检索结果-内蒙古大学图书馆

Motion Stimulation for Compositional Action Recognition

ieee TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2023年第5期33卷 2061-2074页

作者： Ma, Lei Zheng, Yuhui Zhang, Zhao Yao, Yazhou Fan, Xijian Ye, Qiaolin Nanjing Forestry Univ Coll Informat Sci & Technol Nanjing 210037 Peoples R China Nanjing Univ Informat Sci & Technol Jiangsu Engn Ctr Network Monitoring Sch Comp & Software Nanjing 210044 Peoples R China Hefei Univ Technol Key Lab Knowledge Engn Big Data Hefei 230009 Peoples R China Hefei Univ Technol Intelligent Interconnected Syst Lab Anhui Prov Minist Educ Hefei 230009 Peoples R China Nanjing Univ Sci & Technol Coll Comp Sci & Technol Nanjing 210094 Peoples R China Nanjing Xiaozhuang Univ Key Lab Intelligent Informat Proc Nanjing 211171 Peoples R China

Recognizing the unseen combinations of action and different objects, namely (zero-shot) compositional action recognition, is extremely challenging for conventional action recognition algorithms in real-world applications. Previous methods focus on enhancing the dynamic clues of objects that appear in the scene by building region features or tracklet embedding from ground-truths or detected bounding boxes. These methods rely heavily on manual annotation or the quality of detectors, which are inflexible for practical applications. In this work, we aim to mining the temporal clues from moving objects or hands without explicit supervision. Thus, we propose a novel Motion Stimulation (MS) block, which is specifically designed to mine dynamic clues of the local regions autonomously from adjacent frames. Furthermore, MS consists of the following three steps: motion feature extraction, motion feature recalibration, and action-centric excitation. The proposed MS block can be directly and conveniently integrated into existing video backbones to enhance the ability of compositional generalization for action recognition algorithms. Extensive experimental results on three action recognition datasets, the Something-Else, IKEA-Assembly and EPIC-KITCHENS datasets, indicate the effectiveness and interpretability of our MS block.

关键词： Feature extraction Cognition Computational modeling visualization Task analysis Dynamics Detectors Motion stimulation compositional action recognition motion feature extraction motion feature recalibration action-centric excitation

来源：评论

学校读者我要写书评

暂无评论

Large-scale 3D Mesh data Semantic Segmentation: A Survey 9

Large-scale 3D Mesh Data Semantic Segmentation: A Survey

引用

9th International Conference on Big data and Information Analytics, BigDIA 2023

作者： Gao, Lin Liu, Yu Liu, YuXiang Cheng, XiaoYa Zhu, JueLin Wang, JingYi University of Defense Technology College of Systems Engineering ChangSha China

ISBN: (纸本)9798350330076

Utilizing 3D mesh data presents myriad advantages for representing actual environments, encompassing the capability to exhibit geometric information and high-quality textures. Within the domain of geographical information systems, there exists a substantial need for 3D data to precisely depict extensive remote sensing scenes. Meshes are commonly employed for representing geographical terrains, structures, and urban models. Effective visualization and representation of meshes are imperative for managing expansive geographical datasets. The procedure of 3D mesh semantic segmentation entails assigning distinct semantic labels to each triangle, thus dividing the entire scene into various categories. Nevertheless, owing to the irregular structure of 3D mesh data, the progress in developing pertinent semantic segmentation techniques is still in its nascent stages. Many conventional methods rely on multi-view approaches. Given the growing popularity of deep learning for segmenting remote sensing data, end-to-end 3D mesh semantic segmentation techniques have become a focal point of current research. This article firstly introduces existing 3D mesh datasets and classifies them based on scale and application, as these datasets serve as the groundwork for algorithmic research. Subsequently, existing 3D mesh semantic segmentation techniques are presented, categorized into traditional methods and deep learning methods. Lastly, the challenges confronted by 3D mesh semantic segmentation at present are deliberated. © 2023 ieee.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Triplet Graph Attention Network for EEG-Based Cross-Subject Emotion Recognition 7

Triplet Graph Attention Network for EEG-Based Cross-Subject ...

