检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

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

ISBN: (纸本)157735897X

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, 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

High-Dimensional Multi-Label data Stream Classification With Concept Drifting Detection

引用

IEEE Transactions on knowledge and data engineering 2023年第8期35卷 8085-8099页

作者： Li, Peipei Zhang, Haixiang Hu, Xuegang Wu, Xindong Anhui Province Key Laboratory of Industry Safety and Emergency Technology Hefei230601 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China Second People's Hospital of Hefei Anhui Hefei230011 China Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education of China School of Computer Science and Information Engineering Anhui Hefei230002 China

Multi-label data streams such as Web texts and images have been popular on the Web. These data present the characteristics of multiple label, high dimensionality, high volume, high velocity and especial concept drift etc. Thus, multi-label data stream classification is a very challenging and significant task especially in the handling of high-dimensional data with concept drifts. However, this challenge has received little attention from the research community. Therefore, we propose the max-relevance and min-redundancy based algorithm adaptation approach for the efficient and effective classification on multi-label data streams with high-dimensional attributes and concept drifts. In order to reduce the impact from the high-dimensional data with noisy attributes, we first refine the minimal-redundancy-maximal-relevance criterion based on mutual information to select qualified features in multi-label data streams. Second, we propose the data distribution based concept drifting detection approach to distinguish concept drifts hidden in data streams. Finally, we build an incremental ensemble classification model for efficiently classifying multi-label data streams. Extensive studies show that our approach can get optimal subsets of features while maintaining a good performance in the multi-label classification, as compared to several state-of-the-art multi-label feature selection algorithms using two efficient multi-label classification methods as base classifiers. Meanwhile, our approach is superior to three well-known multi-label data stream classification approaches in the effectiveness and efficiency. © 1989-2012 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Partial Label Learning via Conditional-Label-Aware Disambiguation

引用

Journal of Computer Science & Technology 2021年第3期36卷 590-605页

作者： Peng Ni Su-Yun Zhao Zhi-Gang Dai Hong Chen Cui-Ping Li Key Laboratory of Data Engineering and Knowledge Engineering(Renmin University of China) Ministry of Education Beijing 100087China School of Information Renmin University of ChinaBeijing 100087China

Partial label learning is a weakly supervised learning framework in which each instance is associated with multiple candidate labels,among which only one is the ground-truth *** paper proposes a unified formulation that employs proper label constraints for training models while simultaneously performing *** existing partial label learning approaches that only leverage similarities in the feature space without utilizing label constraints,our pseudo-labeling process leverages similarities and differences in the feature space using the same candidate label constraints and then disambiguates noise *** experiments on artificial and real-world partial label datasets show that our approach significantly outperforms state-of-the-art counterparts on classification prediction.

关键词： disambiguation partial label learning similarity and dissimilarity weak supervision

来源：评论

学校读者我要写书评

暂无评论

Efficient Model Store and Reuse in an OLML database System

引用

Journal of Computer Science & Technology 2021年第4期36卷 792-805页

作者： Jian-Wei Cui Wei Lu Xin Zhao Xiao-Yong Du Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education Renmin University of China Beijing 100872China School of Information Renmin University of ChinaBeijing 100872China

Deep learning has shown significant improvements on various machine learning tasks by introducing a wide spectrum of neural network ***,for these neural network models,it is necessary to label a tremendous amount of training data,which is prohibitively expensive in *** this paper,we propose OnLine Machine Learning(OLML)database which stores trained models and reuses these models in a new training task to achieve a better training effect with a small amount of training *** efficient model reuse algorithm AdaReuse is developed in the OLML ***,AdaReuse firstly estimates the reuse potential of trained models from domain relatedness and model quality,through which a group of trained models with high reuse potential for the training task could be selected ***,multi selected models will be trained iteratively to encourage diverse models,with which a better training effect could be achieved by *** evaluate AdaReuse on two types of natural language processing(NLP)tasks,and the results show AdaReuse could improve the training effect significantly compared with models training from scratch when the training data is *** on AdaReuse,we implement an OLML database prototype system which could accept a training task as an SQL-like query and automatically generate a training plan by selecting and reusing trained *** studies are conducted to illustrate the OLML database could properly store the trained models,and reuse the trained models efficiently in new training tasks.

关键词： model selection model reuse OnLine Machine Learning(OLML)database

来源：评论

学校读者我要写书评

暂无评论

Task Offloading Optimization Based on Position Prediction in Pedestrian- Robot Mixed Traffic Flows 8

Task Offloading Optimization Based on Position Prediction in...

