检索结果-内蒙古大学图书馆

ICFRNet: Image Complexity Prior Guided Feature Refinement for Real-time Semantic Segmentation

学校读者我要写书评

暂无评论

ICFRNet: Image Complexity Prior Guided Feature Refinement fo...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xin Zhang Teodor Boyadzhiev Jinglei Shi Jufeng Yang VCIP & TMCC & DISSec College of Computer Science Nankai University Tianjin China Nankai International Advanced Research Institute (SHENZHEN• FUTIAN) Shenzhen China Institute of Mathematics and Informatics Bulgarian Academy of Sciences Sofia Bulgaria

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

In this paper, we leverage image complexity as a prior for refining segmentation features to achieve accurate real-time semantic segmentation. The design philosophy is based on the observation that different pixel regions within an image exhibit varying levels of complexity, with higher complexities posing a greater challenge for accurate segmentation. We thus introduce image complexity as prior guidance and propose the Image Complexity prior-guided Feature Refinement Network (ICFRNet). This network aggregates both complexity and segmentation features to produce an attention map for refining segmentation features within an Image Complexity Guided Attention (ICGA) module. We optimize the network in terms of both segmentation and image complexity prediction tasks with a combined loss function. Experimental results on the Cityscapes and CamViD datasets have shown that our ICFRNet achieves higher accuracy with a competitive efficiency for real-time segmentation.

关键词： Accuracy Philosophical considerations Semantic segmentation Aggregates Refining Semantics Real-time systems

Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Gao, Boyan Zhao, Bo Gowda, Shreyank N. Xing, Xingrun Yang, Yibo Hospedales, Timothy Clifton, David A. Department of Engineering Science University of Oxford United Kingdom School of Artificial Intelligence Shanghai Jiao Tong University China School of Computer Science University of Nottingham United Kingdom Institute of Automation Chinese Academy of Sciences China School of Informatics University of Edinburgh United Kingdom

Dataset condensation aims to synthesize datasets with a few representative samples that can effectively represent the original datasets. This enables efficient training and produces models with performance close to those trained on the original sets. Most existing dataset condensation methods conduct dataset learning under the bilevel (inner- and outer-loop) based optimization. However, the preceding methods perform with limited dataset generalization due to the notoriously complicated loss landscape and expensive time-space complexity of the inner-loop unrolling of bilevel optimization. These issues deteriorate when the datasets are learned via matching the trajectories of networks trained on the real and synthetic datasets with a long horizon inner-loop. To address these issues, we introduce Sharpness-Aware Trajectory Matching (SATM), which enhances the generalization capability of learned synthetic datasets by optimising the sharpness of the loss landscape and objective simultaneously. Moreover, our approach is coupled with an efficient hypergradient approximation that is mathematically well-supported and straightforward to implement along with controllable computational overhead. Empirical evaluations of SATM demonstrate its effectiveness across various applications, including in-domain benchmarks and out-of-domain settings. Moreover, its easy-to-implement properties afford flexibility, allowing it to integrate with other advanced sharpness-aware minimizers. Our code will be released. © 2025, CC BY.

关键词：

Learning to discuss strategically: a case study on one night ultimate werewolf 24

学校读者我要写书评

暂无评论

Learning to discuss strategically: a case study on one night...

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

作者： Xuanfa Jin Ziyan Wang Yali Du Meng Fang Haifeng Zhang Jun Wang Institute of Automation Chinese Academy of Sciences and School of Artificial Intelligence University of Chinese Academy of Sciences Cooperative AI Lab Department of Informatics King's College London University of Liverpool Institute of Automation Chinese Academy of Sciences and School of Artificial Intelligence University of Chinese Academy of Sciences and Nanjing Artificial Intelligence Research of IA AI Centre Department of Computer Science UCL

ISBN: (纸本)9798331314385

Communication is a fundamental aspect of human society, facilitating the exchange of information and beliefs among people. Despite the advancements in large language models (LLMs), recent agents built with these often neglect the control over discussion tactics, which are essential in communication scenarios and games. As a variant of the famous communication game Werewolf, One Night Ultimate Werewolf (ONUW) requires players to develop strategic discussion policies due to the potential role changes that increase the uncertainty and complexity of the game. In this work, we first present the existence of the Perfect Bayesian Equilibria (PBEs) in two scenarios of the ONUW game: one with discussion and one without. The results showcase that the discussion greatly changes players' utilities by affecting their beliefs, emphasizing the significance of discussion tactics. Based on the insights obtained from the analyses, we propose an RL-instructed language agent framework, where a discussion policy trained by reinforcement learning (RL) is employed to determine appropriate discussion tactics to adopt. Our experimental results on several ONUW game settings demonstrate the effectiveness and generalizability of our proposed framework. The project page of our paper: ***.

