检索结果-内蒙古大学图书馆

Temporal and Spatial Perception: A Novel Perceptual Rate-Distortion Optimization Method for H.266/VVC Encoding

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Ai, Da Wang, Jiahao He, Ting Yuan, Hui Liu, Ying Ling, Nam Xi'an University of Posts and Telecommunications Center for Image and Information Processing School of Communications and Information Engineering Xi'an710121 China Shandong University School of Control Science and Engineering Jinan250061 China Shandong University Shenzhen-Research Institute Shenzhen518057 China Santa Clara University Department of Computer Science and Engineering Santa ClaraCA95053 United States

Introducing saliency information to mitigate perceptual redundancy and achieve superior compression represents a novel approach to the development of video compression. Existing saliency-based compression coding methods rely on the determination of saliency regions and focus too much on saliency regions while ignoring the perceptible distortion in non-saliency regions. We propose a spatiotemporal visual perceptual rate-distortion optimization (PRDO) algorithm for Versatile Video Coding (H.266/VVC) that is more in line with the human visual system (HVS). Firstly, we establish a linear weighted distortion model based on spatiotemporal and saliency features. The distortion model makes effective use of saliency features while considering image content in non-saliency regions that is still perceptible to the human eye, thereby achieving an overall visual effect that conforms to human subjective perception. Based on this distortion model, we propose a saliency adaptive quantization parameter (SAQP) selection method with a more flexible quantization parameter selection range, adaptively allocating the optimal coding unit quantization parameter according to the saliency regions of the image, ensuring a balanced bitrate allocation between saliency and non-saliency regions. The proposed method is implemented for the first time on the H.266/VVC coding standard, attaining an average bitrate saving of 19.9% across all test sequences and an average PSNR improvement of 2.65 dB in saliency regions compared to VTM16.0. The BD-EWPSNR of the proposed PRDO and SAQP method improves by 1.34 dB and 1.45 dB in the All-Intra and Lowdelay-P encoding modes, respectively. Additionally, the BD-Rate based on EWPSNR is reduced by 25.86% and 33.73%, respectively, with an overall compression coding time saving of 19.76%. The experimental results demonstrate that the proposed method can significantly reduce the bit rate and coding time while improving the subjective perceptive quality, providing a c

关键词： Signal distortion

来源：评论

学校读者我要写书评

暂无评论

Deep Pyramidal Residual Network for Indoor-Outdoor Activity Recognition Based on Wearable Sensor

引用

Intelligent Automation & Soft Computing 2023年第9期37卷 2669-2686页

作者： Sakorn Mekruksavanich Narit Hnoohom Anuchit Jitpattanakul Department of Computer Engineering School of Information and Communication Technology University of PhayaoPhayao56000Thailand Image Information and Intelligence Laboratory Department of Computer EngineeringFaculty of EngineeringMahidol UniversityNakhon Pathom73170Thailand Department of Mathematics Faculty of Applied ScienceKing Mongkut’s University of Technology North BangkokBangkok10800Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Science and Technology Research Institute King Mongkut’s University of Technology North BangkokBangkok10800Thailand

Recognition of human activity is one of the most exciting aspects of time-series classification,with substantial practical and theoretical *** evidence indicates that activity recognition from wearable sensors is an effective technique for tracking elderly adults and children in indoor and outdoor ***,researchers have demon-strated considerable passion for developing cutting-edge deep learning sys-tems capable of exploiting unprocessed sensor data from wearable devices and generating practical decision assistance in many *** study provides a deep learning-based approach for recognizing indoor and outdoor movement utilizing an enhanced deep pyramidal residual model called Sen-PyramidNet and motion information from wearable sensors(accelerometer and gyroscope).The suggested technique develops a residual unit based on a deep pyramidal residual network and introduces the concept of a pyramidal residual unit to increase detection *** proposed deep learning-based model was assessed using the publicly available 19Nonsens dataset,which gathered motion signals from various indoor and outdoor activities,including practicing various body *** experimental findings demon-strate that the proposed approach can efficiently reuse characteristics and has achieved an identification accuracy of 96.37%for indoor and 97.25%for outdoor ***,comparison experiments demonstrate that the SenPyramidNet surpasses other cutting-edge deep learning models in terms of accuracy and ***,this study explores the influence of several wearable sensors on indoor and outdoor action recognition ability.

