检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhou, Kanglei Li, Junlin Cai, Ruizhi Wang, Liyuan Zhang, Xingxing Liang, Xiaohui Department of Computer Science and Technology Institute for AI BNRist Center Tsinghua-Bosch Joint ML Center THBI Lab Tsinghua University China Zhongguancun Laboratory China State Key Laboratory of Virtual Reality Technology and Systems Beihang University China China Three Gorges University China

Action Quality Assessment (AQA) is pivotal for quantifying actions across domains like sports and medical care. Existing methods often rely on pre-trained backbones from large-scale action recognition datasets to boost performance on smaller AQA datasets. However, this common strategy yields suboptimal results due to the inherent struggle of these backbones to capture the subtle cues essential for AQA. Moreover, fine-tuning on smaller datasets risks overfitting. To address these issues, we propose Coarse-to-Fine Instruction Alignment (CoFInAl). Inspired by recent advances in large language model tuning, CoFInAl aligns AQA with broader pre-trained tasks by reformulating it as a coarse-to-fine classification task. Initially, it learns grade prototypes for coarse assessment and then utilizes fixed sub-grade prototypes for fine-grained assessment. This hierarchical approach mirrors the judging process, enhancing interpretability within the AQA framework. Experimental results on two long-term AQA datasets demonstrate CoFInAl achieves state-of-the-art performance with significant correlation gains of 5.49% and 3.55% on Rhythmic Gymnastics and Fis-V, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Disentangling Local and Global Information for Light Field Depth Estimation

Disentangling Local and Global Information for Light Field D...

引用

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Yang, Xueting Deng, Junli Chen, Rongshan Cong, Ruixuan Ke, Wei Sheng, Hao Communication University of China School of Information and Communication Engineering Beijing100024 China Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang Hangzhou Innovation Institute Yuhang Xixi Octagon City Hangzhou310023 China Macao Polytechnic University Faculty of Applied Sciences 999078 China

ISBN: (纸本)9798350302493

Accurate depth estimation from light field images is essential for various applications. Deep learning-based techniques have shown great potential in addressing this problem while still face challenges such as sensitivity to occlusions and difficulties in handling untextured areas. To overcome these limitations, we propose a novel approach that utilizes both local and global features in the cost volume for depth estimation. Specifically, our hybrid cost volume network consists of two complementary sub-modules: a 2D ContextNet for global context information and a matching cost volume for local feature information. We also introduce an occlusion-aware loss that accounts for occlusion areas to improve depth estimation quality. We demonstrate the effectiveness of our approach on the UrbanLF and HCInew datasets, showing significant improvements over existing methods, especially in occluded and untextured regions. Our method disentangles local feature and global semantic information explicitly, reducing the occlusion and untextured area reconstruction error and improving the accuracy of depth estimation. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Interactive hepatic parenchymal transection simulation with haptic feedback

引用

virtual Reality & Intelligent Hardware 2021年第5期3卷 383-396页

作者： Hongyu WU Haonan YU Fan YE Jian SUN Yuan GAO Ke TAN Aimin HAO State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Beijing Advanced Innovation Center for Biomedical Engineering Beijing 100191China Chinese PLA General Hospital Beijing 100039China

Background Liver resection involves surgical removal of a portion of the *** is used to treat liver tumors and liver *** complexity and high-risk nature of this surgery prevents novice doctors from practicing it on real *** surgery simulation was developed to simulate surgical procedures to enable medical professionals to be trained without requiring a patient,a cadaver,or an ***,there is a strong need for the development of a liver resection surgery simulation *** propose a real-time simulation system that provides realistic visual and tactile feedback for hepatic parenchymal *** The tetrahedron structure and cluster-based shape matching are used for physical model construction,topology update of a three-dimensional liver model soft deformation simulation,and haptic rendering *** the liver parenchyma separation simulation,a tetrahedral mesh is used for surface triangle subdivision and surface generation of the surgical *** shape-matching cluster is separated via component detection on an undirected graph constructed using the tetrahedral *** In our system,cluster-based shape matching is implemented on a GPU,whereas haptic rendering and topology updates are implemented on a *** results show that haptic rendering can be performed at a high frequency(>900Hz),whereas mesh skinning and graphics rendering can be performed at *** topology update can be executed at an interactive rate(>10Hz)on a single CPU *** We propose an interactive hepatic parenchymal transection simulation method based on a tetrahedral *** tetrahedral mesh simultaneously supports physical model construction,topology update,and haptic rendering acceleration.