关键词：

NeRF-Texture: Synthesizing Neural Radiance Field Textures

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Huang, Yi-Hua Cao, Yan-Pei Lai, Yu-Kun Shan, Ying Gao, Lin Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China VAST ARC Lab Tencent PCG China School of Computer Science & Informatics Cardiff University United Kingdom

Texture synthesis is a fundamental problem in computer graphics that would benefit various applications. Existing methods are effective in handling 2D image textures. In contrast, many real-world textures contain meso-structure in the 3D geometry space, such as grass, leaves, and fabrics, which cannot be effectively modeled using only 2D image textures. We propose a novel texture synthesis method with Neural Radiance Fields (NeRF) to capture and synthesize textures from given multi-view images. In the proposed NeRF texture representation, a scene with fine geometric details is disentangled into the meso-structure textures and the underlying base shape. This allows textures with meso-structure to be effectively learned as latent features situated on the base shape, which are fed into a NeRF decoder trained simultaneously to represent the rich view-dependent appearance. Using this implicit representation, we can synthesize NeRF-based textures through patch matching of latent features. However, inconsistencies between the metrics of the reconstructed content space and the latent feature space may compromise the synthesis quality. To enhance matching performance, we further regularize the distribution of latent features by incorporating a clustering constraint. In addition to generating NeRF textures over a planar domain, our method can also synthesize NeRF textures over curved surfaces, which are practically useful. Experimental results and evaluations demonstrate the effectiveness of our approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Image texture

SketchDream: Sketch-based Text-to-3D Generation and Editing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Feng-Lin Fu, Hongbo Lai, Yu-Kun Gao, Lin SCM City University of Hong Kong EMIA HKUST China School of Computer Science and Informatics Cardiff University United Kingdom The Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences China

Existing text-based 3D generation methods generate attractive results but lack detailed geometry control. Sketches, known for their conciseness and expressiveness, have contributed to intuitive 3D modeling but are confined to producing texture-less mesh models within predefined categories. Integrating sketch and text simultaneously for 3D generation promises enhanced control over geometry and appearance but faces challenges from 2D-to-3D translation ambiguity and multi-modal condition integration. Moreover, further editing of 3D models in arbitrary views will give users more freedom to customize their models. However, it is difficult to achieve high generation quality, preserve unedited regions, and manage proper interactions between shape components. To solve the above issues, we propose a text-driven 3D content generation and editing method, SketchDream, which supports NeRF generation from given hand-drawn sketches and achieves free-view sketch-based local editing. To tackle the 2D-to-3D ambiguity challenge, we introduce a sketch-based multi-view image generation diffusion model, which leverages depth guidance to establish spatial correspondence. A 3D ControlNet with a 3D attention module is utilized to control multi-view images and ensure their 3D consistency. To support local editing, we further propose a coarse-to-fine editing approach: the coarse phase analyzes component interactions and provides 3D masks to label edited regions, while the fine stage generates realistic results with refined details by local enhancement. Extensive experiments validate that our method generates higher-quality results compared with a combination of 2D ControlNet and image-to-3D generation techniques and achieves detailed control compared with existing diffusion-based 3D editing approaches. Copyright © 2024, The Authors. All rights reserved.

关键词： 3D modeling

Parameterization of Nonlinear System Matrices for Implementation of State-Dependent Coefficient Control Methods

学校读者我要写书评

暂无评论

Parameterization of Nonlinear System Matrices for Implementa...

International Russian Automation Conference (RusAutoCon)

作者： Aleksey A. Kabanov Department of Informatics and Control in Technical Systems Sevastopol State University Sevastopol Russian Federation Federal Research Center "Computer Science and Control" of Russian Academy of Sciences Moscow Russian Federation

The research is devoted to the methods of state-dependent coefficient (SDC) for solving nonlinear optimal control problems. An important stage in the application of SDС methods is the parameterization (or even say factorization) of the original nonlinear system to the SDC form. In past studies, it has been shown that for multidimensional systems, the number of such parameterizations is infinite. Choosing the right parameterization can provide better convergence and quality parameters of the corresponding SDC method. This paper presents a number of criteria that can be used for parameterization. By the example of the problem of modeling large-scale monsoon intra-seasonal fluctuations based on the solution of the optimal control problem in a finite time interval, the analysis of the influence of the choice of the appropriate parameterization criterion on the solution of the problem is carried out.

关键词：

SpeechMirror: A Multimodal Visual Analytics System for Personalized Reflection of Online Public Speaking Effectiveness

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huang, Zeyuan He, Qiang Maher, Kevin Deng, Xiaoming Lai, Yu-Kun Ma, Cuixia Qin, Sheng-Feng Liu, Yong-Jin Wang, Hongan The Beijing Key Laboratory of Human-Computer Interaction Institute of Software Chinese Academy of Sciences and also with the School of Computer Science and Technology University of Chinese Academy of Sciences China Diatom Design Limited Liability Company United States The School of Computer Science and Informatics Cardiff University United Kingdom The School of Design Northumbria University United Kingdom The Department of Computer Science and Technology MOE-Key Laboratory of Pervasive Computing Tsinghua University China

