检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Deng, Songhe Zhuo, Wei Xie, Jinheng Shen, Linlin Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

Class Activation Map (CAM) has emerged as a popular tool for weakly supervised semantic segmentation (WSSS), allowing the localization of object regions in an image using only image-level labels. However, existing CAM methods suffer from under-activation of target object regions and false-activation of background regions due to the fact that a lack of detailed supervision can hinder the model’s ability to understand the image as a whole. In this paper, we propose a novel Question-Answer Cross-Language-Image Matching framework for WSSS (QA-CLIMS), leveraging the vision-language foundation model to maximize the text-based understanding of images and guide the generation of activation maps. First, a series of carefully designed questions are posed to the VQA (Visual Question Answering) model with Question-Answer Prompt engineering (QAPE) to generate a corpus of both foreground target objects and backgrounds that are adaptive to query images. We then employ contrastive learning in a Region Image Text Contrastive (RITC) network to compare the obtained foreground and background regions with the generated corpus. Our approach exploits the rich textual information from the open vocabulary as additional supervision, enabling the model to generate high-quality CAMs with a more complete object region and reduce false-activation of background regions. We conduct extensive analysis to validate the proposed method and show that our approach performs state-of-the-art on both PASCAL VOC 2012 and MS COCO datasets. Code is available at: https://***/CVI-SZU/QA-CLIMS Copyright © 2024, The Authors. All rights reserved.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

HairDiffusion: vivid multi-colored hair editing via latent diffusion 24

HairDiffusion: vivid multi-colored hair editing via latent d...

引用

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Yu Zeng Yang Zhang Jiachen Liu Linlin Shen Kaijun Deng Weizhao He Jinbao Wang Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University and Shenzhen Institute of Artificial Intelligence and Robotics for Society and National Engineering Laboratory for Big Data System Computing Technology Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University and Guangdong Provincial Key Laboratory of Intelligent Information Processing

ISBN: (纸本)9798331314385

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Discrete Geometric Coded Data Layout for Large-scale Object Storage systems 21

Discrete Geometric Coded Data Layout for Large-scale Object ...

引用

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big Data and Cloud Computing, 16th IEEE International Conference on Social Computing and Networking and 13th International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Tian, Yi Xu, Guangping Yang, Hongzhang Ni, Yue Cao, JiaXin Yang, Lei Tianjin University of Technology School of Computer Science and Engineering Tianjin China Novel Software Technology Tianjin Key Laboratory of Intelligence Computing Tianjin China Key Laboratory of Computer Vision and System Ministry of Education China Information Technology Co. Ltd. China

ISBN: (纸本)9798350329223

Regenerating codes are new network codes proposed to reduce the data required for fault repair, which can improve the recovery efficiency of faulty nodes in data storage systems. However, unlike Reed-Solomon code, which repairs at the granularity of bytes, regenerating codes require data stored in large chunks but leads to severe read amplification, which reads out excess data when degraded read objects and increases degraded read time. That reflects a mutual constraint between improving recovery efficiency and degraded read performance, as manifested in the amplification of data reads, a vital issue considered in this *** solve this problem, we propose a new type of data layout - discrete geometric, which splits the object into a series of geometric sequences of data blocks. They are placed discretely into corresponding containers on the disks at different nodes, with containers of the same size made into a strip for encoding. The discrete characteristic ensures lower repair costs for degraded reads. The geometric characteristic ensures the repair performance of regenerating codes by large blocks, and read amplification can be mitigated through small blocks. To reduce IOPS for discrete geometric, we propose Discrete Geometric-Locally Regenerating Codes (DG-LRCs), guaranteeing lower degraded read latency while improving recovery *** results show that the degraded read time of DG-LRCs compared to regenerating codes combined with geometric partitioning is 22.56% lower at 2Gbpsand 60.56% lower at 4Gbps, and the recovery performance is 7.04 times better than that of RS code. © 2023 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning 22

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Lea...

