检索结果-内蒙古大学图书馆

11th International Conference on Learning Representations, ICLR 2023

作者： Liu, Weijie Xie, Jiahao Zhang, Chao Yamada, Makoto Zheng, Nenggan Qian, Hui Qiushi Academy for Advanced Studies Zhejiang University China College of Computer Science and Technology Zhejiang University China Okinawa Institute of Science and Technology Japan Kyoto University Japan RIKEN AIP Japan Zhejiang Lab China State Key Lab of CAD&CG Zhejiang University China Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies China Advanced Technology Institute Zhejiang University China

Traditional Dictionary Learning (DL) aims to approximate data vectors as sparse linear combinations of basis elements (atoms) and is widely used in machine learning, computer vision, and signal processing. To extend DL to graphs, Vincent-Cuaz et al. 2021 proposed a method, called GDL, which describes the topology of each graph with a pairwise relation matrix (PRM) and compares PRMs via the Gromov-Wasserstein Discrepancy (GWD). However, the lack of robustness often excludes GDL from a variety of real-world applications since GWD is sensitive to the structural noise in graphs. This paper proposes an improved graph dictionary learning algorithm based on a robust Gromov-Wasserstein discrepancy (RGWD) which has theoretically sound properties and an efficient numerical scheme. Based on such a discrepancy, our dictionary learning algorithm can learn atoms from noisy graph data. Experimental results demonstrate that our algorithm achieves good performance on both simulated and real-world datasets. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Signal processing

来源：评论

学校读者我要写书评

暂无评论

NeRF-Det++: Incorporating Semantic Cues and Perspective-aware Depth Supervision for Indoor Multi-View 3D Detection

arXiv

引用

arXiv 2024年

作者： Huang, Chenxi Hou, Yuenan Ye, Weicai Huang, Di Huang, Xiaoshui Lin, Binbin Cai, Deng Ouyang, Wanli The State Key Laboratory of CAD&CG College of Computer Science Zhejiang University China Shanghai AI Laboratory China The University of Sydney Australia

NeRF-Det has achieved impressive performance in indoor multi-view 3D detection by innovatively utilizing NeRF to enhance representation learning. Despite its notable performance, we uncover three decisive shortcomings in its current design, including semantic ambiguity, inappropriate sampling, and insufficient utilization of depth supervision. To combat the aforementioned problems, we present three corresponding solutions: 1) Semantic Enhancement. We project the freely available 3D segmentation annotations onto the 2D plane and leverage the corresponding 2D semantic maps as the supervision signal, significantly enhancing the semantic awareness of multi-view detectors. 2) Perspective-aware Sampling. Instead of employing the uniform sampling strategy, we put forward the perspective-aware sampling policy that samples densely near the camera while sparsely in the distance, more effectively collecting the valuable geometric clues. 3) Ordinal Residual Depth Supervision. As opposed to directly regressing the depth values that are difficult to optimize, we divide the depth range of each scene into a fixed number of ordinal bins and reformulate the depth prediction as the combination of the classification of depth bins as well as the regression of the residual depth values, thereby benefiting the depth learning process. The resulting algorithm, NeRF-Det++, has exhibited appealing performance in the ScanNetV2 and ARKITScenes datasets. Notably, in ScanNetV2, NeRF-Det++ outperforms the competitive NeRF-Det by +1.9% in mAP@0.25 and +3.5% in mAP@0.50. The code will be publicly at https: //***/mrsempress/NeRF-Detplusplus. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

SAMREFINER: TAMING SEGMENT ANYTHING MODEL FOR UNIVERSAL MASK REFINEMENT

arXiv

引用

arXiv 2025年

作者： Lin, Yuqi Li, Hengjia Shao, Wenqi Yang, Zheng Zhao, Jun He, Xiaofei Luo, Ping Zhang, Kaipeng State Key Lab of CAD&CG College of Computer Science Zhejiang University China Shanghai AI Laboratory China FABU Inc The University of Hong Kong Hong Kong

In this paper, we explore a principal way to enhance the quality of widely preexisting coarse masks, enabling them to serve as reliable training data for segmentation models to reduce the annotation cost. In contrast to prior refinement techniques that are tailored to specific models or tasks in a close-world manner, we propose SAMRefiner, a universal and efficient approach by adapting SAM to the mask refinement task. The core technique of our model is the noise-tolerant prompting scheme. Specifically, we introduce a multi-prompt excavation strategy to mine diverse input prompts for SAM (i.e, distance-guided points, context-aware elastic bounding boxes, and Gaussian-style masks) from initial coarse masks. These prompts can collaborate with each other to mitigate the effect of defects in coarse masks. In particular, considering the difficulty of SAM to handle the multi-object case in semantic segmentation, we introduce a split-then-merge (STM) pipeline. Additionally, we extend our method to SAMRefiner++ by introducing an additional IoU adaption step to further boost the performance of the generic SAMRefiner on the target dataset. This step is self-boosted and requires no additional annotation. The proposed framework is versatile and can flexibly cooperate with existing segmentation methods. We evaluate our mask framework on a wide range of benchmarks under different settings, demonstrating better accuracy and efficiency. SAMRefiner holds significant potential to expedite the evolution of refinement tools. Our code is available at SAMRefiner. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Sample2SQL: A Visual Interface for Querying Risky Enterprises

Sample2SQL: A Visual Interface for Querying Risky Enterprise...

