been concentrated on unidirectional recommendation, i.e. only recommending items to users. However, in many real-world scenarios, the platform needs to achieve bi-directional recommendation. For example, in an online recruitment scenario, the recommender system not only needs to recommend positions to candidates, but also recommend candidates to enterprises. In this paper, we first formalize a new recommendation problem called bi-directional recommendation and contribute a new bidirectional recommendation model named BiROR (Bi-directional Recommendation for Online Recruitment). In BiROR, an encoder component is utilized to learn the text embeddings, and a graph learning component is designed to learn the graph embeddings. In addition, a multi-task learning framework is designed to achieve bi-directional recommendation. In the multi-task learning framework, we share the text embeddings and graph embeddings to alleviate the problems of data sparsity and data asymmetry in online recruitment. Extensive experiments in a real-world task show that BiROR outperforms the state-of-the-art methods, verifying the effectiveness of the designs of our model.

关键词： Bidirectional control Multitasking Data models Data mining Task analysis Recommender systems Recruitment

来源：评论

学校读者我要写书评

暂无评论

Online Metro Origin-Destination Prediction via Heterogeneous Information Aggregation

arXiv

引用

arXiv 2021年

作者： Liu, Lingbo Zhu, Yuying Li, Guanbin Wu, Ziyi Bai, Lei Lin, Liang School of Computer Science and Engineering Sun Yat-Sen University 510000 China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Engineering Research Center for Advanced Computing Engineering Software of Ministry of Education China GuangDong Province Key Laboratory of Information Security Technology China School of Electrical and Information Engineering The University of Sydney 2000 Australia

Metro origin-destination prediction is a crucial yet challenging time-series analysis task in intelligent transportation systems, which aims to accurately forecast two specific types of cross-station ridership, i.e., Origin-Destination (OD) one and Destination-Origin (DO) one. However, complete OD matrices of previous time intervals can not be obtained immediately in online metro systems, and conventional methods only used limited information to forecast the future OD and DO ridership separately. In this work, we proposed a novel neural network module termed Heterogeneous Information Aggregation Machine (HIAM), which fully exploits heterogeneous information of historical data (e.g., incomplete OD matrices, unfinished order vectors, and DO matrices) to jointly learn the evolutionary patterns of OD and DO ridership. Specifically, an OD modeling branch estimates the potential destinations of unfinished orders explicitly to complement the information of incomplete OD matrices, while a DO modeling branch takes DO matrices as input to capture the spatial-temporal distribution of DO ridership. Moreover, a Dual Information Transformer is introduced to propagate the mutual information among OD features and DO features for modeling the OD-DO causality and correlation. Based on the proposed HIAM, we develop a unified Seq2Seq network to forecast the future OD and DO ridership simultaneously. Extensive experiments conducted on two large-scale benchmarks demonstrate the effectiveness of our method for online metro origin-destination prediction. Our code is resealed at https://***/HCPLab-SYSU/HIAM. Copyright © 2021, The Authors. All rights reserved.

关键词： Forecasting

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：