检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Wenhao Wang, Jun Luo, Yong Yu, Lei Yu, Wei He, Zheng Shen, Jialie School of Computer Science National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China School of Electronics and Information Wuhan University China Department of Computer Science City University of London United Kingdom

ISBN: (纸本)157735897X

Lip-reading is to utilize the visual information of the speaker's lip movements to recognize words and sentences. Existing event-based lip-reading solutions integrate different frame rate branches to learn spatio-temporal features of varying granularities. However, aggregating events into event frames inevitably leads to the loss of fine-grained temporal information within frames. To remedy this drawback, we propose a novel framework termed Multi-view Temporal Granularity aligned Aggregation (MTGA). Specifically, we first present a novel event representation method, namely time-segmented voxel graph list, where the most significant local voxels are temporally connected into a graph list. Then we design a spatio-temporal fusion module based on temporal granularity alignment, where the global spatial features extracted from event frames, together with the local relative spatial and temporal features contained in voxel graph list are effectively aligned and integrated. Finally, we design a temporal aggregation module that incorporates positional encoding, which enables the capture of local absolute spatial and global temporal information. Experiments demonstrate that our method outperforms both the event-based and video-based lip-reading counterparts. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Disambiguated Attention Embedding for Multi-Instance Partial-Label Learning

arXiv

引用

arXiv 2023年

作者： Tang, Wei Zhang, Weijia Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China School of Information and Physical Sciences The University of Newcastle CallaghanNSW2308 Australia

In many real-world tasks, the concerned objects can be represented as a multi-instance bag associated with a candidate label set, which consists of one ground-truth label and several false positive labels. Multi-instance partial-label learning (MIPL) is a learning paradigm to deal with such tasks and has achieved favorable performances. Existing MIPL approach follows the instance-space paradigm by assigning augmented candidate label sets of bags to each instance and aggregating bag-level labels from instance-level labels. However, this scheme may be suboptimal as global bag-level information is ignored and the predicted labels of bags are sensitive to predictions of negative instances. In this paper, we study an alternative scheme where a multi-instance bag is embedded into a single vector representation. Accordingly, an intuitive algorithm named DEMIPL, i.e., Disambiguated attention Embedding for Multi-Instance Partial-Label learning, is proposed. DEMIPL employs a disambiguation attention mechanism to aggregate a multi-instance bag into a single vector representation, followed by a momentum-based disambiguation strategy to identify the ground-truth label from the candidate label set. Furthermore, we introduce a real-world MIPL dataset for colorectal cancer classification. Experimental results on benchmark and real-world datasets validate the superiority of DEMIPL against the compared MIPL and partial-label learning approaches. Copyright © 2023, The Authors. All rights reserved.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Transformer-based Multi-Instance Learning for Weakly Supervised Object Detection

arXiv

引用

arXiv 2023年

作者： Wang, Zhaofei Zhang, Weijia Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China School of Information and Physical Sciences The University of Newcastle CallaghanNSW2308 Australia

Weakly Supervised Object Detection (WSOD) enables the training of object detection models using only image-level annotations. State-of-the-art WSOD detectors commonly rely on multi-instance learning (MIL) as the backbone of their detectors and assume that the bounding box proposals of an image are independent of each other. However, since such approaches only utilize the highest score proposal and discard the potentially useful information from other proposals, their independent MIL backbone often limits models to salient parts of an object or causes them to detect only one object per class. To solve the above problems, we propose a novel backbone for WSOD based on our tailored Vision Transformer named Weakly Supervised Transformer Detection network (WSTDN). Our algorithm is not only the first to demonstrate that self-attention modules that consider inter-instance relationships are effective backbones for WSOD, but also we introduce a novel bounding box mining method (BBM) integrated with a memory transfer refinement (MTR) procedure to utilize the instance dependencies for facilitating instance refinements. Experimental results on PASCAL VOC2007 and VOC2012 benchmarks demonstrate the effectiveness of our proposed WSTDN and modified instance refinement modules. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Multi-dimensional classification via stacked dependency exploitation

引用

Science China(information Sciences) 2020年第12期63卷 104-117页

作者： Bin-Bin JIA Min-Ling ZHANG School of Computer Science and Engineering Southeast University College of Electrical and Information Engineering Lanzhou University of Technology Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of EducationChina Collaborative Innovation Center of Wireless Communications Technology

Multi-dimensional classification(MDC) aims to build classification models for multiple heterogenous class spaces simultaneously, where each class space characterizes the semantics of an object w.r.t. one specific dimension. Modeling dependencies among class spaces plays a key role in solving MDC tasks, where most approaches work by assuming directed acyclic graph(DAG) structure or random chaining structure over class spaces. Different from existing probabilistic strategies, a deterministic strategy named Seem for dependency modeling is proposed in this paper via stacked dependency exploitation. In the first-level, pairwise dependencies are considered which can be modeled more reliably than modeling full dependencies among all class spaces by DAG or chaining structure. In the second-level, the class label of unseen instance *** class space is determined by adaptively stacking predictive outputs from first-level pairwise *** results show that stacked dependency exploitation leads to superior performance against stateof-the-art MDC approaches.

