检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Cai, Ziqi Jiang, Kaiwen Chen, Shu-Yu Lai, Yu-Kun Fu, Hongbo Shi, Boxin Gao, Lin Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences China Beijing Jiaotong University China University of California San Diego United States Cardiff University United Kingdom City University of Hong Kong Hong Kong The Hong Kong University of Science and Technology Hong Kong University of Chinese Academy of Sciences China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China National Engineering Research Center of Visual Technology School of Computer Science Peking University China

Synthesizing realistic videos of talking faces under custom lighting conditions and viewing angles benefits various downstream applications like video conferencing. However, most existing relighting methods are either time-consuming or unable to adjust the viewpoints. In this paper, we present the first real-time 3D-aware method for relighting in-the-wild videos of talking faces based on Neural Radiance Fields (NeRF). Given an input portrait video, our method can synthesize talking faces under both novel views and novel lighting conditions with a photo-realistic and disentangled 3D representation. Specifically, we infer an albedo tri-plane, as well as a shading tri-plane based on a desired lighting condition for each video frame with fast dual-encoders. We also leverage a temporal consistency network to ensure smooth transitions and reduce flickering artifacts. Our method runs at 32.98 fps on consumer-level hardware and achieves state-of-the-art results in terms of reconstruction quality, lighting error, lighting instability, temporal consistency and inference speed. We demonstrate the effectiveness and interactivity of our method on various portrait videos with diverse lighting and viewing conditions. Copyright © 2024, The Authors. All rights reserved.

关键词： Video conferencing

来源：评论

学校读者我要写书评

暂无评论

Adversarial Testing: A Novel On-Line Testing Method for Deep Learning Processors

Adversarial Testing: A Novel On-Line Testing Method for Deep...

引用

Asian Test Symposium (ATS)

作者： Wen Li Ying Wang Kaiwei Zou Huawei Li Xiaowei Li School of Computer and Information Technology Shanxi University Taiyuan Shanxi China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Taiyuan Shanxi China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Department of Electronic Engineering Tsinghua University Beijing China

Deep neural networks have shown outstanding performance on complex tasks. Recently, various researches have been developed to pursue fast and energy-efficient deep learning accelerators. However, devices may suffer from hard defects and hardware variability during its lifetime, which poses severe challenges to deep learning accelerators. To protect edge deep learning accelerators from fault-induced failures, we leverage the adversarial deep learning technique to tailor a lightweight online fault detection method for neural network accelerator chips. The proposed Adversarial Testing scheme (AT) is a function-level testing method outcompeting conventional test in several ways: negligible run-time overhead, super sensitivity to subtle hardware variations, which reduces chip over-kills and also the unnecessary diagnosis operations. The evaluation results show that AT can accurately detect fault occurrence and ensure the normal use of deep learning accelerator during its lifetime.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Q-Space Sampling Optimization and Reconstruction for Fast and High-Fidelity Diffusion Magnetic Resonance Imaging

Simultaneous Q-Space Sampling Optimization and Reconstructio...

引用

IEEE International Symposium on Biomedical Imaging

作者： Jing Yang Jian Cheng Cheng Li Wenxin Fan Juan Zou Ruoyou Wu Qiegen Liu Hairong Zheng Shanshan Wang Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China University of Chinese Academy of Sciences Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing China Key Laboratory of Data Science and Intelligent Computing Institute of International Innovation Beihang University Hangzhou China Department of Electronic Information Engineering Nanchang University Nanchang China

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Diffusion Magnetic Resonance Imaging (dMRI) plays a crucial role in the noninvasive investigation of tissue microstructural properties and structural connectivity in the in vivo human brain. However, to effectively capture the intricate characteristics of water diffusion at various directions and scales, it is important to employ comprehensive q-space sampling. Unfortunately, this requirement leads to long scan times, limiting the clinical applicability of dMRI. To address this challenge, we propose SSOR, a Simultaneous q-Space sampling Optimization and Reconstruction framework. We jointly optimize a subset of q-space samples using a continuous representation of spherical harmonic functions and a reconstruction network. Additionally, we integrate the unique properties of diffusion magnetic resonance imaging (dMRI) in both the q-space and image domains by applying l1-norm and total-variation *** experiments conducted on HCP data demonstrate that SSOR has promising strengths both quantitatively and qualitatively and exhibits robustness to noise.