引用

7th Asian Conference on Artificial Intelligence Technology, ACAIT 2023

作者： Zhu, Ting Zheng, Chuhang Zhou, Yueying Wang, Pengpai Zhu, Qi Nanjing University of Aeronautics And Astronautics College of Computer Science And Technology Nanjing China

ISBN: (纸本)9798350359145

As the correlation between emotion and brain activities has been gradually investigated, it is promising to objectively model the brain mechanism of human emotion with EEG in medical applications, such as the diagnosis of dysthymic disorder and brain disease. However, the huge individual variation of EEG may lead to the failure of recognition, and most existing studies cannot effectively exploit the complex topological information between channels. In this paper, a triplet graph attention network jointly trained from both local and global features is proposed to address the above problems. Specifically, we preliminarily explore topological connectivity by fusing both physical connections and functional connections between electrodes. To alleviate the effects of subject variation and capture the most essential emotional neural patterns, we design a mechanism that can dynamically select samples to form triplets to improve the class discriminability and weaken the subject discriminability in the high-order feature space. In addition, our model can obtain rich node features and effective graph features at the local and global levels, respectively, to capture emotion-related neural patterns. The experimental results on the SEED dataset show the effectiveness of our method in EEG-based cross-subject emotion recognition, and the visualization of the data distribution significantly illustrates that our model can enhance the discriminability of the emotion class. © 2023 ieee.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

An Approach to Generate a Caption for an Image Collection Using Scene Graph Generation

引用

ieee ACCESS 2023年 11卷 128245-128260页

作者： Phueaksri, Itthisak Kastner, Marc A. Kawanishi, Yasutomo Komamizu, Takahiro Ide, Ichiro Nagoya Univ Grad Sch Informat Nagoya Aichi 4648601 Japan RIKEN Guardian Robot Project Informat Res & Dev & Strategy Headquarters Seika Kyoto 6190288 Japan Kyoto Univ Grad Sch Informat Kyoto 6068501 Japan Nagoya Univ Math & Data Sci Ctr Nagoya Aichi 4648601 Japan

Summarization is a challenging task that aims to generate a summary by grasping common information of a given set of information. Text summarization is a popular task of determining the topic or generating a textual summary of documents. In contrast, image summarization aims to find a representative summary of a collection of images. However, current methods are still restricted to generating a visual scene graph, tags, and noun phrases, but cannot generate a fitting textual description of an image collection. Thus, we introduce a novel framework for generating a summarized caption of an image collection. Since scene graph generation shows advancement in describing objects and their relationships on a single image, we use it in the proposed method to generate a scene graph for each image in an image collection. Then, we find common objects and their relationships from all scene graphs and represent them as a summarized scene graph. For this, we merge all scene graphs and select part of it by estimating the most common objects and relationships. Finally, the summarized scene graph is input into a captioning model. In addition, we introduce a technique to generalize specific words in the final caption into common concept words incorporating external knowledge. To evaluate the proposed method, we construct a dataset for this task by extending the annotation of the MS-COCO dataset using an image retrieval method. The evaluation of the proposed method on this dataset showed promising performance compared to text summarization-based methods.

关键词： Task analysis visualization Semantics Image edge detection Image capture Image analysis Information retrieval Image collection captioning multiple image summarization semantic summarization scene-graph summarization

来源：评论

学校读者我要写书评

暂无评论

Constructing a Knowledge Graph for the database Course Group via Deep Learning 13

Constructing a Knowledge Graph for the Database Course Group...

引用

13th International Conference on Educational and Information Technology, ICEIT 2024

作者： Zou, Xianxia Lin, Haodong Wu, JingPing Zheng, Cenyu Guan, Quanlong Jinan University Dept. of Computer Science Guangzhou China Wuhan Dameng Database Co. Ltd. Wuhan China Jinan University Guangdong Institute of Smart Education Guangzhou China

ISBN: (纸本)9798350372663

Elevating proactive and innovative learning abilities in students is crucial for modern education. Our research develops an adaptive learning system., a key tool for delivering customized educational experiences. Focusing on database course groups., we leverage specific deep learning models and advanced natural language processing techniques. We have constructed a multimodal educational knowledge graph., integrating data from authoritative textbooks and Chinese University MOOC Resources. This graph significantly enhances data storage., visualization., and querying capabilities., thereby facilitating the digital transformation of traditional textbooks. Our approach showcases not only improved efficiency and precision but also provides robust knowledge support for adaptive learning platforms., thereby advancing tailored educational recommendations significantly. © 2024 ieee.

