检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Jiang, Changlong Xiao, Yang Wu, Cunlin Zhang, Mingyang Zheng, Jinghong Cao, Zhiguo Zhou, Joey Tianyi Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Alibaba Group China Singapore Singapore

3D interacting hand pose estimation from a single RGB image is a challenging task, due to serious self-occlusion and inter-occlusion towards hands, confusing similar appearance patterns between 2 hands, ill-posed joint position mapping from 2D to 3D, etc.. To address these, we propose to extend A2J-the state-of-the-art depth-based 3D single hand pose estimation method-to RGB domain under interacting hand condition. Our key idea is to equip A2J with strong local-global aware ability to well capture interacting hands’ local fine details and global articulated clues among joints jointly. To this end, A2J is evolved under Transformer’s non-local encoding-decoding framework to build A2J-Transformer. It holds 3 main advantages over A2J. First, self-attention across local anchor points is built to make them global spatial context aware to better capture joints’ articulation clues for resisting occlusion. Secondly, each anchor point is regarded as learnable query with adaptive feature learning for facilitating pattern fitting capacity, instead of having the same local representation with the others. Last but not least, anchor point locates in 3D space instead of 2D as in A2J, to leverage 3D pose prediction. Experiments on challenging InterHand 2.6M demonstrate that, A2J-Transformer can achieve state-of-the-art model-free performance (3.38mm MPJPE advancement in 2-hand case) and can also be applied to depth domain with strong generalization. The code is avaliable at https://***/ChanglongJiangGit/A2J-Transformer. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Context Modeling for Road Obstacle Detection 1

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Wu, Xiuen Wang, Tao Liang, Lingyu Li, Zuoyong Ching, Fum Yew College of Computer and Data Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350108 China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University Wuyishan354300 China School of Electronic and Information Engineering South China University of Technology Guangzhou510641 China Ministry of Education Key Laboratory of Computer Network and Information Integration Southeast University Nanjing211189 China Guangzhou510320 China Penang11800 Malaysia

ISBN: (数字)9783031200960

ISBN: (纸本)9783031200953

Road obstacle detection is an important problem for vehicle driving safety. In this paper, we aim to obtain robust road obstacle detection based on spatio-temporal context modeling. Firstly, a data-driven spatial context model of the driving scene is constructed with the layouts of the training data. Then, obstacles in the input image are detected via the state-of-the-art object detection algorithms, and the results are combined with the generated scene layout. In addition, to further improve the performance and robustness, temporal information in the image sequence is taken into consideration, and the optical flow is obtained in the vicinity of the detected objects to track the obstacles across neighboring frames. Qualitative and quantitative experiments were conducted on the Small Obstacle Detection (SOD) dataset and the Lost and Found dataset. The results indicate that our method with spatio-temporal context modeling is superior to existing methods for road obstacle detection. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Optimal Power and Gas Flow of Energy Internet with Non-Isothermal Process and Energy Storage

Optimal Power and Gas Flow of Energy Internet with Non-Isoth...

引用

第43届中国控制会议

作者： Chen Liu Shiyuan He Xinyi Wang Xiao-Kang Liu School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of lmage Processing and Intelligent Control (Huazhong University of Science and Technology) Ministry of Education

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The electrical-gas coupled power flow problem is one of the most basic problems under Energy Internet. In order to achieve a more complete analysis of the electric-gas coupled power flow, this paper establishes a novel integrated energy system model that considers electricity and natural gas. This model integrates the power system AC power flow model and the non-isothermal process of natural gas pipeline transmission, achieving a more accurate description of the power grid and gas network power flow. At the same time, the beneficial effects of energy storage units on the network of each part of the system are analyzed. Through simulation design, the benefits of energy storage access on system cost and security are analyzed and quantified.

关键词： Electrical-gas coupled power flow Energy Internet AC power flow non-isothermal process energy storage

来源：评论

学校读者我要写书评

暂无评论

Traffic Pricing Based on Network Congestion Games with Player and Resource Failures

Traffic Pricing Based on Network Congestion Games with Playe...

引用

第43届中国控制会议

作者： Shuqi Liu Jinhuan Wang Lin Wang Institute of Mathematics School of ScienceHebei University of Technology Department of Automation Shanghai Jiaotong Universityand the Key Laboratory of System Control and Information ProcessingMinistry of Education

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

This paper investigates the pricing problem of transportation based on a framework of network congestion game with both player and resource ***,the traffic pricing problem is modeled as a network congestion game by redefining the player's cost function in the event of player and resource ***,by using the method of semi-tensor product of matrices,the game with player and resource failures is algebraized and verified to be a weighted potential *** weighted potential function is also ***,the impact of player and resource failures on Nash equilibria(NEs) is studied,and the condition on keeping the NE of the original game unchanged is ***,the theoretical results are verified by numerical examples.

