检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Jin, Jian Yu, Zhenbo Shen, Yang Fu, Zhenyong Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Sci. & Tech. China

Customized text-to-image generation renders user-specified concepts into novel contexts based on textual prompts. Scaling the number of concepts in customized generation meets a broader demand for user creation, whereas existing methods face challenges with generation quality and computational efficiency. In this paper, we propose LATEXBLEND, a novel framework for effectively and efficiently scaling multi-concept customized generation. The core idea of LATEXBLEND is to represent single concepts and blend multiple concepts within a Latent Textual space, which is positioned after the text encoder and a linear projection. LATEXBLEND customizes each concept individually, storing them in a concept bank with a compact representation of latent textual features that captures sufficient concept information to ensure high fidelity. At inference, concepts from the bank can be freely and seamlessly combined in the latent textual space, offering two key merits for multi-concept generation: 1) excellent scalability, and 2) significant reduction of denoising deviation, preserving coherent layouts. Extensive experiments demonstrate that LATEXBLEND can flexibly integrate multiple customized concepts with harmonious structures and high subject fidelity, substantially outperforming baselines in both generation quality and computational efficiency. Project Page. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance

Driving-Video Dehazing with Non-Aligned Regularization for S...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Junkai Fan Jiangwei Weng Kun Wang Yijun Yang Jianjun Qian Jun Li Jian Yang PCA Lab Nanjing University of Science and Technology China PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Sci. & Tech. The Hong Kong University of Science and Technology Guangzhou

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Real driving-video dehazing poses a significant challenge due to the inherent difficulty in acquiring precisely aligned hazy/clear video pairs for effective model training, especially in dynamic driving scenarios with unpredictable weather conditions. In this paper, we propose a pioneering approach that addresses this challenge through a nonaligned regularization strategy. Our core concept involves identifying clear frames that closely match hazy frames, serving as references to supervise a video dehazing network. Our approach comprises two key components: reference matching and video dehazing. Firstly, we introduce a non-aligned reference frame matching module, leveraging an adaptive sliding window to match high-quality reference frames from clear videos. Video dehazing incorporates flow-guided cosine attention sampler and deformable cosine attention fusion modules to enhance spatial multi-frame alignment and fuse their improved information. To validate our approach, we collect a GoProHazy dataset captured effortlessly with GoPro cameras in diverse rural and urban road environments. Extensive experiments demonstrate the superiority of the proposed method over current state-of-the-art methods in the challenging task of real driving-video dehazing. Project page.

关键词： Training computer vision Fuses Roads Cameras Safety Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Equivariant Diffusion for Crystal Structure Prediction 41

Equivariant Diffusion for Crystal Structure Prediction

引用

41st International Conference on Machine Learning, ICML 2024

作者： Lin, Peijia Chen, Pin Jiao, Rui Mo, Qing Cen, Jianhuan Huang, Wenbing Liu, Yang Huang, Dan Lu, Yutong School of Computer Science and Engineering Sun Yat-sen University Guangzhou China National Supercomputer Center Guangzhou China Dept. of Comp. Sci. Tech. Institute for AI Tsinghua University Beijing China Institute for AIR Tsinghua University Beijing China Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

In addressing the challenge of Crystal Structure Prediction (CSP), symmetry-aware deep learning models, particularly diffusion models, have been extensively studied, which treat CSP as a conditional generation task. However, ensuring permutation, rotation, and periodic translation equivariance during diffusion process remains incompletely addressed. In this work, we propose EquiCSP, a novel equivariant diffusion-based generative model. We not only address the overlooked issue of lattice permutation equivariance in existing models, but also develop a unique noising algorithm that rigorously maintains periodic translation equivariance throughout both training and inference processes. Our experiments indicate that EquiCSP significantly surpasses existing models in terms of generating accurate structures and demonstrates faster convergence during the training process. Code is available at https://***/EmperorJia/EquiCSP. Copyright 2024 by the author(s)

关键词： Crystal symmetry

来源：评论

学校读者我要写书评

暂无评论

Multi-label classification review and opportunities

Journal of Network Intelligence

引用

Journal of Network Intelligence 2021年第2期6卷 255-275页

作者： Weng, Wei Li, Yu-Wen Liu, Jing-Hua Wu, Shun-Xiang Chen, Chin-Ling College of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China School of Instrument Science and Engineering Southeast University Nanjing210096 China College of Computer Science and Technology Huaqiao University Xiamen361021 China Department of Automation Xiamen University Xiamen361005 China School of Computer and Information Engineering Xiamen University of Technology Xiamen361005 China School of Information Engineering Changchun Sci-Tech University Changchun130600 China Department of Computer Science and Information Engineering Chaoyang University of Technology Taichung41349 Taiwan

Multi-label classification originated from text classification and has became one of the most widely studied machine learning frameworks. After nearly twenty years of development, many multi-label classification models have been produced. In this paper, the representative algorithms are introduced and reviewed. On the other hand, in recent years, the volume of multi-label data has become larger, and the features and labels have become higher dimensions, so the multi-label algorithms have also generated new trends. The main research directions focus on label specific feature, label correlation, and dimension compression. This paper discusses these studies in detail. Different from other review works, this paper discusses the evolution and improvement process of various algorithms and summarizes the main research directions in recent years. The content summarized in this paper can provide a more comprehensive perspective for related researchers to understand the main research contents in this direction, and inspire new research means and methods. © 2021 Global Research Online. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Fault-Tolerant Data Aggregation with Error-Checking for Smart Grids

Fault-Tolerant Data Aggregation with Error-Checking for Smar...