关键词： Human activity recognition deep learning wearable sensors indoor and outdoor activity deep pyramidal residual network

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Reassessment of Large-Scale Evaluation Outcomes in LLMs: A Multifaceted Statistical Approach

arXiv

引用

arXiv 2024年

作者： Sun, Kun Wang, Rong Søgaard, Anders Department of Linguistics University of Tübingen Germany Institute of Natural Language Processing Stuttgart University Stuttgart Germany Department of Computer Science University of Copenhagen Copenhagen Denmark

Amidst the rapid evolution of LLMs, the significance of evaluation in comprehending and propelling these models forward is increasingly paramount. Evaluations have revealed that factors such as scaling, training types, architectures and other factors profoundly impact the performance of LLMs. However, the extent and nature of these impacts continue to be subjects of debate because most assessments have been restricted to a limited number of models and data points. Clarifying the effects of these factors on performance scores can be more effectively achieved through a statistical lens. Our study embarks on a thorough re-examination of these LLMs, targeting the inadequacies in current evaluation methods. With the advent of a uniform evaluation framework, our research leverages an expansive dataset of evaluation results, introducing a comprehensive statistical methodology. This includes the application of ANOVA, Tukey HSD tests, GAMM, and clustering technique, offering a robust and transparent approach to deciphering LLM performance data. Contrary to prevailing findings, our results challenge assumptions about emergent abilities and the influence of given training types and architectures in LLMs. These findings furnish new perspectives on the characteristics, intrinsic nature, and developmental trajectories of LLMs. By providing straightforward and reliable methods to scrutinize and reassess LLM performance data, this study contributes a nuanced perspective on LLM efficiency and potentials. © 2024, CC BY-NC-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Driving Activity Classification Using Deep Residual Networks Based on Smart Glasses Sensors

引用

Intelligent Automation & Soft Computing 2023年第11期38卷 139-151页

作者： Narit Hnoohom Sakorn Mekruksavanich Anuchit Jitpattanakul Department of Computer Engineering Image Information and Intelligence LaboratoryFaculty of EngineeringMahidol UniversityNakhon Pathom73170Thailand Department of Computer Engineering School of Information and Communication TechnologyUniversity of PhayaoPhayaoThailand Department of Mathematics Faculty of Applied ScienceKing Mongkut’s University of Technology North BangkokBangkok10800Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Science and Technology Research InstituteKing Mongkut’s University of Technology North BangkokBangkok10800Thailand

Accidents are still an issue in an intelligent transportation system,despite developments in self-driving technology(ITS).Drivers who engage in risky behavior account for more than half of all road *** a result,reckless driving behaviour can cause congestion and *** vision and multimodal sensors have been used to study driving behaviour categorization to lessen this *** research has also collected and analyzed a wide range of data,including electroencephalography(EEG),electrooculography(EOG),and photographs of the driver’s *** the other hand,driving a car is a complicated action that requires a wide range of body *** this work,we proposed a ResNet-SE model,an efﬁcient deep learning classiﬁer for driving activity clas-siﬁcation based on signal data obtained in real-world trafﬁc conditions using smart ***-to-end learning can be achieved by combining residual networks and channel attention approaches into a single learning *** data from 3-point EOG electrodes,tri-axial accelerometer,and tri-axial gyroscope from the Smart Glasses dataset was utilized in this *** performed various experiments and compared the proposed model to base-line deep learning algorithms(CNNs and LSTMs)to demonstrate its *** to the research results,the proposed model outperforms the previous deep learning models in this domain with an accuracy of 99.17%and an F1-score of 98.96%.