引用

Pacific (formerly Asia-Pacific APVIS) Visualization Symposium

作者： Hongjia Wu Shanchen Zou Jiazhi Xia Hongxin Zhang Wei Chen State Key Lab of CAD&CG Zhejiang University Hangzhou China School of Computer Science and Engineering Central South University Changsha China

ISBN: (数字)9798350393804

ISBN: (纸本)9798350393811

We propose a visual query system for risky enterprises. Based on a small number of input samples of risky enterprises, users can interactively analyze and obtain SQL statements that express the query results, facilitating subsequent task operations and understanding risk criteria. Due to the diversity of enterprises and the complexity of economic indicators, understanding, evaluating, and querying risky enterprises is a challenging task for ordinary users. To solve this problem, our visual query system integrates multicriteria decision-making techniques and data mining through a visual analysis interface. The system facilitates efficient identification of risky enterprises, leveraging knowledge gained from a small number of known risk company samples. Our system includes an analytic hierarchy model to express domain knowledge, a query tree construction algorithm, and a well-designed visual interface. Two real cases demonstrate the effectiveness of our system.

关键词： Visualization Analytical models Law Economic indicators Time series analysis Decision making Data visualization

来源：评论

学校读者我要写书评

暂无评论

Interpreting the vulnerability of power systems in cascading failures using multi-graph convolutional networks

引用

Frontiers of Information Technology & Electronic Engineering 2022年第12期23卷 1848-1861页

作者： Supaporn LONAPALAWONG Changsheng CHEN Can WANG Wei CHEN State Key Lab of CAD&CG Zhejiang UniversityHangzhou 310058China China Electric Power Research Institute Beijing 100192China College of Computer Science and Technology Zhejiang UniversityHangzhou 310058China

Analyzing the vulnerability of power systems in cascading failures is generally regarded as a challenging problem. Although existing studies can extract some critical rules, they fail to capture the complex subtleties under different operational conditions. In recent years, several deep learning methods have been applied to address this issue. However, most of the existing deep learning methods consider only the grid topology of a power system in terms of topological connections, but do not encompass a power system’s spatial information such as the electrical distance to increase the accuracy in the process of graph convolution. In this paper, we construct a novel power-weighted line graph that uses power system topology and spatial information to optimize the edge weight assignment of the line graph. Then we propose a multi-graph convolutional network(MGCN) based on a graph classification task, which preserves a power system’s spatial correlations and captures the relationships among physical components. Our model can better handle the problem with power systems that have parallel lines, where our method can maintain desirable accuracy in modeling systems with these extra topology features. To increase the interpretability of the model, we present the MGCN using layer-wise relevance propagation and quantify the contributing factors of model classification.

关键词： Power systems Vulnerability Cascading failures Multi-graph convolutional networks Weighted line graph

来源：评论

学校读者我要写书评

暂无评论

InsightLens: Augmenting LLM-Powered Data Analysis With Interactive Insight Management and Navigation

引用

IEEE Transactions on Visualization and computer Graphics 2025年第6期31卷 3719-3732页

作者： Luoxuan Weng Xingbo Wang Junyu Lu Yingchaojie Feng Yihan Liu Haozhe Feng Danqing Huang Wei Chen State Key Lab of CAD&CG Zhejiang University Hangzhou China Weill Cornell Medical College Cornell University Ithaca NY USA Tencent Inc. Shenzhen China

The proliferation of large language models (LLMs) has revolutionized the capabilities of natural language interfaces (NLIs) for data analysis. LLMs can perform multi-step and complex reasoning to generate data insights based on users’ analytic intents. However, these insights often entangle with an abundance of contexts in analytic conversations such as code, visualizations, and natural language explanations. This hinders efficient recording, organization, and navigation of insights within the current chat-based LLM interfaces. In this paper, we first conduct a formative study with eight data analysts to understand their general workflow and pain points of insight management during LLM-powered data analysis. Accordingly, we introduce InsightLens, an interactive system to overcome such challenges. Built upon an LLM-agent-based framework that automates insight recording and organization along with the analysis process, InsightLens visualizes the complex conversational contexts from multiple aspects to facilitate insight navigation. A user study with twelve data analysts demonstrates the effectiveness of InsightLens, showing that it significantly reduces users’ manual and cognitive effort without disrupting their conversational data analysis workflow, leading to a more efficient analysis experience.