引用

IEEE International Symposium on Dependable, Autonomic and Secure Computing (DASC)

作者： Congcong Wang Chen Wang Jian Shen Pandi Vijayakumar Zakirul Alam Bhuiyan School of Software Nanjing University of Information Science & Technology Nanjing China School of Information Science and Engineering Zhejiang Sci-Tech University Hangzhou China Department of Computer Science and Engineering University College of Engineering Tindivanam Tamilnadu India Department of Computer and Information Sciences Fordham University New York USA

With the rapid development of smart grid tech.ology, a new challenge has been brought about by the massive data generated from distributed devices. Data aggregation tech.ology plays a crucial role in smart grid schemes, in terms of energy data statistics and resource allocation. However, achieving fast error-checking and improving device fault-tolerance are still open issues in the smart grid data aggregation. To address these issues, this paper proposes an error-tolerant data aggregation scheme integrated with error-checking mechanisms. The scheme proposes a tree-based aggregation structure, facilitating swift error-checking of data. We combine masking values with user anonymity in the ElGamal cryptographic scheme to ensure the security of sensitive data and resist collusion attacks. Both theoretical and experimental analyses demonstrate that this scheme enables a lightweight, secure data aggregation, ensuring enhanced reliability and error-checking.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tri-Perspective view Decomposition for Geometry-Aware Depth Completion

Tri-Perspective view Decomposition for Geometry-Aware Depth ...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Zhiqiang Yan Yuankai Lin Kun Wang Yupeng Zheng Yufei Wang Zhenyu Zhang Jun Li Jian Yang PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Sci. & Tech. China Huazhong University of Science and Technology Chinese Academy of Sciences Northwestem Poly technical University Nanjing University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Depth completion is a vital taskfor autonomous driving, as it involves reconstructing the precise 3D geometry of a scene from sparse and noisy depth measurements. How-ever, most existing methods either rely only on 2D depth representations or directly incorporate raw 3D point clouds for compensation, which are still insufficient to capture the fine-grained 3D geometry of the scene. To address this chal-lenge, we introduce Tri-Perspective View Decomposition (TPVD), a novel framework that can explicitly model 3D geometry. In particular, (1) TPVD ingeniously decomposes the original point cloud into three 2D views, one of which corresponds to the sparse depth input. (2) We design TPV Fusion to update the 2D TPV features through recurrent 2D-3D-2D aggregation, where a Distance-Aware Spherical Convolution (DASC) is applied. (3) By adaptively choosing TPVaffinitive neighbors, the newly proposed Geometric Spatial Propagation Network (GSPN) further improves the geometric consistency. As a result, our TPVD outperforms existing methods on KITTI, NYUv2, and SUN RGBD. Fur-thermore, we build a novel depth completion dataset named TOFDC, which is acquired by the time-of-flight (TOF) sen-sor and the color camera on smart phones. Project page.

关键词： Geometry Point cloud compression Solid modeling Three-dimensional displays Laser radar Convolution Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Enhanced receptive field smoke detection model embedded with attention mechanism

Enhanced receptive field smoke detection model embedded with...

引用

Chinese Automation Congress (CAC)

作者： Yang Cao Gang Wang Hongyuan Wen Xiaojun Liu Zhijie Yang School of Intelligent Manufacturing Taizhou Institute of Sci. & Tech. Nanjing University of Science & Technology Taizhou China School of Electronic and Electrical Engineering Taizhou Institute of Sci. & Tech. Nanjing University of Science & Technology Taizhou China

Smoke is an important feature of forest fire early detection. The accuracy of the existing smoke detection model is easily affected by the surrounding environment, and the sampling times of the image center and edge are uneven, which eventually leads to the unsatisfactory effect of feature extraction and low accuracy. In order to solve these problems, a SE_RFB_YOLO fire smoke target detection model is proposed which embeds channel attention mechanism based on YOLOv3 model to improve the anti-interference ability and feature extraction ability of the network; Clustering is used to obtain the a priori frame size that meets the smoke target; The feature map is connected to the RFB-s module to expand the receptive field, and the extracted features are more obvious. Compared with YOLOv3, target detection accuracy of RFBNet model is 86.4%, the recall rate is 89.7%, and the detection speed is 26 *** proposed target detection model can better meet the needs of the task and show better detection effect.