关键词： Semi-tensor product network congestion game player and resource failures

来源：评论

学校读者我要写书评

暂无评论

Multiple kernel subspace clustering with dual tensors learning

引用

Applied Intelligence 2025年第11期55卷 1-11页

作者： Liao, Yinsong Ren, Zhenwen Wu, Bin Zhao, Chunyu School of Mianyang City College Mianyang City College Mianyang China School of Information Engineering Southwest University of Science and Technology Mianyang China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai China

Multiple kernel clustering (MKC) excels at integrating information from multiple kernels for effective data clustering. Multiple kernel subspace clustering (MKSC) further enhances this by incorporating subspace learning, achieving significant performance improvements. However, most of existing MKSC methods often learn the affinity graphs directly and overlook the rich high-order correlations between different kernels, leading to suboptimal clustering results. This paper introduces MKSC-DT, a novel approach that addresses this limitation by utilizing dual tensors to capture high-order correlations in both feature space and semantic space. MKSC-DT learns multiple new kernels in original feature spaces and projects them onto a clean subspace to generate candidate affinity graphs. These new kernels and candidate graphs are then stacked into two third-order tensors, enabling the exploration of high-order relationships. An efficient alternating optimization algorithm is proposed to solve the resulting objective function. Extensive experiments on benchmark datasets demonstrate the superiority of MKSC-DT compared to state-of-the-art MKC methods, showcasing its effectiveness in leveraging high-order correlations for improved clustering performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds

DELFlow: Dense Efficient Learning of Scene Flow for Large-Sc...

引用

International Conference on Computer Vision (ICCV)

作者： Chensheng Peng Guangming Wang Xian Wan Lo Xinrui Wu Chenfeng Xu Masayoshi Tomizuka Wei Zhan Hesheng Wang Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai Jiao Tong University Mechanical Systems Control Laboratory University of California Berkeley

Point clouds are naturally sparse, while image pixels are dense. The inconsistency limits feature fusion from both modalities for point-wise scene flow estimation. Previous methods rarely predict scene flow from the entire point clouds of the scene with one-time inference due to the memory inefficiency and heavy overhead from distance calculation and sorting involved in commonly used farthest point sampling, KNN, and ball query algorithms for local feature aggregation. To mitigate these issues in scene flow learning, we regularize raw points to a dense format by storing 3D coordinates in 2D grids. Unlike the sampling operation commonly used in existing works, the dense 2D representation 1) preserves most points in the given scene, 2) brings in a significant boost of efficiency, and 3) eliminates the density gap between points and pixels, allowing us to perform effective feature fusion. We also present a novel warping projection technique to alleviate the information loss problem resulting from the fact that multiple points could be mapped into one grid during projection when computing cost volume. Sufficient experiments demonstrate the efficiency and effectiveness of our method, outperforming the prior-arts on the FlyingThings3D and KITTI dataset. Our source codes will be released on https://***/IRMVLab/DELFlow.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Proactive Resilient Day-Ahead Unit Commitment with Cloud Computing Data Centers

Proactive Resilient Day-Ahead Unit Commitment with Cloud Com...

引用

作者： Liu, Shengwei Zhao, Tianyang Liu, Xuan Li, Yuanzheng Wang, Peng Energy and Electricity Research Center Jinan University Zhuhai China School of Artificial Intelligence and Automation Ministry of Education Key Laboratory of Image Processing and Intelligence Control Huazhong University of Science and Technology Wuhan China School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore

To enhance the resilience of power systems toward the temporal and spatial impacts caused by extreme weather events, e.g., hurricanes, the flexibility of cloud data centers (CDCs) is treated as a kind of efficient demand response. Since the workloads of CDCs have the shifting capacity between different locations and time slots, a day-ahead unit commitment problem including data centers is proposed to explore the integrated spatial and temporal flexibility of the workloads to its full extent through task migration. Considering the uncertainty of probability density functions, the line failure rates, workload arrival rates, power loads are integrated into an ambiguity set. The scheduling process of generators and CDCs is modeled as a two-stage distributionally robust optimization problem, which is reformulated as a large-scale deterministic mixed-integer linear programming problem and solved by the multicuts Benders decomposition method. The performance of the proposed scheduling strategy is tested in both the IEEE 24-bus RTS system and the three-area RTS-96 system. The results reveal that the method could mitigate the adverse impacts of hurricanes by enhancing the resilience of power systems and decreasing the dropping workloads of CDCs. © 1972-2012 IEEE.