As communications are increasingly taking place virtually, the ability to present well online is becoming an indispensable skill. Online speakers are facing unique challenges in engaging with remote audiences. However, there has been a lack of evidence-based analytical systems for people to comprehensively evaluate online speeches and further discover possibilities for improvement. This paper introduces SpeechMirror, a visual analytics system facilitating reflection on a speech based on insights from a collection of online speeches. The system estimates the impact of different speech techniques on effectiveness and applies them to a speech to give users awareness of the performance of speech techniques. A similarity recommendation approach based on speech factors or script content supports guided exploration to expand knowledge of presentation evidence and accelerate the discovery of speech delivery possibilities. SpeechMirror provides intuitive visualizations and interactions for users to understand speech factors. Among them, SpeechTwin, a novel multimodal visual summary of speech, supports rapid understanding of critical speech factors and comparison of different speech samples, and SpeechPlayer augments the speech video by integrating visualization of the speaker's body language with interaction, for focused analysis. The system utilizes visualizations suited to the distinct nature of different speech factors for user comprehension. The proposed system and visualization techniques were evaluated with domain experts and amateurs, demonstrating usability for users with low visualization literacy and its efficacy in assisting users to develop insights for potential improvement. Copyright © 2023, The Authors. All rights reserved.

关键词： Modal analysis

Efficient Resource Management in IoTs Using Evolutionary and Swarm Intelligence Algorithms 7

学校读者我要写书评

暂无评论

Efficient Resource Management in IoTs Using Evolutionary and...

7th International Symposium on Innovative Approaches in Smart Technologies, ISAS 2023

作者： Gupta, Keshav Dev Cengiz, Korhan Awasthi, Charu Ramini, Siva Akash Chatterjee, Shyamapriya Pavithra, M. Poornima College of Engineering Department of Computer Science Engineering Jaipur India University of Fujairah College of Information Technology United Arab Emirates Istinye University Department of Computer Engineering Istanbul Turkey University of Hradec Kralove Faculty of Informatics and Management Department of Information Technologies Hradec Kralove500 03 Czech Republic JSS Academy of Technical Education Department of Information Technology Noida India Andhra Pradesh Amaravati India Narula Institute of Technology Department of Information Technology West Bengal Kolkata India Jansons Institute of Technology Karumathampatti Department of Computer Science and Engineering Coimbatore641659 India

ISBN: (纸本)9798350383065

The proliferation of the Internet of Things (IoT) has ushered in a transformative era of connected devices, emphasizing the critical need for effective resource management. This study introduces an innovative approach that harnesses Evolutionary and Swarm Intelligence algorithms for IoT Task Scheduling, addressing resource optimization challenges. The approach offers superior resource utilization through advanced optimization techniques, reducing energy consumption and enhancing efficiency. Furthermore, it significantly reduces task scheduling execution time, enabling prompt decision-making in dynamic IoT environments. This results in improved task allocation quality, meeting application-specific requirements, and prioritizing critical tasks. Notably, the approach excels in minimizing completion time, making it particularly advantageous for real-time IoT applications. This research contributes to the advancement of IoT resource management, offering an adaptive, efficient, and intelligent solution with broad applicability. In the evolving landscape of IoT, the findings presented here lay a solid foundation for future research and practical implementations, ultimately promoting more responsive, sustainable, and intelligent IoT ecosystems. © 2023 IEEE.

关键词： Swarm intelligence

Chinese E-Romance: Analyzing and Visualizing 7.92 Million Alibaba Valentine's Day Purchases

学校读者我要写书评

暂无评论

Data and Information Management 2021年第4期5卷 363-371页

作者： Wang, Yongzhen Liu, Xiaozhong Ju, Yingnan Börner, Katy Lin, Jun Sun, Changlong Si, Luo WISE Lab Institute of Science of Science and S&T Management Faculty of Humanities and Social Sciences Dalian University of Technology Dalian China Computer Science Department Worcester Polytechnic Institute WorcesterMA United States School of Informatics Computing and Engineering Indiana University BloomingtonIN United States Alibaba DAMO Academy Hangzhou China

The days that precede Valentine's Day are characterized by extensive gift shopping activities all across the globe. In China, where much shopping takes place online, there has been an explosive growth in e-commerce sales during Valentine's Day over the recent years. This exploratory study investigates the extent to which each product category and each shopper group can exhibit romantic love within China's e-market throughout the 2 weeks leading up to 2019 Valentine's Day. Massive data from Alibaba, the biggest e-commerce retailer worldwide, are utilized to formulate an innovative romance index (RI) to quantitatively measure e-romantic values for products and shoppers. On this basis, millions of shoppers, along with their millions of products purchased around Valentine's Day, are analyzed as a case study to demonstrate their love consumption and romantic gift-giving. The results of the analysis are then illustrated to help understand Chinese e-romance based on the perspectives of different product categories and shopper groups. This empirical information visualization also contributes to improving the segmentation, targeting, and positioning of China's e-market for Valentine's Day. © 2021 Yongzhen Wang et al., published by Sciendo

关键词： Sales