检索结果-内蒙古大学图书馆

Embedding an Ethical Mind: Aligning Text-to-Image Synthesis via Lightweight Value Optimization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Xingqi Yi, Xiaoyuan Xie, Xing Jia, Jia Department of Computer Science and Technology Tsinghua University Beijing China Microsoft Research Asia Beijing China BNRist Tsinghua University Key Laboratory of Pervasive Computing Beijing China

Recent advancements in diffusion models trained on large-scale data have enabled the generation of indistinguishable human-level images, yet they often produce harmful content misaligned with human values, e.g., social bias, and offensive content. Despite extensive research on Large Language Models (LLMs), the challenge of Text-to-Image (T2I) model alignment remains largely unexplored. Addressing this problem, we propose LiVO (Lightweight Value Optimization), a novel lightweight method for aligning T2I models with human values. LiVO only optimizes a plug-and-play value encoder to integrate a specified value principle with the input prompt, allowing the control of generated images over both semantics and values. Specifically, we design a diffusion model-tailored preference optimization loss, which theoretically approximates the Bradley-Terry model used in LLM alignment but provides a more flexible trade-off between image quality and value conformity. To optimize the value encoder, we also develop a framework to automatically construct a text-image preference dataset of 86k (prompt, aligned image, violating image, value principle) samples. Without updating most model parameters and through adaptive value selection from the input prompt, LiVO significantly reduces harmful outputs and achieves faster convergence, surpassing several strong baselines and taking an initial step towards ethically aligned T2I models. Our code is available at https://***/achernarwang/LiVO. Warning: This paper involves descriptions and images depicting discriminatory, pornographic, bloody, and horrific scenes. © 2024, CC BY-NC-ND.

关键词： Semantics

FF-LOGO: Cross-Modality Point Cloud Registration with Feature Filtering and Local to Global Optimization

学校读者我要写书评

暂无评论

FF-LOGO: Cross-Modality Point Cloud Registration with Featur...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Nan Ma Mohan Wang Yiheng Han Yong-Jin Liu Faculty of Information Technology Beijing University of Technology Beijing China Department of Computer Science and Technology BNRist MOE-Key Laboratory of Pervasive Computing Tsinghua University Beijing China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Cross-modality point cloud registration is confronted with significant challenges due to inherent differences in modalities between sensors. To deal with this problem, we propose FF-LOGO: a cross-modality point cloud registration framework with Feature Filtering and LOcal-Global Optimization. The cross-modality feature correlation filtering module extracts geometric transformation-invariant features from cross-modality point clouds and achieves point selection by feature matching. We also introduce a cross-modality optimization process, including a local adaptive key region aggregation module and a global modality consistency fusion optimization module. Experimental results demonstrate that our two-stage optimization significantly improves the registration accuracy of the feature association and selection module. Our method achieves a substantial increase in recall rate compared to the current state-of-the-art methods on the 3DCSR dataset, improving from 40.59% to 75.74%. Our code will be available at https://***/wangmohan17/FFLOGO.

关键词： Point cloud compression Deep learning Accuracy Correlation Codes Filtering Feature extraction

Medical image-based detection of COVID-19 using Deep Convolution Neural Networks

学校读者我要写书评

暂无评论

Medical image-based detection of COVID-19 using Deep Convolu...

作者： Gaur, Loveleen Bhatia, Ujwal Jhanjhi, N.Z. Muhammad, Ghulam Masud, Mehedi Amity International Business School Amity University Noida India School of Computer Science and Engineering SCE Taylor’s University Subang Jaya Malaysia Research Chair of Pervasive and Mobile Computing King Saud University Riyadh11543 Saudi Arabia Computer Engineering Department College of Computer and Information Sciences King Saud University Riyadh11543 Saudi Arabia Department of Computer Science College of Computers and Information Technology Taif University P.O. Box 11099 Taif21944 Saudi Arabia