关键词： Hurricanes

来源：评论

学校读者我要写书评

暂无评论

MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects

arXiv

引用

arXiv 2022年

作者： Peng, Juewen Zhang, Jianming Luo, Xianrui Lu, Hao Xian, Ke Cao, Zhiguo Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of AIA Huazhong University of Science and Technology China Adobe Research

Partial occlusion effects are a phenomenon that blurry objects near a camera are semi-transparent, resulting in partial appearance of occluded background. However, it is challenging for existing bokeh rendering methods to simulate realistic partial occlusion effects due to the missing information of the occluded area in an all-in-focus image. Inspired by the learnable 3D scene representation, Multiplane image (MPI), we attempt to address the partial occlusion by introducing a novel MPI-based high-resolution bokeh rendering framework, termed MPIB. To this end, we first present an analysis on how to apply the MPI representation to bokeh rendering. Based on this analysis, we propose an MPI representation module combined with a background inpainting module to implement high-resolution scene representation. This representation can then be reused to render various bokeh effects according to the controlling parameters. To train and test our model, we also design a ray-tracing-based bokeh generator for data generation. Extensive experiments on synthesized and real-world images validate the effectiveness and flexibility of this framework. Copyright © 2022, The Authors. All rights reserved.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Transfer learning with a spatiotemporal graph convolution network for city flowprediction

引用

Frontiers of Information Technology & Electronic Engineering 2025年第1期26卷 79-92页

作者： Binkun LIU Yu KANG Yang CAO Yunbo ZHAO Zhenyi XU Department of Automation University of Science and Technology of ChinaHefei 230026China Key Laboratory of System Control and Information Processing Ministry of EducationShanghai 200240China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China Institute of Advanced Technology University of Science and Technology of ChinaHefei 230088China

Recently,deep learning based city flow prediction has been extensively used in the establishment of *** methods are data-hungry,making them unscalable to areas lacking *** transfer learningcan use data-rich source domains to assist target domain cities in city flow prediction,the performance of existingmethods cannot meet the needs of actual use,because the long-distance road network connectivity is *** this problem,we propose a transfer learning method based on spatiotemporal graph convolution,in which weconstruct a co-occurrence space between the source and target domains,and then align the mapping of the sourceand target domains’data in this space,to achieve the transfer learning of the source city flow prediction modelon the target ***,a dynamic spatiotemporal graph convolution module along with a temporalencoder is devised to simultaneously capture the concurrent spatiotemporal features,which implies the inherentrelationship among the road network structures,human travel habits,and city bike ***,these concurrentfeatures are leveraged as cross-city invariant representations and nonlinearly spanned to a co-occurrence *** domain features are thereby aligned with the source domain features in the co-occurrence space by using aMahalanobis distance loss,to achieve cross-city bike flow *** proposed method is evaluated on the publicbike flow datasets in Chicago,New York,and Washington in 2015,and significantly outperforms state-of-the-arttechniques.

关键词： Transfer learning City flow prediction Spatiotemporal graph convolution

来源：评论

学校读者我要写书评

暂无评论

ToF 3D vision detection and localization of soft packaging bags based on deep learning

ToF 3D vision detection and localization of soft packaging b...

引用

2021 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2021

作者： Shen, Chengyang Chen, Weidong Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Department of Automation

ISBN: (纸本)9781665436786

The detection of soft packaging bags is a key step in the process of soft packaging bags unpacking. Time-of-flight(ToF) camera is used as vision sensor and a multi-scale detection method based on deep learning is proposed to solve the deformation and shielding problems of soft packaging bags. This method is improved on the basis of YOLOv3. Aiming at the texture disorder and shape change caused by the deformation of the soft packaging bags, the deformation convolution is used to replace the standard convolution for feature extraction. In view of the slow detection speed of YOLOv3, the inverted residual module based on depth separable convolution is used to replace the residual module. Aiming at the problem of non-detection caused by the occlusion between soft packaging bags, the loss function in YOLOv3 is improved and the size of anchor box is adjusted. The test is carried out when there were different degrees of shielding between the soft packaging bags and different degrees of deformation of the soft packaging bags. The experimental results show that the detection speed of this method reaches 0.8s/frame, the recall rate reaches 99%, and the relative positioning accuracy reaches 2 cm. © 2021 IEEE.

关键词： Convolution

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：