关键词： Water In vivo Limiting Magnetic resonance imaging Harmonic analysis Robustness Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Look one step ahead through first-order aggregation in reinforcement learning-based knowledge graph reasoning

引用

information Sciences 2025年 718卷

作者： Wang, Hao Song, Dandan Wu, Zhijing Tian, YuHang Xu, Jing Laboratory of High-Volume Language Information Processing and Cloud Computing Beijing Lab of Intelligent Information Technology School of Computer Science and Technology Beijing Institute of Technology Beijing Beijing100081 China

Multi-hop reasoning is an effective and interpretable approach for query answering, as it finds reasoning paths over knowledge graphs (KGs) to enhance interpretability. Recent studies have applied reinforcement learning-based (RL-based) methods with policy agents to solve this problem. However, these methods primarily focus on sequential reasoning paths and candidate nodes, while overlooking the local structural information of adjacency subgraphs and the semantic correlations between relations at each decision step. In this paper, we propose a novel RL-based multi-hop reasoning model, Look One Step Ahead (LOSA), which leverages first-order aggregation to regard more expressive adjacency subgraphs rather than nodes as candidate actions and pays attention to the semantic correlations between relations. Specifically, an adjacency aggregation module encodes the local subgraph information and feeds the representations into the policy network to guide decision-making, thereby reducing backtracking and mitigating sparse-reward issues. Furthermore, a semantic matching module is designed to emphasize the semantic correlations of relations to improve the rationality of the reasoning paths. Extensive experiments on benchmark datasets demonstrate the effectiveness of the proposed approach. © 2025

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Diverse and High-Quality Food Image Generation from Only Food Names

引用

ACM Transactions on Multimedia computing, Communications and Applications 2025年第5期21卷

作者： Yu, Dongjian Min, Weiqing Jin, Xin Jiang, Qian Jin, Ying Jiang, Shuqiang School of Software Yunnan University Kunming China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China

Food image generation holds promising application prospects in food design, advertising, and food education. However, the existing methods rely on information such as recipes, ingredients, or food names, which leads to generated food images with less intra-class diversity. When recipes, ingredients, and food names are identical for the same food, the real-world images may vary significantly in appearance. The question of how to simultaneously ensure the quality and diversity of the generated images is a key issue. To this end, we employ pre-trained diffusion model and Transformer to propose a method for generating diverse and high-quality images of both Chinese and Western food, named CW-Food. Different from previous works that utilize an overall food feature to generate new images, CW-Food first decouples the food images to obtain common intra-class features and private instance features. Additionally, we design a Transformer-based feature fusion module to integrate the common and private features, in order to avoid the shortcomings of conventional methods. Moreover, we also utilize a pre-trained diffusion model as our backbone, which is fine-tuned using LoRA with the fused multi-variate features. Extensive experiments on four datasets demonstrate the advantages of our proposed method, producing diverse and high-quality food images encompassing both Chinese and Western cuisines. To the best of our knowledge, our work is the first attempt to generate Chinese food images using only food names. © 2025 Copyright held by the owner/author(s).

关键词： Food ingredients

来源：评论

学校读者我要写书评

暂无评论

High information Density and Low Coverage Data Storage in DNA with Efficient Channel Coding Schemes

arXiv

引用

arXiv 2024年

作者： Ding, Yi He, Xuan Nguyen, Tuan Thanh Song, Wentu Yakhini, Zohar Yaakobi, Eitan Pan, Linqiang Tang, Xiaohu Cai, Kui Information Coding and Transmission Key Lab of Sichuan Province Southwest Jiaotong University Sichuan Chengdu611756 China Cluster Singapore University of Technology and Design 487372 Singapore Faculty of Computer Science Technion - Israel Institute of Technology Haifa3200003 Israel School of Computer Science RUNI Herzliya4615200 Israel Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan430074 China