关键词： Query processing

来源：评论

学校读者我要写书评

暂无评论

TransFusionOdom: Transformer-Based LiDAR-Inertial Fusion Odometry Estimation

引用

ieee SENSORS JOURNAL 2023年第18期23卷 22064-22079页

作者： Sun, Leyuan Ding, Guanqun Qiu, Yue Yoshiyasu, Yusuke Kanehiro, Fumio Natl Inst Adv Ind Sci & Technol CNRS AIST Joint Robot Lab JRL IRL Tsukuba 3058560 Japan Natl Inst Adv Ind Sci & Technol Comp Vis Res Team Artificial Intelligence Res Ctr AIRC Tsukuba 3058560 Japan Natl Inst Adv Ind Sci & Technol Digital Architecture Res Ctr DigiARC Tokyo 1350064 Japan Univ Tsukuba Grad Sch Sci & Technol Dept Intelligent & Mech Interact Syst Tsukuba 3050006 Japan

Multimodal fusion of sensors is a commonly used approach to enhance the performance of odometry estimation, which is also a fundamental module for mobile robots. Recently, learning-based approaches garner the attention in this field, due to their robust nonhandcrafted designs. However, the question of How to perform fusion among different modalities in a supervised sensor fusion odometry estimation task? is one of the challenging issues still remaining. Some simple operations, such as elementwise summation and concatenation, are not capable of assigning adaptive attentional weights to incorporate different modalities efficiently, which makes it difficult to achieve competitive odometry results. Besides, the Transformer architecture has shown potential for multimodal fusion tasks, particularly in the domains of vision with language. In this work, we propose an end-to-end supervised Transformer-based LiDAR-Inertial fusion framework (namely TransFusionOdom) for odometry estimation. The multiattention fusion module demonstrates different fusion approaches for homogeneous and heterogeneous modalities to address the overfitting problem that can arise from blindly increasing the complexity of the model. Additionally, to interpret the learning process of the Transformer-based multimodal interactions, a general visualization approach is introduced to illustrate the interactions between modalities. Moreover, exhaustive ablation studies evaluate different multimodal fusion strategies to verify the performance of the proposed fusion strategy. A synthetic multimodal dataset is made public to validate the generalization ability of the proposed fusion strategy, which also works for other combinations of different modalities. The quantitative and qualitative odometry evaluations on the KITTI dataset verify that the proposed TransFusionOdom can achieve superior performance compared with other learning-based related works.

关键词： Attention mechanisms LiDAR-inertial odometry (LIO) multimodal learning sensor data fusion transformer

来源：评论

学校读者我要写书评

暂无评论

Sketch2PQ: Freeform Planar Quadrilateral Mesh Design via a Single Sketch

引用

ieee TRANSACTIONS ON visualization AND COMPUTER GRAPHICS 2023年第9期29卷 3826-3839页

作者： Deng, Zhi Liu, Yang Pan, Hao Jabi, Wassim Zhang, Juyong Deng, Bailin Univ Sci & Technol China Sch Data Sci Hefei 230026 Peoples R China Microsoft Res Asia Internet Graph Grp Beijing 100080 Peoples R China Cardiff Univ Welsh Sch Architecture Cardiff CF24 3AA Wales Univ Sci & Technol China Sch Math Sci Hefei 230026 Peoples R China Cardiff Univ Sch Comp Sci & Informat Cardiff CF24 3AA Wales

The freeform architectural modeling process often involves two important stages: concept design and digital modeling. In the first stage, architects usually sketch the overall 3D shape and the panel layout on a physical or digital paper briefly. In the second stage, a digital 3D model is created using the sketch as a reference. The digital model needs to incorporate geometric requirements for its components, such as the planarity of panels due to consideration of construction costs, which can make the modeling process more challenging. In this work, we present a novel sketch-based system to bridge the concept design and digital modeling of freeform roof-like shapes represented as planar quadrilateral (PQ) meshes. Our system allows the user to sketch the surface boundary and contour lines under axonometric projection and supports the sketching of occluded regions. In addition, the user can sketch feature lines to provide directional guidance to the PQ mesh layout. Given the 2D sketch input, we propose a deep neural network to infer in real-time the underlying surface shape along with a dense conjugate direction field, both of which are used to extract the final PQ mesh. To train and validate our network, we generate a large synthetic dataset that mimics architect sketching of freeform quadrilateral patches. The effectiveness and usability of our system are demonstrated with quantitative and qualitative evaluation as well as user studies.