The demand for automatic detection of Novel Coronavirus or COVID-19 is increasing across the globe. The exponential rise in cases burdens healthcare facilities, and a vast amount of multimedia healthcare data is being explored to find a solution. This study presents a practical solution to detect COVID-19 from chest X-rays while distinguishing those from normal and impacted by Viral Pneumonia via Deep Convolution Neural Networks (CNN). In this study, three pre-trained CNN models (EfficientNetB0, VGG16, and InceptionV3) are evaluated through transfer learning. The rationale for selecting these specific models is their balance of accuracy and efficiency with fewer parameters suitable for mobile applications. The dataset used for the study is publicly available and compiled from different sources. This study uses deep learning techniques and performance metrics (accuracy, recall, specificity, precision, and F1 scores). The results show that the proposed approach produced a high-quality model, with an overall accuracy of 92.93%, COVID-19, a sensitivity of 94.79%. The work indicates a definite possibility to implement computer vision design to enable effective detection and screening measures. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： COVID-19

Dancing with Shackles, Meet the Challenge of Industrial Adaptive Streaming via Offline Reinforcement Learning

学校读者我要写书评

暂无评论

Dancing with Shackles, Meet the Challenge of Industrial Adap...

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Lianchen Jia Chao Zhou Tianchi Huang Chaoyang Li Lifeng Sun Department of Computer Science and Technology Tsinghua University Beijing Kuaishou Technology Co. Ltd BNRist Ministry of Education Key Laboratory of Pervasive Computing (Tsinghua University) China

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

Adaptive video streaming has been studied for over 10 years and has demonstrated remarkable performance. However, adaptive video streaming is not an independent algorithm but relies on other components of the video system. Consequently, as other components undergo optimization, the gap between the traditional simulator and the real-world system continues to grow which makes the adaptive video streaming algorithm must adapt to these *** order to address the challenges facing industrial adaptive video streaming, we introduce a novel offline reinforcement learning framework called Backwave. This framework leverages history logs to reduce the sim-real gap. We propose new metrics based on counterfactual reasoning to evaluate its performance and we integrate expert knowledge to generate valuable data to mitigate the issue of data override. Furthermore, we employ curriculum learning to minimize additional *** deployed Backwave on a mainstream commercial short video platform, Kuaishou. In a series of A/B tests conducted nearly one month with over 400M daily watch times, Backwave consistently outperforms prior algorithms. Specifically, Backwave reduces stall time by 0.45% to 8.52% while maintaining comparable video quality and Backwave demonstrates improvements in average play duration by 0.12% to 0.16%, and overall play duration by 0.12% to 0.26%.

关键词： Measurement Industries Adaptive systems Reinforcement learning Streaming media Watches Cognition

Optimizing Tandem Solar Cell Efficiency: A Perovskite-CIGS Approach 2

学校读者我要写书评

暂无评论

Optimizing Tandem Solar Cell Efficiency: A Perovskite-CIGS A...

2nd International Conference on Emerging Trends in Information Technology and Engineering, ic-ETITE 2024

作者： Chakraborty, Arpita Chakraborty, Aditya Khan, Fariba Tasnia Mahmud, Tanjim Hossain, Mohammad Shahadat Andersson, Karl Chittagong University of Engineering and Technology Dept. of Cse Chattogram4349 Bangladesh Chittagong University of Engineering and Technology Dept. of Eee Chattogram4349 Bangladesh Computer Science and Engineering Southern University Bangladesh Chattogram4201 Bangladesh Rangamati Science and Technology University Dept. of Cse Rangamati4500 Bangladesh University of Chittagong Dept. of Cse Chittagong4331 Bangladesh Luleå University of Technology Pervasive and Mobile Computing Laboratory Luleå97187 Sweden