引用

8th IEEE International Conference on Computer and Communications, ICCC 2022

作者： Zheng, Dawen Wang, Lusheng Kai, Caihong Peng, Min Key Laboratory of Knowledge Engineering with Big Data Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology Hefei China

ISBN: (纸本)9781665450515

Service robots play an increasingly important role in people's daily life. The density of pedestrians is large and the movement is irregular in pedestrian-robot mixed traffic flows. Robots are prone to collision with pedestrians, and the tasks to be offloaded are closely related to pedestrians. How to analyze the tasks of robots and select the appropriate roadside unit is an important issue. In this paper, the social force model is used to predict the positions of pedestrians and robots, taking into account the influence of various forces to avoid collisions. A task offloading resource optimization algorithm with position prediction is proposed. According to the predicted information, the size and position distribution of all tasks in the scenario are obtained, and then the neural network trained beforehand based on deep Q-Iearning is used to generate a task offloading strategy. The simulation results show that the running time of the proposed algorithm is very short, and the resource allocation required for task offloading is completed in advance based on the predicted information before robots arriving the corresponding positions. Besides, the algorithm significantly reduces the task offloading delay. © 2022 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

CITE: Compact Interactive TransformEr for Multilingual Image Captioning 23

CITE: Compact Interactive TransformEr for Multilingual Image...

引用

6th International Conference on Image and Graphics Processing, ICIGP 2023

作者： Xu, Yueyuan Hu, Zhenzhen Zhou, Yuanen Hao, Shijie Hong, Richang Key Laboratory of Knowledge Engineering with Big Data School of Computer and Information Hefei University of Technology China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China

ISBN: (纸本)9781450398572

Current state-of-the-art image captioning models generate captions in a single language, requiring a combination of multiple language specific models to build a multilingual image captioning system. However, as the number of supported languages increases, it leads to the parameters of the multilingual image captioning system grow linearly. To tackle this issue, we propose a single Compact Interactive TransformEr (CITE) model, which can describe an image in multiple languages simultaneously, making the captioning system more compact. Specifically, based on the standard Transformer model, we share the encoder and decoder backbone parameters and replace the self-attention sub-layer in the decoder with the interactive attention sub-layer. In addition, we extend the traditional monolingual reinforcement learning mechanism to a multilingual version to promote better description generation. Due to the wide use of Chinese and English, we evaluate the performance of our CITE model by simultaneously generating English and Chinese captions. We expand the image captions of the whole MSCOCO dataset and release a COCO-EN-CN dataset. Extensive experiments on the COCO-EN-CN dataset show that our single CITE model with more parameter-efficient can maintain the competitive performance or even better than the monolingual captioning models. © 2023 ACM.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An Efficient Two-Round Distributed Transaction Processing Approach over Heterogeneous Networks

引用

The VLDB Journal 2025年第4期34卷 1-25页

作者： Zhao, Hongyao Lu, Wei Zhao, Zhanhao Hong, Yinhao Xu, Quanqing Xiao, Jinliang Han, Fusheng Yang, Chuanhui Du, Xiaoyong The Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education China and School of Information Renmin University of China Beijing China OceanBase Ant Group Beijing China

Countrywide and worldwide business, like gaming and social networks, drives the popularity of inter-data-center transactions. To support inter-data-center transaction processing and data center fault tolerance simultaneously, existing protocols suffer from significant performance degradation due to high-latency and unstable networks. In this paper, we propose RedT, a novel distributed transaction processing protocol that works in heterogeneous networks. In detail, nodes within a data center are inter-connected via the RDMA-capable network, and nodes across data centers are inter-connected via TCP/IP networks. RedT extends two-phase commit (2PC) by decomposing transactions into sub-transactions in terms of the data center granularity, and proposing a pre-write-log mechanism that is able to reduce the number of inter-data-center round-trips from a maximal of 6 to 2. Furthermore, RedT optimizes read-only transactions to commit with no inter-data-center communication. RedT supports supports both serializability and snapshot isolation. Extensive evaluation against state-of-the-art protocols shows that RedT can achieve up to $$1.80\times $$ higher throughputs and $$0.41\times $$ lower latency.

关键词： Concurrency control Distributed transaction Heterogeneous networks RDMA

来源：评论

学校读者我要写书评

暂无评论

A Low-Rank Matching Attention Based Cross-Modal Feature Fusion Method for Conversational Emotion Recognition

引用

IEEE Transactions on Affective Computing 2025年第2期16卷 1177-1189页

作者： Shou, Yuntao Liu, Huan Cao, Xiangyong Meng, Deyu Dong, Bo Xi’an Jiaotong University School of Computer Science and Technology Ministry of Education Key Laboratory for Intelligent Networks and Network Security Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Shaanxi Xi’an710049 China Xi’an Jiaotong University School of Computer Science and Technology Shaanxi Xi’an710049 China SHMEEA BigKE Joint Innovation Center Shanghai201318 China Xi’an Jiaotong University School of Mathematics and Statistics Shaanxi Xi’an710049 China

