检索结果-内蒙古大学图书馆

16th European Conference on computer Vision, ECCV 2020

作者： Yang, Siyuan Liu, Jun Lu, Shijian Er, Meng Hwa Kot, Alex C. Lab Interdisciplinary Graduate Programme Nanyang Technological University Singapore Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore Singapore School of Computer Science and Engineering Nanyang Technological University Singapore Singapore

ISBN: (纸本)9783030585792

Gesture recognition and 3D hand pose estimation are two highly correlated tasks, yet they are often handled separately. In this paper, we present a novel collaborative learning network for joint gesture recognition and 3D hand pose estimation. The proposed network exploits joint-aware features that are crucial for both tasks, with which gesture recognition and 3D hand pose estimation boost each other to learn highly discriminative features. In addition, a novel multi-order multi-stream feature analysis method is introduced which learns posture and multi-order motion information from the intermediate feature maps of videos effectively and efficiently. Due to the exploitation of joint-aware features in common, the proposed technique is capable of learning gesture recognition and 3D hand pose estimation even when only gesture or pose labels are available, and this enables weakly supervised network learning with much reduced data labeling efforts. Extensive experiments show that our proposed method achieves superior gesture recognition and 3D hand pose estimation performance as compared with the state-of-the-art. © 2020, Springer Nature Switzerland AG.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Candidate Eclipsing Binary Systems with a δ Scuti Star in Northern TESS Field

引用

Research in Astronomy and Astrophysics 2022年第8期 36-50页

作者： F.Kahraman Ali?avu? D.Gümü? ?.K?rm?z?ta? ?.Ekinci S.?avu? Y.T.Kaya F.Ali?avu? ?anakkale Onsekiz Mart University Faculty of Sciences and Arts Physics Department ?anakkale Onsekiz Mart University Astrophysics Research Center and Ulupnar Observatory Istanbul University Institute of Graduate Studies in Science Programme of Astronomy and Space Sciences ?anakkale Onsekiz Mart University School of Graduate Studies Department of Physics ?anakkale Onsekiz Mart University School of Graduate Studies Department of Space Sciences and Technologies ?anakkale Onsekiz Mart University Faculty of Engineering Computer Engineering

The existence of pulsating stars in eclipsing binaries has been known for decades. These types of objects are extremely valuable systems for astronomical studies as they exhibit both eclipse and pulsation variations. The eclipsing binaries are the only way to directly measure the mass and radius of stars with a good accuracy（≤1%）,while the pulsations are a unique way to probe the stellar interior via oscillation frequencies. There are different types of pulsating stars existing in eclipsing binaries. One of them is the δ Scuti variables. Currently, the known number of δ Scuti stars in eclipsing binaries is around 90 according to the latest catalog of these variables. An increasing number of these kinds of variables is important to understand the stellar structure, evolution and the effect of binarity on the pulsations. Therefore, in this study, we focus on discovering new eclipsing binaries with δ Scuti component（s）. We searched within the northern Transiting Exoplanet Survey Satellite（TESS） field with a visual inspection by following some criteria such as light curve shape, the existence of pulsation like variations in the out-of-eclipse light curve and the Teffvalues of the targets. As a result of these criteria, we discovered some targets. The orbital variations were first removed from the TESS light curves and frequency analysis was performed on the residuals. The luminosity, and absolute and bolometric magnitudes of the targets were calculated as well. To find how much of these parameters represent the primary（more luminous） binary component, we also computed the flux density ratio of the systems by utilizing the area of the eclipses. In addition, the positions of the systems in the H-R diagram were examined considering the flux density ratios. As a consequence of the investigation, we defined 38 candidate δ Scuti stars and also one Maia variable in eclipsing binary systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model Predictive Control of Five-Level Current Source Converter with Optimized Weighting Factors 3

Model Predictive Control of Five-Level Current Source Conver...

引用

3rd IEEE International Conference on Industrial Electronics for Sustainable Energy Systems, IESES 2023

作者： Chen, Muyu Yuan, Zhige Faraji, Faramarz Ghias, Amer M. Y. M. Cha, Honnyong Nicholas, Vun Chan Hua School of Electrical and Electronic Engineering Nanyang Technological University Collab. Initiative Interdisciplinary Graduate Programme Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore School of Energy Engineering Kyungpook National University Daegu Korea Republic of School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (纸本)9798350324754

This paper presents the finite control set model predictive control (FCS-MPC) with improved control objectives using optimized weighting factors. The Pareto curve obtained from the Particle Swarm optimizes the weighting factors. The optimal weighting factors are then used in the FCS-MPC algorithm to enhance the control objective performance of a three-phase five-level current source converter (5L-CSC). In 5L-CSC, two identical three-level CSC (3L-CSC) modules are connected in parallel with one common current source supply to provide uniform five-level output current waveform. This CSC requires a current balance to operate the converter safely. Therefore, the control objective of the MPC is to control the output voltage and balance the internal currents. The weighting factors are optimized based on the converter's total harmonics distortion (THD) performance and inductor current ripple. The performance enhancement of 5L-CSC, utilizing optimal weighting factors, is confirmed through MATLAB simulations when compared to the model employing arbitrarily assigned weighting factors. The simulation outcomes additionally indicate that the integration of Particle Swarm Optimization (PSO) with FCS-MPC exhibits resilience across various condition settings. © 2023 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection of 2D Human Postures Based on Single Images

Automatic Detection of 2D Human Postures Based on Single Ima...