关键词： Freeform surface architectural geometry planar quadrilateral mesh sketch-based modeling deep learning

来源：评论

学校读者我要写书评

暂无评论

Artificial Neural Network Based Audio Reinforcement for Computer Assisted Rote Learning

引用

ieee ACCESS 2023年 11卷 39466-39483页

作者： Supitayakul, Parisa Yucel, Zeynep Monden, Akito Okayama Univ Grad Sch Nat Sci & Technol Okayama 7008530 Japan

The dual-channel assumption of the cognitive theory of multimedia learning suggests that importing a large amount of information through a single (visual or audio) channel overloads that channel, causing partial loss of information, while importing it simultaneously through multiple channels relieves the burden on them and leads to the registration of a larger amount of information. In light of such knowledge, this study investigates the possibility of reinforcing visual stimuli with audio for supporting e-learners in memorization tasks. Specifically, we consider three kinds of learning material and two kinds of audio stimuli and partially reinforce each kind of material with each kind of stimuli in an arbitrary way. In a series of experiments, we determine the particular type of audio, which offers the highest improvement for each kind of material. Our work stands out as being the first study investigating the differences in memory performance in relation to different combinations of learning content and stimulus. Our key findings from the experiments are: (i) E-learning is more effective in refreshing memory rather than studying from scratch, (ii) Non-informative audio is more suited to verbal content, whereas informative audio is better for numerical content, (iii) Constant audio triggering degrades learning performance and thus audio triggering should be handled with care. Based on these findings, we develop an ANN-based estimator to determine the proper moment for triggering audio (i.e. when memory performance is estimated to be declining) and carry out follow-up experiments for testing the integrated framework. Our contributions involve (i) determination of the most effective audio for each content type, (ii) estimation of memory deterioration based on learners' interaction logs, and (iii) the proposal of improvement of memory registration through auditory reinforcement. We believe that such findings constitute encouraging evidence the memory registration of e

关键词： visualization Electronic learning Task analysis Estimation Vocabulary Memory management Learning (artificial intelligence) E-learning neural networks artificial intelligence cognitive theory of multimedia learning cognitive load distinctiveness account perceptual decoupling adaptability educational data mining

来源：评论

学校读者我要写书评

暂无评论

2023 11th International Conference on Smart Grid and Clean Energy Technologies, ICSGCE 2023

2023 11th International Conference on Smart Grid and Clean E...

引用

11th International Conference on Smart Grid and Clean Energy Technologies, ICSGCE 2023

ISBN: (纸本)9798350305364

The proceedings contain 14 papers. The topics discussed include: stacking of 3D-printed plant-microbial fuel cells with green chili (capsicum annuum);smart grid integration of hybrid multi-source power systems in Lebanon’s renewable energy technologies landscape;framework and clustering dashboard for analyzing temporal-based parameters of solar PV output model;stochastic planning of solar PV/wind turbine/micro-hydro/biomass microgrids integrating fuel cell electric vehicles;modeling and design of floating solar PV systems for buildings;towards an approach for household energy monitoring and visualization to enable sustainable peer-to-peer energy trading;grid voltage adaptive feed-forward control strategy in weak grid;short-term load forecasting for peak demand reduction with limited historical data;and systematic charging scheduling of electric taxis based on active partial travel methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Radar Heatmap Generation for Advanced Driver Assistance Systems 5

Machine Learning based Radar Heatmap Generation for Advanced...

引用

5th International Conference on High Performance Big data and Intelligent Systems, HDIS 2023

作者： Klassen, Angela Karakuş, Erkan Yang, Qing Dept. of Electrical Computer and Biomedical Engineering University of Rhode Island KingstonRI02881 United States

ISBN: (纸本)9798350394160

Radar sensors are commonly used in Advanced Driver Assistance Systems (ADAS) to detect surrounding objects. Radar signals pass a signal processing chain to compute the range, the velocity and the angular position of potential obstacles and other traffic participants. Major challenges of this procedure are the high complexity and latency of transferring a large amount of raw radar data to subsequent processing units. This paper presents a machine learning model that dramatically reduces the latency of the data transfer by compression of the raw radar data and that generates Range-Angle (RA) Heatmaps directly from the compressed data. RA Heatmaps present the essential visualization technique for the localization of surrounding objects in the radar horizon. In addition, they can be used to detect and identify objects. We use the autoencoder and the U-Net architecture for the compression and the RA Heatmap generation respectively. For the collection of raw radar data, a Texas Instruments (TI) AWR1243 FMCW radar sensor board is utilized. The data to train the U-Net architecture is obtained by applying analytical radar imaging algorithms including a 3-dimensional Fast Fourier Transform (3D FFT) and our proposed framework for Region of Interest (ROI) extraction on the collected data. Experimental results indicate that our final system can achieve a significant reduction of the original raw radar data while still maintaining all relevant features required for object recognition tasks. Excellent accuracy scores exceeding 99 % on input data that has been compressed by a factor of four validate the capabilities of the model and underline its potential for radar data processing in the context of ADAS. ©2023 ieee.

关键词： data transfer

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：