引用

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： Cao, Weipeng Yao, Xuyang Xu, Zhiwu Pan, Yinghui Sun, Yixuan Li, Dachuan Qiu, Bohua Wei, Muheng Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (纸本)9798331527471

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model’s capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods. © 2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Tree Regularization for Visual Explanations of Cancer Cell Classification

Tree Regularization for Visual Explanations of Cancer Cell C...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Muhammad Umair Raza Jie Chen Li Wang Adil Nawaz Victor C.M. Leung Jianqiang Li College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

The challenge of interpretability remains a significant barrier to adopting deep neural networks in healthcare domains. Although tree regularization aims to align a deep neural network’s decisions with a single axis-aligned decision tree, however, relying on one tree for all inputs often leads to sub-optimal performance and interoperability. To address this limitation, we propose an enhanced tree regularization method that integrates a post-hoc visual explainable model such as Grad-CAM. This approach guides the deep model to be well-approximated by decision trees tailored to the salient regions identified by Grad-CAM in the input space. We rigorously validate the effectiveness of this framework on two cancer cell datasets: CNMC, which focuses on acute lymphoblastic leukemia cells, and ISBI2016, which comprises benign and malignant skin lesions. The results demonstrate that the proposed method delivers simpler and more interpretable explanations without compromising accuracy, thereby advancing the interpretability of deep learning models in critical healthcare applications.

关键词： Visualization Accuracy Decision making Artificial neural networks Predictive models Skin Decision trees Lesions Biological cells Cancer

来源：评论

学校读者我要写书评

暂无评论

Diversified Sequential Recommendation via Evolutionary Multi-Objective Transfer Optimization

Diversified Sequential Recommendation via Evolutionary Multi...

引用

Artificial Intelligence (CAI), IEEE Conference on

作者： Wei Zhou Xiaolong Luo Hongyue Bao Zexuan Zhu National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China

ISBN: (数字)9798350354096

ISBN: (纸本)9798350354102

Sequential Recommendation (SR) intends to model user interests based on historical behavior sequences and suggest the next item. Most existing sequential models primarily focus on learning users’ preferences on the relevance objective of the target item. However, the investigation of personalized preferences on the diversity objective of SR results is usually ignored. Evolutionary algorithms have amply demonstrated effectiveness in solving multi-objective problems but encounter efficiency bottlenecks when applied to multi-objective recommendation tasks due to the limited scalability at the user level. To address the problem, this study proposes to facilitate diversified SR via a multi-objective transfer optimization algorithm, in which each optimization task corresponds to the recommendation for a target user. With the optimization knowledge of user preference transferred within and across tasks, the diversified SR of a set of users can synchronously proceed. The novelty of our proposed algorithm is fully utilizing the outstanding global search capability of evolutionary multi-objective optimization without hindering the efficiency of sequential models.

关键词： Scalability Evolutionary computation Task analysis Artificial intelligence Optimization

来源：评论

学校读者我要写书评

暂无评论

Leveraging Predictive Maintenance for Photovoltaic systems 9th

Leveraging Predictive Maintenance for Photovoltaic Systems

引用

9th International Conference on Smart City Applications, SCA 2024

作者： Ledmaoui, Younes Raif, Mourad El Aroussi, Mohamed Saadane, Rachid Jakimi, Abdeslam Chehri, Abdellah Laboratory Engineering System Hassania School of Public Works Casablanca Morocco Software Engineering and Information Systems Engineering Team FST of Errachidia Moulay Ismail University Meknes Morocco Department of Mathematics and Computer Science Royal Military College of Canada KingstonONK7K 7B4 Canada