Conversational emotion recognition (CER) is an important research topic in human-computer interactions. Although recent advancements in transformer-based cross-modal fusion methods have shown promise in CER tasks, they tend to overlook the crucial intra-modal and inter-modal emotional interaction or suffer from high computational complexity. To address this, we introduce a novel and lightweight cross-modal feature fusion method called Low-Rank Matching Attention Method (LMAM). LMAM effectively captures contextual emotional semantic information in conversations while mitigating the quadratic complexity issue caused by the self-attention mechanism. Specifically, by setting a matching weight and calculating inter-modal features attention scores row by row, LMAM requires only one-third of the parameters of self-attention methods. We also employ the low-rank decomposition method on the weights to further reduce the number of parameters in LMAM. As a result, LMAM offers a lightweight model while avoiding overfitting problems caused by a large number of parameters. Moreover, LMAM is able to fully exploit the intra-modal emotional contextual information within each modality and integrates complementary emotional semantic information across modalities by computing and fusing similarities of intra-modal and inter-modal features simultaneously. Experimental results verify the superiority of LMAM compared with other popular cross-modal fusion methods on the premise of being more lightweight. Also, LMAM can be embedded into any existing state-of-the-art CER methods in a plug-and-play manner, and can be applied to other multi-modal recognition tasks, e.g., session recommendation and humour detection, demonstrating its remarkable generalization ability. © 2010-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An efficient and scalable graph database with built-in temporal support

引用

The VLDB Journal 2025年第4期34卷 1-25页

作者： Hou, Jiamin Zhao, Zhanhao Lu, Wei Yang, Shiming Liu, Shuang Xu, Quanqing Yang, Chuanhui Du, Xiaoyong Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education Beijing China School of Information Renmin University of China Beijing China OceanBase Ant Group Beijing China

Real-world graphs are often dynamic and evolve over time. It is crucial for storing and querying a graph’s evolution in graph databases. However, existing works either suffer from high storage overhead or lack efficient temporal query support, or both. In this paper, we propose $$\textsf {AeonG}$$ , a new graph database with built-in temporal support. Based on a novel temporal graph model, we build $$\textsf {AeonG}$$ with a hybrid storage engine and an efficient temporal query engine. The storage engine consists of current storage to manage the most recent versions of graph objects, and historical storage to manage previous versions. This separation minimizes the performance degradation when querying the most recent graph object versions. To reduce the historical storage overhead, we propose an anchor+delta strategy, in which we periodically create a complete version (namely anchor) of a graph object, and maintain every change (namely delta) between two adjacent anchors of the same object. In the query engine, we propose an anchor-based version retrieval technique to skip unnecessary historical version traversals to boost temporal query processing. Further, we extend $$\textsf {AeonG}$$ into a cloud-native database with disaggregated compute and storage layers, thus enabling elastic and scalable management of temporal graph data. Extensive experiments are conducted on both real and synthetic datasets. The results show that $$\textsf {AeonG}$$ achieves up to 5.73 $$\times $$ lower storage consumption and 2.57 $$\times $$ lower temporal query latency against state-of-the-art approaches, while introducing only 9.74% performance degradation for supporting temporal features.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RGB-D SLAM Method Based on Feature Association in Dynamic Environment 6

RGB-D SLAM Method Based on Feature Association in Dynamic En...

引用

6th Asian Conference on Artificial Intelligence Technology, ACAIT 2022

作者： Fang, Baofu Wang, Hao Wang, Hao Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology School of Computer Science and Information Engineering Hefei China

ISBN: (纸本)9781665453110

Simultaneous localization and mapping (SLAM) is one of the current research hotspots. However, in visual SLAM for dynamic environments, inaccurate detection of object motion states and incomplete dynamic region culling will lead to large localization errors. To address these issues, this paper proposes an RGB-D SLAM method based on feature association. The method has strongly correlated features in time and space according to the input image sequence. Using the moving probability of the feature points in the previous frame, the movement of the feature points in the current frame is calculated in combination with the dynamic corner points screened in the current frame. Then, the motion state of the object is determined according to the proportion of different feature points. Then combined with semantic information and object depth information, the fast search method is used to obtain accurate dynamic regions. Finally, the selected effective feature points are used to estimate the camera pose and establish a static map of the environment. This paper evaluates the robustness and accuracy of our method on the TUM dataset and real environment, and the results show that our method can significantly improve the system tracking effect and reduce the system tracking error compared with other SLAM methods in dynamic environments. © 2022 IEEE.

关键词： Semantics

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：