引用

Brazilian Symposium on computer Graphics and Image Processing (SIBGRAPI)

作者： Humberto Souto Soraia Musse Graduate Programme in Computer Science Virtual Human Laboratory Pontifícia Universidade Católica do Rio Grande do Sul Porto Alegre Brazil

Estimating human pose in static images is a challenging task due to the high dimensional state space, presence of image clutter and ambiguities of image observations. In this paper we propose a method to automatically detect human poses in a single image, based on a 2D model combined with anthropometric data. Furthermore, we use artificial neural networks to detect high level information about the human posture. Experimental results showed that the proposed technique performs well in non trivial images.

关键词： Humans Image segmentation Training Joints Legged locomotion Face Skin

来源：评论

学校读者我要写书评

暂无评论

Eyes and Eyebrows Detection for Performance Driven Animation

Eyes and Eyebrows Detection for Performance Driven Animation

引用

Brazilian Symposium on computer Graphics and Image Processing (SIBGRAPI)

作者： Juliano L. Moreira Adriana Braun Soraia R. Musse Virtual Human Laboratory Graduate Programme in Computer Science Pontifícia Universidade Católica do Rio Grande do Sul Porto Alegre Brazil

Real-time localization of eyes and eyebrows in video sequences can find several applications in nowadays. However, this task is still a challenge, mainly if we consider images of low quality as those achieved by web cams. This paper describes a methodology to accurately detect meaningful feature points in eyes and eyebrows of people in frontal pose, in images captured by web cams. Also it discusses the mapping of the movement of the eyes of a real person to an avatar, in order to provide Performance Driven Animation (PDA). Furthermore, this paper presents obtained results and the limitations of the proposed methodology.

关键词： Eyebrows Face Pixel Feature extraction Facial animation Avatars

来源：评论

学校读者我要写书评

暂无评论

Reflecting user faces in avatars

Reflecting user faces in avatars

引用

10th International Conference on Intelligent Virtual Agents, IVA 2010

作者： Baptista Queiroz, Rossana Braun, Adriana Moreira, Juliano Lucas Cohen, Marcelo Musse, Soraia Raupp Thielo, Marcelo Resende Samadani, Ramin Graduate Programme in Computer Science PUCRS 6681 - Building 32 Av. Ipiranga Porto Alegre/RS Brazil Hewlett Packard Brazil 6681 Building 95c Av. Ipiranga Porto Alegre/RS Brazil Hewlett Packard Laboratories Page Mill Rd. Palo Alto CA 1501 United States

ISBN: (纸本)3642158919

This paper presents a model to generate personalized facial animations for avatars using Performance Driven Animation (PDA). This approach allows the users to reflect their face expressions in his/her avatar, considering as input a small set of feature points provided by computer Vision (CV) tracking algorithms. The model is based on the MPEG-4 Facial Animation standard, and uses a hierarchy of the animation parameters to provide animation of face regions where it lacks CV data. To deform the face, we use two skin mesh deformation methods, which are computationally cheap and provide avatar animation in real time. We performed an evaluation with subjects in order to qualitatively evaluate our method. Results show that the proposed model can generate coherent and visually satisfactory animations. © 2010 Springer-Verlag Berlin Heidelberg.

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

Analyzing Properties of Fuzzy Implications Obtained via the Interval Constructor

Analyzing Properties of Fuzzy Implications Obtained via the ...

引用

International Symposium on Scientific Computing, computer Arithmetic and Validated Numerics (SCAN)

作者： B.C. Bedregal R.H.N. Santiago R.H.S. Reiser G.P. Dimuro Department of Informatics and Applied Mathematics Federal University of Rio Grande do Norte Natal Brazil Pos-Graduate Programme in Computer Science Catholic University of Pelotas Pelotas Brazil

ISBN: (纸本)9781424431410

This work considers an interval extension of fuzzy implications based on the best interval representation of usual fuzzy implications. The related properties of fuzzy implications can be naturally extended and the interval representation meets the optimality property and preserves the behaviors of the implications in the interval endpoints. Our discussion mainly focuses on the best interval representation of three important classes of fuzzy implications: S-implications, R-implications and QL-implications. We analyze sufficient and necessary conditions for these three classes of implications as inclusion-monotonic functions in both arguments satisfying the minimal properties of fuzzy implications.