关键词： Data analysis Data visualization Navigation Oral communication Recording Codes Natural languages Semantics Organizations Manuals

来源：评论

学校读者我要写书评

暂无评论

DPS-Net: Deep Polarimetric Stereo Depth Estimation

DPS-Net: Deep Polarimetric Stereo Depth Estimation

引用

International Conference on computer Vision (ICCV)

作者： Chaoran Tian Weihong Pan Zimo Wang Mao Mao Guofeng Zhang Hujun Bao Ping Tan Zhaopeng Cui State Key Lab of CAD&CG Zhejiang University Hong Kong University of Science and Technology

Stereo depth estimation usually struggles to deal with textureless scenes for both traditional and learning-based methods due to the inherent dependence on image correspondence matching. In this paper, we propose a novel neural network, i.e., DPS-Net, to exploit both the prior geometric knowledge and polarimetric information for depth estimation with two polarimetric stereo images. Specifically, we construct both RGB and polarization correlation volumes to fully leverage the multi-domain similarity between polarimetric stereo images. Since inherent ambiguities exist in the polarization images, we introduce the iso-depth cost explicitly into the network to solve these ambiguities. Moreover, we design a cascaded dual-GRU architecture to recurrently update the disparity and effectively fuse both the multi-domain correlation features and the iso-depth cost. Besides, we present new synthetic and real polarimetric stereo datasets for evaluation. Experimental results demonstrate that our method outperforms the state-of-the-art stereo depth estimation methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Clothed Human Performance Capture with a Double-layer Neural Radiance Fields

Clothed Human Performance Capture with a Double-layer Neural...

引用

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

作者： Wang, Kangkan Zhang, Guofeng Cong, Suxu Yang, Jian Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China State Key Laboratory of CAD&CG Zhejiang University China

This paper addresses the challenge of capturing performance for the clothed humans from sparse-view or monocular videos. Previous methods capture the performance of full humans with a personalized template or recover the garments from a single frame with static human poses. However, it is inconvenient to extract cloth semantics and capture clothing motion with one-piece template, while single frame-based methods may suffer from instable tracking across videos. To address these problems, we propose a novel method for human performance capture by tracking clothing and human body motion separately with a double-layer neural radiance fields (NeRFs). Specifically, we propose a double-layer NeRFs for the body and garments, and track the densely deforming template of the clothing and body by jointly optimizing the deformation fields and the canonical double-layer NeRFs. In the optimization, we introduce a physics-aware cloth simulation network which can help generate physically plausible cloth dynamics and body-cloth interactions. Compared with existing methods, our method is fully differentiable and can capture both the body and clothing motion robustly from dynamic videos. Also, our method represents the clothing with an independent NeRFs, allowing us to model implicit fields of general clothes feasibly. The experimental evaluations validate its effectiveness on real multi-view or monocular videos. ©2023 IEEE.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

GAD-PVI: A General Accelerated Dynamic-Weight Particle-based Variational Inference Framework

arXiv

引用

arXiv 2023年

作者： Wang, Fangyikang Zhu, Huminhao Zhang, Chao Zhao, Hanbin Qian, Hui College of Computer Science and Technology Zhejiang University China Advanced Technology Institute Zhejiang University China State Key Lab of CAD&CG Zhejiang University China

Particle-based Variational Inference (ParVI) methods approximate the target distribution by iteratively evolving finite weighted particle systems. Recent advances of ParVI methods reveal the benefits of accelerated position update strategies and dynamic weight adjustment approaches. In this paper, we propose the first ParVI framework that possesses both accelerated position update and dynamical weight adjustment simultaneously, named the General Accelerated Dynamic-Weight Particle-based Variational Inference (GAD-PVI) framework. Generally, GAD-PVI simulates the semi-Hamiltonian gradient flow on a novel Information-Fisher-Rao space, which yields an additional decrease on the local functional dissipation. GAD-PVI is compatible with different dissimilarity functionals and associated smoothing approaches under three information metrics. Experiments on both synthetic and real-world data demonstrate the faster convergence and reduced approximation error of GAD-PVI methods over the state-of-the-art. © 2023, CC BY.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

GenesisTex2: Stable, Consistent and High-Quality Text-to-Texture Generation 39

GenesisTex2: Stable, Consistent and High-Quality Text-to-Tex...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Lu, Jiawei Zhang, Yingpeng Zhao, Zengjun Wang, He Zhou, Kun Shao, Tianjia State Key Lab of CAD&CG Zhejiang University China Tencent IEG China AI Centre University College London United Kingdom

ISBN: (纸本)157735897X

Large-scale text-guided image diffusion models have demonstrated remarkable results in text-to-image (T2I) generation. However, applying these models to synthesize textures for 3D geometries remains challenging due to the domain gap between 2D images and textures on a 3D surface. Early works that used a projecting-inpainting approach managed to preserve generation diversity, but often resulted in noticeable artifacts and style inconsistencies. While recent methods have attempted to address these inconsistencies, they often introduce other issues, such as blurring, over-saturation, or over-smoothing. To overcome these challenges, we propose a novel text-to-texture synthesis framework that takes advantage of pre-trained diffusion models. We introduce a local attention reweighing mechanism in the self-attention layers to guide the model in focusing on spatial-correlated patches across different views, thereby enhancing local details while preserving cross-view consistency. Additionally, we propose a novel latent space merge pipeline, which further ensures consistency across different viewpoints without sacrificing too much diversity. Our method significantly outperforms existing state-of-the-art techniques in terms of texture consistency and visual quality, while delivering results much faster than distillation-based methods. Importantly, our framework does not require additional training or fine-tuning, making it highly adaptable to a wide range of models available on public platforms. 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

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：