DNA-based data storage has been attracting significant attention due to its extremely high data storage density, low power consumption, and long duration compared to conventional data storage media. Despite the recent advancements in DNA data storage technology, significant challenges remain. In particular, various types of errors can occur during the processes of DNA synthesis, storage, and sequencing, including substitution errors, insertion errors, and deletion errors. Furthermore, the entire oligo may be lost. In this work, we report a DNA-based data storage architecture that incorporates efficient channel coding schemes, including different types of error-correcting codes (ECCs) and constrained codes, for both the inner coding and outer coding for the DNA data storage channel. We also carried out large scale experiments to validate our proposed DNA-based data storage architecture. Specifically, 1.61 and 1.69 MB data were encoded into 30,000 oligos each, with information densities of 1.731 and 1.815, respectively. It has been found that the stored information can be fully recovered without any error at average coverages of 4.5 and 6.0, respectively. This experiment achieved the highest net information density and lowest coverage among existing DNA-based data storage experiments (with standard DNA), with data recovery rates and coverage approaching theoretical optima. Copyright © 2024, The Authors. All rights reserved.

关键词： Channel coding

来源：评论

学校读者我要写书评

暂无评论

Industrial Semantic Communications for Tool Wear Monitoring in Industrial IoT Networks

Industrial Semantic Communications for Tool Wear Monitoring ...

引用

IEEE International Conference on Communications in China Workshops (ICCC)

作者： Mingqiang Zhang Yajuan Yang Baokun Song Zexin Chen Xiaocong Ma Dongyang Li Na Li Feng Cao Yanping Zhang Haixia Zhang School of Cyber Science and Engineering Qufu Normal University Qufu China College of Oceanography and Space Informatics China University of Petroleum (East China) Huangdao China School of Intelligent Manufacturing and Control Engineering Qilu Institute of Technology Jinan China School of Computer and Information Engineering Qilu Institute of Technology Jinan China School of Control Science and Engineering Shandong University Jinan China Shandong Key Laboratory of Intelligent Communication and Sensing-Computing Integration Shandong University Jinan China

ISBN: (数字)9798350377675

ISBN: (纸本)9798350377682

In this paper, we propose an Industrial Semantic Communications (ISC) framework to ensure efficient and in-telligent communication in Industrial Internet-of-Things (IIoT) networks, and further apply the proposed framework to the task of tool wear monitoring. A semantic-aware tool wear monitoring network (TWM-Net) is designed to accurately identify the idling state from tool wear data, thus assisting the semantic data transmission process of the ISC framework. Then, a demo software system is implemented to verify the delay performance of the proposed ISC framework. Experimental results demonstrated that the proposed ISC framework can facilitate the semantic information exchange between edge industrial system and cloud platform together with the deep compressed sensing method, and significantly reduce the amount of data transmissions in IIoT networks. The source code and dataset is available through https://***/pnixsoft/TWM-Net.

关键词： Vibrations Source coding Software systems Multitasking Delays Data communication Monitoring information exchange Industrial Internet of Things Testing

来源：评论

学校读者我要写书评

暂无评论

Temporal information Reconstruction and Non-Aligned Residual in Spiking Neural Networks for Speech Classification

arXiv

引用

arXiv 2024年

作者： Zhang, Qi Wang, Huamin Shen, Hangchi Duan, Shukai Wen, Shiping Huang, Tingwen College of Artificial Intelligence Southwest University Chongqing400715 China Chongqing Key Laboratory of Brain Inspired Computing and Intelligent Chips Chongqing400715 China College of Information Engineering University of Technology Sydney Australian Institute of Artificial Intelligence Sydney2007 Australia Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen518055 China