ISBN: (纸本)9798350328202

Tandem solar cells combining perovskite and CIGS have rapidly gained prominence as highly efficient photovoltaic devices. Recent advancements in enhancing their efficiency in-volve adjusting the thickness of distinct layers with tunable bandgaps, demonstrating superior performance compared to al-ternative tandem solar cells. The upper cell, employing perovskite material chosen for its excellent light absorption coefficient and optoelectronic properties, collaborates with the bottom CIGS cell, characterized by a tunable bandgap and low thermal requirements, contributing significantly to overall efficiency improvement. Through numerical simulations conducted with wxAMPS software, our proposed model, which incorporates a 3μm thick perovskite absorber layer as the upper cell and a 3.5μm thick CIGS absorber layer as the lower cell, demonstrated outstanding power conversion efficiency of 40.0209%, Voc of 1.8675 V, Jsc of 23.2146 mA/cm2, and FF of 92.3152 © 2024 IEEE.

关键词： Perovskite

Just Speak It: Minimize Cognitive Load for Eyes-Free Text Editing with a Smart Voice Assistant 21

学校读者我要写书评

暂无评论

Just Speak It: Minimize Cognitive Load for Eyes-Free Text Ed...

34th Annual ACM Symposium on User Interface Software and Technology, UIST 2021

作者： Fan, Jiayue Xu, Chenning Yu, Chun Shi, Yuanchun Department of Computer Science and Technology Tsinghua University and Key Laboratory of Pervasive Computing Ministry of Education and Beijing Aademy of Artificial Intelligence China

ISBN: (纸本)9781450386357

Entering text precisely by voice, users might encounter colloquial inserts, inappropriate wording, and recognition errors, which brings difficulties to voice editing. Users need to locate the errors and then correct them. In eyes-free scenarios, this select-modify mode brings a cognitive burden and a risk of error. This paper introduces neural networks and pre-trained models to understand users' revision intention based on semantics, reducing the need for the information from users' statements. We present two strategies. One is to remove the colloquial inserts automatically. The other is to allow users to edit by just speaking out the target words without having to say the context and the incorrect text. Accordingly, our approach can predict whether to insert or replace, the incorrect text to replace, and the position to insert. We implement these strategies in SmartEdit, an eyes-free voice input agent controlled with earphone buttons. The evaluation shows that our techniques reduce the cognitive load and decrease the average failure rate by 54.1% compared to descriptive command or re-speaking. © 2021 ACM.

关键词： Semantics

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

computing with Smart Rings: A Systematic Literature Review

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Zeyu Yu, Ruotong Wang, Xiangyang Ding, Jiexin Tang, Jiankai Fang, Jun He, Zhe Li, Zhuojun Röddiger, Tobias Xu, Weiye Zhang, Xiyuxing Gao, Huan-Ang Gao, Nan Yu, Chun Shi, Yuanchun Wang, Yuntao Key Laboratory of Pervasive Computing Ministry of Education Department of Computer Science and Technology Tsinghua University China Tsinghua University China University of Washington United States Karlsruhe Institute of Technology Germany Intelligent Computing and Application Laboratory of Qinghai Province Qinghai University China

A smart ring is a wearable electronic device in the form of a ring that incorporates diverse sensors and computing technologies to perform a variety of functions. Designed for use with fingers, smart rings are capable of sensing more subtle and abundant hand movements, thus making them a good platform for interaction. Meanwhile, fingers are abundant with blood vessels and nerve endings and accustomed to wearing rings, providing an ideal site for continuous health monitoring through smart rings, which combine comfort with the ability to capture vital biometric data, making them suitable for all-day wear. We collected in total of 206 smart ring-related publications and conducted a systematic literature review. We provide a taxonomy regarding the sensing and feedback modalities, applications, and phenomena. We review and categorize these literatures into four main areas: (1) interaction - input, (2) interaction - output, (3) passive sensing - in body feature, (4) passive sensing - out body activity. This comprehensive review highlights the current advancements within the field of smart ring and identifies potential areas for future research. © 2025, CC BY.

关键词： Wearable computers

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