ISBN: (纸本)9783031886522

This paper introduces a novel edge device architecture designed to optimize solar energy management systems. It integrates cutting-edge functionalities such as generation prediction, maintenance alerts, and anomaly detection into a unified framework. Through the utilization of edge computing, the system enables real-time analysis and decision-making at the network’s edge. Leveraging machine learning algorithms and predictive models, these edge devices provide highly accurate energy generation forecasts, facilitating efficient energy utilization and strategic planning. Additionally, the architecture incorporates anomaly detection techniques to proactively identify deviations from normal operation, minimizing downtime and enabling timely maintenance interventions. The seamless integration of these features within the edge devices significantly enhances the overall efficiency, reliability, and performance of energy monitoring systems. By adopting this advanced edge device architecture, energy stakeholders can reap benefits such as improved energy management, reduced operational costs, and enhanced system reliability. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Battery management systems

来源：评论

学校读者我要写书评

暂无评论

Prediction of Solar Energy Production Using Low-Cost Data Logger and ANN Algorithm 9th

Prediction of Solar Energy Production Using Low-Cost Data L...

引用

9th International Conference on Smart City Applications, SCA 2024

作者： Raif, Mourad Ledmaoui, Younes El Aroussi, Mohamed Saadane, Rachid Jakimi, Abdeslam Chehri, Abdellah Laboratory Engineering System Hassania School of Public Works Casablanca Casablanca Morocco Software Engineering and Information Systems Engineering Team FST of Errachidia Moulay Ismail University Meknes Morocco Department of Mathematics and Computer Science Royal Military College of Canada KingstonONK7K 7B4 Canada

ISBN: (纸本)9783031886522

This article introduces a novel method for predicting solar energy production using an affordable data logger and the Artificial Neural Network (ANN) algorithm. The main goal of this research is to create a precise predictive model for solar energy output, addressing the critical need for accurate forecasting in the renewable energy industry. The study capitalizes on the accessibility and cost-efficiency of a low-cost data logger to collect detailed environmental and solar irradiance data. The ANN algorithm is utilized to analyze the collected dataset, providing a robust and effective approach for forecasting solar energy production. Extensive experiments demonstrate that the developed model achieves an impressive R2 score of 0.95, indicating a high degree of accuracy and reliability in predicting solar energy output. This significant R2 score highlights the proposed methodology’s effectiveness, demonstrating its potential for practical applications in solar energy planning and management. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： data logger Machine learning Photovoltaic prediction Renewable energy

来源：评论

学校读者我要写书评

暂无评论

Large Model Collaborative Optimization Enhanced by Mobile Consumer Electronics Constructed Federated ML

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Bu, Chao Li, Jianlong Wang, Jinsong Tianjin University of Technology Key Laboratory of Computer Vision and System of Ministry of Education School of Computer Science and Engineering Tianjin300384 China Tianjin University of Technology Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology School of Computer Science and Engineering Tianjin300384 China

With the rapid development of internet of everything, current Mobile Consumer Electronics (MCEs) can support complex computing due to their specialized data-handling capacity. Thus, federated Machine Learning (ML) and edge computing are integrated to leverage such capacity of MCEs to enhance large model training. This paper studies motivations of all participants that take part in large model collaborative optimization from a global perspective, and proposes the positive promotion pattern that collaborates MCEs, Edge Computing Servers (ECSs), and the centralized computing center to support large model collaborative optimization by introducing the idea of computing economic. We firstly propose the novel three-layered framework for large model collaboratively optimizing based on MCEs constructed federated ML. Secondly, we introduce the economic factor into the large model optimization by devising algorithms to assess consumptions of all participants and dynamically adjust incentive benefits according to the qualities of trained models. Finally, we design the scheme to encourage more MCEs to train local models by adaptively adjusting the ECS pricing strategy with the ECS future economic benefit trend considered. Experimental results validate that our proposed approach is able to optimize the global accuracy and improve the economic benefit more efficiently than the state of the art. © 1975-2011 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Kaijun Deng Dezhi Zheng Jindong Xie Jinbao Wang Weicheng Xie Linlin Shen Siyang Song Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Department of Computer Science University of Exeter

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code is available at https://***/CVI-SZU/DEGSTalk.

关键词： Hair Training Three-dimensional displays Dynamics Signal processing Rendering (computer graphics) Noise measurement Speech processing Faces Videos

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：