关键词： machine learning multi-dimensional classification class dependencies deterministic strategy stacked dependency exploitation

来源：评论

学校读者我要写书评

暂无评论

PAIR: Complementarity-guided Disentanglement for Composed Image Retrieval

PAIR: Complementarity-guided Disentanglement for Composed Im...

引用

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

作者： Zhiheng Fu Zixu Li Zhiwei Chen Chunxiao Wang Xuemeng Song Yupeng Hu Liqiang Nie School of Software Shandong University Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences) School of Computer Science and Technology Shandong University School of Computer Science and Technology Harbin Institute of Technology (Shenzhen)

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Composed Image Retrieval (CIR) is a novel image retrieval paradigm that aims at searching for the target images via the multimodal query including a reference image and a modification text. Although existing works have made significant progress, they overlook the inter-modal coherence and incoherence relations modeling, hindering the retrieval accuracy of CIR models. This limitation is non-trivial due to the following two challenges: 1) inter-modal incoherence and 2) intra-modal entanglement. To address the above challenges, we propose a comPlementArity-guided dIsentanglement network (PAIR), which can disentangle the features of multimodal queries from a semantic coherence perspective, thereby facilitating the identification of both complementary coherent and incoherent features. Furthermore, based on disentangled features, PAIR develops an asymmetric feature composition module, which is designed to enhance the retrieval performance of the model. Extensive experiments on three benchmark datasets demonstrate the superiority of PAIR. The code is available at https://***/***/.

关键词： Codes Accuracy Image retrieval Semantics Coherence Benchmark testing Signal processing Acoustics Speech processing Protection

来源：评论

学校读者我要写书评

暂无评论

Towards an Ontology of Traceable Impact Management in the Food Supply Chain

arXiv

引用

arXiv 2025年

作者： Gajderowicz, Bart Fox, Mark S. Gao, Yongchao Urban Data Centre School of Cities University of Toronto Toronto Canada Key Laboratory of Computing Power Network and Information Security Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Jinan China

The pursuit of quality improvements and accountability in the food supply chains, especially how they relate to food-related outcomes, such as hunger, has become increasingly vital, necessitating a comprehensive approach that encompasses product quality and its impact on various stakeholders and their communities. Such an approach offers numerous benefits in increasing product quality and eliminating superfluous measurements while appraising and alleviating the broader societal and environmental repercussions. A traceable impact management model (TIMM) provides an impact structure and a reporting mechanism that identifies each stakeholder’s role in the total impact of food production and consumption stages. The model aims to increase traceability’s utility in understanding the impact of changes on communities affected by food production and consumption, aligning with current and future government requirements, and addressing the needs of communities and consumers. This holistic approach is further supported by an ontological model that forms the logical foundation and a unified terminology. By proposing a holistic and integrated solution across multiple stakeholders, the model emphasizes quality and the extensive impact of championing accountability, sustainability, and responsible practices with global traceability. With these combined efforts, the food supply chain moves toward a global tracking and tracing process that not only ensures product quality but also addresses its impact on a broader scale, fostering accountability, sustainability, and responsible food production and consumption. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MEDIAN: Adaptive Intermediate-grained Aggregation network for Composed Image Retrieval

MEDIAN: Adaptive Intermediate-grained Aggregation Network fo...

引用

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

作者： Qinlei Huang Zhiwei Chen Zixu Li Chunxiao Wang Xuemeng Song Yupeng Hu Liqiang Nie School of Software Shandong University Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences) School of Computer Science and Technology Shandong University School of Computer Science and Technology Harbin Institute of Technology (Shenzhen)

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The Composed Image Retrieval (CIR) task aims to retrieve a target image that meets the requirements based on a given multimodal query (includes a reference image and modification text). Most existing works align multimodal semantics at both local and global granularity. However, they have failed to consider the mining of semantic correspondences at the intermediate-grained level, which has resulted in sub-optimal model performance. In this paper, we propose an adaptive interMEDiate-graIned Aggregation network (MEDIAN). Compared with the conventional CIR models, MEDIAN is capable of generating intermediate-grained feature aggregation supervised signals and constructing graph attention networks to extract intermediate-grained features. Concurrently, MEDIAN also devises cross-modal semantic correspondence aligning guided by the target image, which in turn enables accurate multi-grained feature composition. The superiority of MEDIAN is demonstrated by extensive experiments on three benchmark datasets. Our code is available at https://***/***/.