关键词： virtual surgery Hepatic parenchymal transection Position-based dynamics

来源：评论

学校读者我要写书评

暂无评论

MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling with Informative-Preserved Reconstruction and Self-Distilled Consistency

MM-3DScene: 3D Scene Understanding by Customizing Masked Mod...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Mingye Xu Mutian Xu Tong He Wanli Ouyang Yali Wang Xiaoguang Han Yu Qiao The Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Chinese Academy of Sciences Shenzhen Institute of Advanced Technology Shenzhen China University of Chinese Academy of Sciences Shanghai Artificial Intelligence Laboratory SSE CUHKSZ FNii CUHKSZ

Masked Modeling (MM) has demonstrated widespread success in various vision challenges, by reconstructing masked visual patches. Yet, applying MM for large-scale 3D scenes remains an open problem due to the data sparsity and scene complexity. The conventional random masking paradigm used in 2D images often causes a high risk of ambiguity when recovering the masked region of 3D scenes. To this end, we propose a novel informative-preserved reconstruction, which explores local statistics to discover and preserve the representative structured points, effectively enhancing the pretext masking task for 3D scene understanding. Integrated with a progressive reconstruction manner, our method can concentrate on modeling regional geometry and enjoy less ambiguity for masked reconstruction. Besides, such scenes with progressive masking ratios can also serve to self-distill their intrinsic spatial consistency, requiring to learn the consistent representations from unmasked areas. By elegantly combining informative-preserved reconstruction on masked areas and consistency self-distillation from unmasked areas, a unified framework called MM-3DScene is yielded. We conduct comprehensive experiments on a host of downstream tasks. The consistent improvement (e.g., +6.1% mAP@0.5 on object detection and +2.2% mIoU on semantic segmentation) demonstrates the superiority of our approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning to Cluster Person in the Video via Graph Convolution Network

Learning to Cluster Person in the Video via Graph Convolutio...

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Wei Li Sixin Liang Ang Bian Guodong Du College of Computer Science Sichuan University Chengdu China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province School of Information Science and Engineering Yanshan University Qinhuangdao P.R. China

Video person re-identification is receiving academic interest. However, the practical application of the algorithm is hardly supported because of prohibitive annotated data. Hence, the study for unlabeled data will lead to an attractive alternative. This work explores an innovative strategy, namely, learning to cluster unlabeled person in the video through graph convolutional networks. In this paper, we find that the possibility of inter-frame linkage can be inferred from context. Therefore, a pose-guided topology linkage clustering framework is proposed. Our framework consists of three modules: (i) a pose-guided representation module; (ii) a pose-guided embedding module; (iii) a link prediction module. Firstly, the representation coding alone is performed at the level of relational induction bias, embedding the implicit pose structure information in image features. Then, based on the consideration of the topology relationship between adjacent and cross-frame, graph convolutional network is introduced to infer the likelihood of linkage between frame nodes. Experiments show that the method demonstrates excellent scalability in addition to being an effective response to person clustering in case of changes, and does not need the number of clusters as a prior.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Depth-continuous Scene Representation with Displacement Field for Robust Light Field Depth Estimation

引用

IEEE Transactions on Multimedia 2025年 27卷 3637-3649页

作者： Chen, Rongshan Sheng, Hao Yang, Da Cong, Ruixuan Cui, Zhenglong Wang, Sizhe Wang, Tun Zhao, Mingyuan Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University Key Laboratory of Data Science and Intelligent Computing International Innovation Institute 166 Shuanghongqiao Street Pingyao Town Yuhang District Hangzhou31 1115 China Macao Polytechnic University Faculty of Applied Sciences Macao999078 China