关键词： Mathematics Fuzzy logic Fuzzy control Informatics computer science Natural languages Multivalued logic Fuzzy sets Uncertainty

来源：评论

学校读者我要写书评

暂无评论

Codec Data Augmentation for Time-Domain Heart Sound Classification

Codec Data Augmentation for Time-Domain Heart Sound Classifi...

引用

International Conference of Advanced Informatics: Concept, Theory and Application (ICAICTA)

作者： Ansh Mishra Jia Qi Yip Eng Siong Chng Department of Physics IIT Delhi New Delhi India Interdisciplinary Graduate Programme Nanyang Technological University (NTU) Singapore School of Computer Science and Engineering Nanyang Technological University (NTU) Singapore

Heart auscultations are a low-cost and effective way of detecting valvular heart diseases early, which can save lives. Nevertheless, it has been difficult to scale this screening method since the effectiveness of auscultations is dependent on the skill of doctors. As such, there has been increasing research interest in the automatic classification of heart sounds using deep learning algorithms. However, it is currently difficult to develop good heart sound classification models due to the limited data available for training. In this work, we propose a simple time domain approach, to the heart sound classification problem with a base classification error rate of 0.8 and show that augmentation of the data through codec simulation can improve the classification error rate to 0.2. With data augmentation, our approach outperforms the existing time-domain CNN-BiLSTM baseline model. Critically, our experiments show that codec data augmentation is effective in getting around the data limitation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Audio-Visual Deception Detection: DOLOS Dataset and Parameter-Efficient Crossmodal Learning

arXiv

引用

arXiv 2023年

作者： Guo, Xiaobao Selvaraj, Nithish Muthuchamy Yu, Zitong Kong, Adams Wai-Kin Shen, Bingquan Kot, Alex Lab Interdisciplinary Graduate Programme Nanyang Technological University Singapore School of Computer Science and Engineering NTU Singapore School of Electrical & Electronic Engineering NTU Singapore DSO National Laboratories Singapore

Deception detection in conversations is a challenging yet important task, having pivotal applications in many fields such as credibility assessment in business, multimedia anti-frauds, and custom security. Despite this, deception detection research is hindered by the lack of high-quality deception datasets, as well as the difficulties of learning multimodal features effectively. To address this issue, we introduce DOLOS1, the largest gameshow deception detection dataset with rich deceptive conversations. DOLOS includes 1,675 video clips featuring 213 subjects, and it has been labeled with audio-visual feature annotations. We provide train-test, duration, and gender protocols to investigate the impact of different factors. We benchmark our dataset on previously proposed deception detection approaches. To further improve the performance by fine-tuning fewer parameters, we propose Parameter-Efficient Crossmodal Learning (PECL), where a Uniform Temporal Adapter (UT-Adapter) explores temporal attention in transformer-based architectures, and a crossmodal fusion module, Plug-in Audio-Visual Fusion (PAVF), combines crossmodal information from audio-visual features. Based on the rich fine-grained audio-visual annotations on DOLOS, we also exploit multi-task learning to enhance performance by concurrently predicting deception and audiovisual features. Experimental results demonstrate the desired quality of the DOLOS dataset and the effectiveness of the PECL. The DOLOS dataset and the source codes are available at here. © 2023, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PnP-DETR: Towards Efficient Visual Analysis with Transformers

arXiv

引用

arXiv 2021年

作者： Wang, Tao Yuan, Li Chen, Yunpeng Feng, Jiashi Yan, Shuicheng Institute of Data Science National University of Singapore Singapore Yitu Technology Integrative Science and Engineering Programme NUS Graduate School National University of Singapore Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore

Recently, DETR [3] pioneered the solution of vision tasks with transformers, it directly translates the image feature map into the object detection result. Though effective, translating the full feature map can be costly due to redundant computation on some area like the background. In this work, we encapsulate the idea of reducing spatial redundancy into a novel poll and pool (PnP) sampling module, with which we build an end-to-end PnP-DETR architecture that adaptively allocates its computation spatially to be more efficient. Concretely, the PnP module abstracts the image feature map into fine foreground object feature vectors and a small number of coarse background contextual feature vectors. The transformer models information interaction within the fine-coarse feature space and translates the features into the detection result. Moreover, the PnP-augmented model can instantly achieve various desired trade-offs between performance and computation with a single model by varying the sampled feature length, without requiring to train multiple models as existing methods. Thus it offers greater flexibility for deployment in diverse scenarios with varying computation constraint. We further validate the generalizability of the PnP module on panoptic segmentation and the recent transformer-based image recognition model ViT [7] and show consistent efficiency gain. We believe our method makes a step for efficient visual analysis with transformers, wherein spatial redundancy is commonly observed. Code will be available at https://***/twangnh/pnp-detr. Copyright © 2021, The Authors. All rights reserved.

关键词： Feature extraction

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：