Recently, it can be noticed that most models based on spiking neural networks (SNNs) only use a same level temporal resolution to deal with speech classification problems, which makes these models cannot learn the information of input data at different temporal scales. Additionally, owing to the different time lengths of the data before and after the sub-modules of many models, the effective residual connections cannot be applied to optimize the training processes of these models. To solve these problems, on the one hand, we reconstruct the temporal dimension of the audio spectrum to propose a novel method named as Temporal Reconstruction (TR) by referring the hierarchical processing process of the human brain for understanding speech. Then, the reconstructed SNN model with TR can learn the information of input data at different temporal scales and model more comprehensive semantic information from audio data because it enables the networks to learn the information of input data at different temporal resolutions. On the other hand, we propose the Non-Aligned Residual (NAR) method by analyzing the audio data, which allows the residual connection can be used in two audio data with different time lengths. We have conducted plentiful experiments on the Spiking Speech Commands (SSC), the Spiking Heidelberg Digits (SHD), and the Google Speech Commands v0.02 (GSC) datasets. According to the experiment results, we have achieved the state-of-the-art (SOTA) result 81.02% on SSC for the test classification accuracy of all SNN models, and we have obtained the SOTA result 96.04% on SHD for the classification accuracy of all models. Furthermore, on the non-spiking dataset GSC, we can achieve a test classification accuracy of 95.63%, which surpasses the original baseline SNN-Delays. Meanwhile, the method proposed in this paper can speed up the model’s processing speed and reduce its energy consumption. Copyright © 2024, The Authors. All rights reserved.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Disentangled Generation Network for Enlarged License Plate Recognition and A Unified Dataset

arXiv

引用

arXiv 2022年

作者： Li, Chenglong Yang, Xiaobin Wang, Guohao Zheng, Aihua Tan, Chang Jia, Ruoran Tang, Jin Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Key Lab of Intelligent Computing and Signal Processing Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China iFLYTEK Co. Ltd. Hefei230088 China

License plate recognition plays a critical role in many practical applications, but license plates of large vehicles are difficult to be recognized due to the factors of low resolution, contamination, low illumination, and occlusion, to name a few. To overcome the above factors, the transportation management department generally introduces the enlarged license plate behind the rear of a vehicle. However, enlarged license plates have high diversity as they are non-standard in position, size, and style. Furthermore, the background regions contain a variety of noisy information which greatly disturbs the recognition of license plate characters. Existing works have not studied this challenging problem. In this work, we first address the enlarged license plate recognition problem and contribute a dataset containing 9342 images, which cover most of the challenges of real scenes. However, the created data are still insufficient to train deep methods of enlarged license plate recognition, and building large-scale training data is very time-consuming and high labor cost. To handle this problem, we propose a novel task-level disentanglement generation framework based on the Disentangled Generation Network (DGNet), which disentangles the generation into the text generation and background generation in an end-to-end manner to effectively ensure diversity and integrity, for robust enlarged license plate recognition. Extensive experiments on the created dataset are conducted, and we demonstrate the effectiveness of the proposed approach in three representative text recognition frameworks. © 2022, CC BY.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

A Survey on Deep Learning for Polyp Segmentation: Techniques, Challenges and Future Trends

arXiv

引用

arXiv 2023年

作者： Mei, Jiaxin Zhou, Tao Huang, Kaiwen Zhang, Yizhe Zhou, Yi Wu, Ye Fu, Huazhu Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Computer Science and Engineering Southeast University Nanjing China Institute of High Performance Computing A*STAR Singapore

Early detection and assessment of polyps play a crucial role in the prevention and treatment of colorectal cancer (CRC). Polyp segmentation provides an effective solution to assist clinicians in accurately locating and segmenting polyp regions. In the past, people often relied on manually extracted lower-level features such as color, texture, and shape, which often had problems capturing global context and lacked robustness to complex scenarios. With the advent of deep learning, more and more medical image segmentation algorithms based on deep learning networks have emerged, making significant progress in the field. This paper provides a comprehensive review of polyp segmentation algorithms. We first review some traditional algorithms based on manually extracted features and deep segmentation algorithms, and then describe benchmark datasets related to the topic. Specifically, we carry out a comprehensive evaluation of recent deep learning models and results based on polyp size, taking into account the focus of research topics and differences in network structures. Finally, we discuss the challenges of polyp segmentation and future trends in the field. Copyright © 2023, The Authors. All rights reserved.

关键词： Medical imaging

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：