The light field (LF) captures both the spatial and angular information of scenes, enabling accurate depth estimation. However, previous deep learning methods typically model surface depth only while ignoring the continuous nature of depth in 3D scenes. In this paper, we use the displacement field (DF) to describe this continuous property, and propose a novel depth-continuous scene representation for robust LF depth estimation. Experiments demonstrate that our representation enables the network to generate highly detailed depth maps with fewer parameters and faster speeds. Specifically, inspired by the signed distance field in 3D object descriptions, we aim to exploit the intrinsic depth-continuous property of 3D scenes via DF and define a novel depth-continuous scene representation. Then, we introduce a simple, yet general, learning framework for depth-continuous scene embedding, and the proposed network, DepthDF, achieves state-of-the-art performance on both synthetic and real-world LF datasets, ranking 1st on the HCI 4D light field benchmark. Furthermore, previous LF depth estimation methods can also be seamlessly integrated into this framework. Finally, we extend this framework beyond LF depth estimation to various tasks, including multiview stereo depth inference, LF superresolution, and LF salient object detection. Our experiments demonstrate an improved performance when continuous scene representation is applied, suggesting that our framework can potentially provide insights for more fields. © 1999-2012 IEEE.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Understanding Wireless Charger Networks: Concepts, Current Research, and Future Directions

引用

IEEE Communications Surveys and Tutorials 2024年

作者： Ren, Meixuan Dai, Haipeng Liu, Tang Deng, Xianjun Dou, Wanchun Yang, Yuanyuan Chen, Guihai Nanjing University State Key Laboratory for Novel Software Technology Nanjing210023 China Sichuan Normal University College of Computer Science Sichuan Chengdu610101 China Sichuan Normal University Visual Computing and Virtual Reality Key Laboratory of Sichuan Province Sichuan Chengdu610068 China Huazhong University of Science and Technology School of Cyber Science and Engineering Wuhan430074 China Stony Brook University Department of Electrical and Computer Engineering NY11794 United States

Wireless Charger Network (WCN) emerges as a promising networking paradigm, employing wireless chargers with Wireless Power Transfer (WPT) technology to provide long-term and sustainable energy supply for future networks. Although extensive research has been conducted in this area over the last decade, there is currently no comprehensive survey to compile the latest literature and provide insights into future research directions. To fill this gap, our survey explores the recent developments in the active research area of WCNs. This paper starts by providing a framework of WCNs in detail, covering aspects of network architecture, various charging models, network design issues, and typical applications of WCNs. Then, we give an overview of charger deployment schemes, focusing on omnidirectional, directional, non-radiative, and heterogeneous charger deployments. We also provide an overview of charging scheduling schemes, encompassing power control, time allocation, energy beamforming, and multi-resource scheduling. Moreover, we explore communication optimization schemes, including Medium Access Control (MAC) protocols, routing protocols, broadcast transmission, and data collection. Finally, we highlight some future research directions and present corresponding open issues to advance the research on WCNs. © 1998-2012 IEEE.

关键词： Inductive power transmission

来源：评论

学校读者我要写书评

暂无评论

Reinforced Heterogeneous Graphlet Design for Knowledge Graph Representation Learning

SSRN

引用

SSRN 2023年

作者： Gong, Jibing Lin, Yuting Zhao, Yi Lin, Tianyu Fang, Xiaohan Feng, Xinchao Peng, Jiquan School of Information Science and Engineering Yanshan University Qinhuangdao066004 China The Key Laboratory for Computer Virtual Technology System Integration of Hebei Province Yanshan University Qinhuangdao066004 China