关键词： Sensitivity Image edge detection Object detection Interference Feature extraction Data models Robustness

来源：评论

学校读者我要写书评

暂无评论

Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding

Rethinking the Video Sampling and Reasoning Strategies for T...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Zhu, Jiahao Liu, Daizong Zhou, Pan Di, Xing Cheng, Yu Yang, Song Xu, Wenzheng Xu, Zichuan Wan, Yao Sun, Lichao Xiong, Zeyu Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology China ProtagoLabs Inc Microsoft Research Wangxuan Institute of Computer Technology Peking University China Beijing Institute of Technology China School of Sichuan University China Dalian University of Technology China Lehigh University United States School of Computer Sci. & Tech. Huazhong University of Science and Technology China

Temporal sentence grounding (TSG) aims to identify the temporal boundary of a specific segment from an untrimmed video by a sentence query. All existing works first utilize a sparse sampling strategy to extract a fixed number of video frames and then conduct multimodal interactions with query sentence for reasoning. However, we argue that these methods have overlooked two indispensable issues: 1) Boundary-bias: The annotated target segment generally refers to two specific frames as corresponding start and end timestamps. The video downsampling process may lose these two frames and take the adjacent irrelevant frames as new boundaries. 2) Reasoning-bias: Such incorrect new boundary frames also lead to the reasoning bias during frame-query interaction, reducing the generalization ability of model. To alleviate above limitations, in this paper, we propose a novel Siamese Sampling and Reasoning Network (SSRN) for TSG, which introduces a siamese sampling mechanism to generate additional contextual frames to enrich and refine the new boundaries. Specifically, a reasoning strategy is developed to learn the inter-relationship among these frames and generate soft labels on boundaries for more accurate frame-query reasoning. Such mechanism is also able to supplement the absent consecutive visual semantics to the sampled sparse frames for fine-grained activity understanding. Extensive experiments demonstrate the effectiveness of SSRN on three challenging datasets. © 2022 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Balancing Human-robot Collaborative Disassembly Line by Using Dingo Optimization Algorithm

Balancing Human-robot Collaborative Disassembly Line by Usin...

引用

IEEE International Conference on Human-Machine Systems

作者： Xiwang Guo Liangbo Zhou Mengchu Zhou Weitian Wang Jiacun Wang Liang Qi Information and Control Engineering Liaoning Petrochemical University Fushun China Information and Control Liaoning Petrochemical University Fushun China Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ USA School of Computing Montclair State University Montclair USA Computer Science and Software Eng. Monmouth University West Long Branch NJ USA Computer Intelligent Sci. and Tech. Shandong University of Sci. and Tech. Qingdao China

ISBN: (数字)9798350315790

ISBN: (纸本)9798350315806

Disassembling and recycling scrapped products play important roles in effectively reducing environmental pollution and improving resource sustainability. A multi-product human-robot collaborative disassembly-line-balancing problem (MHDP) arises from doing so and represents an important yet to be solved in the remanufacturing field. This work explores how to use optimization algorithms to schedule tasks between humans and robots to maximize remanufacturing profit in human-robot collaboration contexts. Specifically, we investigate MHDP and develop a mixed integer programming model considering various system constraints. We propose a dingo optimization algorithm that simulates wild dogs’ social hierarchy and chasing processes to solve MHDP. We compare the proposed algorithm with an exact solution finder, i.e., IBM CPLEX and a well-known intelligent optimization method, i.e., Genetic Algorithm to show its competitive performance in terms of solution accuracy and efficiency.

关键词： Integer programming Schedules Pollution Human-machine systems Collaboration Optimization methods Recycling

来源：评论

学校读者我要写书评

暂无评论

Dual-Source CBCT for Larger Longitudinal Coverage: System Design and Image Reconstruction

Dual-Source CBCT for Larger Longitudinal Coverage: System De...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Xusheng Zhang Tianling Lyu Yijie Shi Xinyun Zhong Zhan Wu Yan Xi Shijie Wang Yang Chen Wentao Zhu School of Software Southeast University Nanjing China Zhejiang Lab Hangzhou China Laboratory of Image Science and Technology the School of Computer Science and Engineering Southeast University Nanjing China First-Imaging Tech. Shanghai China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing the Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Nanjing China

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

The application of CBCT systems in intraoperative environments has become increasingly common, but concurrent CBCT systems are unsuitable for situations that require a large longitudinal imaging FoV, such as orthopedics. To increase longitudinal coverage, we developed a dual-source CBCT (DS-CBCT) system in which two ray sources are symmetrically placed along the central plane. After further analyzing its geometric characteristics, we propose an analytical reconstruction algorithm termed DT-FDK specialized for DS-CBCT, which combines cone-beam rebinning and two rays with smaller cone angles among the four conjugate rays to further suppress cone beam artifacts. The system design and reconstruction algorithm are tested on both simulated and real-scanned data. Results show that the DS-CBCT can expand the effective imaging volume by 37.1% compared to single-source CBCT systems. The reconstructed images by DT-FDK also show improved image quality compared to traditional reconstruction algorithms.

关键词： Image quality Orthopedic surgery Imaging Reconstruction algorithms engineering in medicine and biology Image reconstruction System analysis and design

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：