关键词： Adaptation models Adaptive systems Accuracy Codes Semantics Image retrieval Benchmark testing Signal processing Feature extraction Speech processing

来源：评论

学校读者我要写书评

暂无评论

Revocable Registered Attribute-Based Encryption With User Deregistration

引用

IEEE Internet of Things Journal 2025年

作者： Li, Jiguo Chen, Shaobo Lu, Yang Ning, Jianting Shen, Jian Zhang, Yichen Fujian Normal University College of Computer and Cyber Security Fuzhou350117 China Fuzhou350117 China Fujian Provincial Key Laboratory of Network Security and Cryptology Fuzhou350117 China Nanjing Normal University School of Computer and Electronic Information Nanjing210023 China Fujian Provincial Key Laboratory of Network Security and Cryptology College of Computer and Cyber Security Fuzhou350117 China Zhejiang Sci-Tech University School of Information Science and Engineering Hangzhou310018 China

Many businesses are putting their sensitive data in the cloud with the fast growth of cloud computing and storage. To ensure user privacy, it is necessary to keep encrypted data only in the cloud. Attribute-based encryption (ABE) is a popular mean in cloud storage scenarios. ABE is not only faced with key escrow problem but also suffers from user revocation issue when he or she is no longer authorized to access to encrypted data. In order to address these two issues, we propose a revocable registered attribute-based encryption scheme, which not only avoids key escrow problem but also supports precise revocation of a user’s access to a file as well as permanent deregistration of a user from the system. Furthermore, we prove the semantic security of the scheme and conduct a performance experiment to show the efficiency. © 2014 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Short Text Clustering Using Joint Optimization of Feature Representations and Cluster Assignments 18th

Short Text Clustering Using Joint Optimization of Feature Re...

引用

18th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2021

作者： Sun, Liping Du, Tingli Duan, Xiaoyu Luo, Yonglong School of Computer and Information Anhui Normal University Wuhu Anhui241002 China Anhui Provincial Key Laboratory of Network and Information Security Anhui Normal University Wuhu Anhui241002 China

ISBN: (纸本)9783030893620

The application of traditional text clustering methods to short text data is inefficient owing to the high dimensionality and semantic sparseness of such data. Contrastingly, convolutional neural networks can capture the local information between consecutive words in a sentence and extract the semantic features of the text. In this paper, we propose a short text clustering method based on convolutional autoencoders (CAE-STC) that jointly optimizes feature representations and cluster assignments. The proposed method employs a convolutional autoencoder to learn deep text feature representations and preserve the local structure of text generation distribution. By integrating the clustering loss and convolutional autoencoder’s reconstruction loss, a unified loss function is formulated to update the network parameters and cluster centers iteratively, improving the performance of the feature learning and clustering tasks. The results of extensive experiments conducted on three public short text datasets demonstrate that the proposed method outperforms several popular clustering methods in terms of the normalized mutual information and clustering accuracy. © 2021, Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

The Design and Implementation of KMeans Based on Unified Batch and Streaming Processing 15th

The Design and Implementation of KMeans Based on Unified Bat...

引用

15th CCF Conference on computer Supported Cooperative Work and Social Computing, Chinese CSCW 2020

作者： Chen, Hao Guo, Kun Chen, Yuzhong Guo, Hong College of Mathematics and Computer Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350108 China

ISBN: (纸本)9789811625398

Clustering algorithms aim at gathering similar data points from a dataset in an unsupervised manner. Although the batch clustering algorithms have relatively high accuracy, they cannot make use of the dynamic clustering results efficiently. The requirement of using the whole dataset in calculation results in the problems of resource waste and high time cost. On the contrary, incremental clustering only needs to update the varied part of a model upon the arrival of new data, which makes it unnecessary to recluster the whole data all the time. The feature is very suitable for the streaming data process, but it decreases the accuracy of the algorithms and cannot satisfy the low latency requirement of real-time data processing. In response to this problem, the paper proposes a novel unified batch and streaming clustering model (UBSCM) based on streaming computation, which includes a streaming cluster feature updating mechanism (SCFUM). The Flink framework is used to implement a new streaming KMeans algorithm based on UBSCM (KMeansUBSP). The experiments on the real-world datasets validate that the new streaming KMeans algorithm is effective in clustering the batch and streaming data in a unified manner. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Clustering algorithms

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：