Knowledge Graphs have been practical tools to represent and integrate plentiful structural and semantic information in mainstream industrial scenarios. While promising, the heterogeneity and complexity of KGs pose a formidable obstacle, especially for graph representation learning. Most existing KG embedding models omit the dynamic high-order connectivity patterns, and heavily rely on the handcrafted patterns to handle the complex semantic relationships, thereby limiting their ability to adaptively capture nuanced and intricate relationships of knowledge graphs in different tasks. To fill this gap, we present ReHGD — a model designed for KGs that focuses on adaptively designing typed graphlets through a cooperative Multi-agent Reinforcement Learning algorithm. This approach can learn more discriminative graph representations tailored to specific downstream tasks. Specifically, ReHGD engages in the creation of typed graphlets through a two-stage process: it (1) establishes a reinforced chain design module to generate chains without predefined rules, and (2) employs a buffer-aware sampling technique to derive episodic chains from prior experiences. Subsequently, motifs are deduced by applying commute count and Hadamard product operations to the episodic chain-based subgraphs. Finally, ReHGD utilize chain and motif aggregations to learn graph representations. Experimental results on three real-world KGs show that ReHGD outperforms baselines on entity classification. © 2023, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

RepMode: Learning to Re-Parameterize Diverse Experts for Subcellular Structure Prediction

RepMode: Learning to Re-Parameterize Diverse Experts for Sub...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Donghao Zhou Chunbin Gu Junde Xu Furui Liu Qiong Wang Guangyong Chen Pheng-Ann Heng Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences The Chinese University of Hong Kong Zhejiang Lab

In biological research, fluorescence staining is a key technique to reveal the locations and morphology of subcellular structures. However, it is slow, expensive, and harmful to cells. In this paper, we model it as a deep learning task termed subcellular structure prediction (SSP), aiming to predict the 3D fluorescent images of multiple subcellular structures from a 3D transmitted-light image. Unfortunately, due to the limitations of current biotechnology, each image is partially labeled in SSP. Besides, naturally, subcellular structures vary considerably in size, which causes the multi-scale issue of SSP. To overcome these challenges, we propose Re-parameterizing Mixture-of-Diverse-Experts (RepMode), a network that dynamically organizes its parameters with task-aware priors to handle specified single-label prediction tasks. In RepMode, the Mixture-of-Diverse-Experts (MoDE) block is designed to learn the generalized parameters for all tasks, and gating re-parameterization (GatRep) is performed to generate the specialized parameters for each task, by which RepMode can maintain a compact practical topology exactly like a plain network, and meanwhile achieves a powerful theoretical topology. Comprehensive experiments show that RepMode can achieve state-of-the-art overall performance in SSP.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HoughLaneNet: Lane Detection with Deep Hough Transform and Dynamic Convolution

arXiv

引用

arXiv 2023年

作者： Zhang, Jia-Qi Duan, Hao-Bin Chen, Jun-Long Shamir, Ariel Wang, Miao The State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China The Efi Arazi School of Computer Science Reichman University Herzliya4610000 Israel The Zhongguancun Laboratory Beijing100195 China

The task of lane detection has garnered considerable attention in the field of autonomous driving due to its complexity. Lanes can present difficulties for detection, as they can be narrow, fragmented, and often obscured by heavy traffic. However, it has been observed that the lanes have a geometrical structure that resembles a straight line, leading to improved lane detection results when utilizing this characteristic. To address this challenge, we propose a hierarchical Deep Hough Transform (DHT) approach that combines all lane features in an image into the Hough parameter space. Additionally, we refine the point selection method and incorporate a Dynamic Convolution Module to effectively differentiate between lanes in the original image. Our network architecture comprises a backbone network, either a ResNet or Pyramid Vision Transformer, a Feature Pyramid Network as the neck to extract multi-scale features, and a hierarchical DHT-based feature aggregation head to accurately segment each lane. By utilizing the lane features in the Hough parameter space, the network learns dynamic convolution kernel parameters corresponding to each lane, allowing the Dynamic Convolution Module to effectively differentiate between lane features. Subsequently, the lane features are fed into the feature decoder, which predicts the final position of the lane. Our proposed network structure demonstrates improved performance in detecting heavily occluded or worn lane images, as evidenced by our extensive experimental results, which show that our method outperforms or is on par with state-of-the-art techniques. © 2023, CC BY-NC-SA.

关键词： Hough transforms

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：