关键词： Smart glasses human activity recognition deep learning wearable sensors driving activity

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

Radiologist-in-the-Loop Self-Training for Generalizable CT Metal Artifact Reduction

引用

IEEE Transactions on Medical Imaging 2025年第6期44卷 2504-2514页

作者： Ma, Chenglong Li, Zilong Li, Yuanlin Han, Jing Zhang, Junping Zhang, Yi Liu, Jiannan Shan, Hongming Fudan University Institute of Science and Technology for Brain-inspired Intelligence Moe Frontiers Center for Brain Science Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Shanghai200433 China Fudan University Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Shanghai200433 China Shanghai Ninth People's Hospital Department of Oral Maxillofacial Head and Neck Oncology China Shanghai Jiao Tong University School of Medicine College of Stomatology China Shanghai Key Laboratory of Stomatology Shanghai Research Institute of Stomatology National Center for Stomatology National Clinical Research Center for Oral Diseases Shanghai200011 China Sichuan University School of Cyber Science and Engineering Chengdu Sichuan610065 China

Metal artifacts in computed tomography (CT) images can significantly degrade image quality and impede accurate diagnosis. Supervised metal artifact reduction (MAR) methods, trained using simulated datasets, often struggle to perform well on real clinical CT images due to a substantial domain gap. Although state-of-the-art semi-supervised methods use pseudo ground-truths generated by a prior network to mitigate this issue, their reliance on a fixed prior limits both the quality and quantity of these pseudo ground-truths, introducing confirmation bias and reducing clinical applicability. To address these limitations, we propose a novel radiologist-in-the-loop self-training framework for MAR, termed RISE-MAR, which can integrate radiologists' feedback into the semi-supervised learning process, progressively improving the quality and quantity of pseudo ground-truths for enhanced generalization on real clinical CT images. For quality assurance, we introduce a clinical quality assessor model that emulates radiologist evaluations, effectively selecting high-quality pseudo ground-truths for semi-supervised training. For quantity assurance, our self-training framework iteratively generates additional high-quality pseudo groundtruths, expanding the clinical dataset and further improving model generalization. Extensive experimental results on multiple clinical datasets demonstrate the superior generalization performance of our RISE-MAR over state-of-the-art methods, advancing the development of MAR models for practical application. © 2025 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

QMix: Quality-aware Learning with Mixed Noise for Robust Retinal Disease Diagnosis

引用

IEEE Transactions on Medical Imaging 2025年 PP卷 PP页

作者： Hou, Junlin Xu, Jilan Feng, Rui Chen, Hao Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong Fudan University School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai China HKUST Department of Chemical and Biological Engineering Division of Life Science Hong Kong HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute Shenzhen China

Due to the complex nature of medical image acquisition and annotation, medical datasets inevitably contain noise. This adversely affects the robustness and generalization of deep neural networks. Previous noise learning methods mainly considered noise arising from images being mislabeled, i.e., label noise, assuming all mislabeled images were of high quality. However, medical images can also suffer from severe data quality issues, i.e., data noise, where discriminative visual features for disease diagnosis are missing. In this paper, we propose QMix, a noise learning framework that learns a robust disease diagnosis model under mixed noise scenarios. QMix alternates between sample separation and quality-aware semisupervised training in each epoch. The sample separation phase uses a joint uncertainty-loss criterion to effectively separate (1) correctly labeled images, (2) mislabeled high-quality images, and (3) mislabeled low-quality images. The semi-supervised training phase then learns a robust disease diagnosis model from the separated samples. Specifically, we propose a sample-reweighing loss to mitigate the effect of mislabeled low-quality images during training, and a contrastive enhancement loss to further distinguish them from correctly labeled images. QMix achieved state-of-the-art performance on six public retinal image datasets and exhibited significant improvements in robustness against mixed noise. © 1982-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Management of Scientific Agricultural Digital Ecosystems Based on Ecosystem Classification 16

Management of Scientific Agricultural Digital Ecosystems Bas...

引用

16th International Conference Management of Large-Scale System Development, MLSD 2023

作者： Kulba, Vladimir Medennikov, Viktor V.A. Trapeznikov Institute of Control Sciences of the Russian Academy of Sciences Laboratory of Modular Data Processing and Control Systems Moscow Russia Federal Research Center 'Computer Science and Control' of the Russian Academy of Sciences Information and Computing Systems Department Moscow Russia

ISBN: (纸本)9798350337907

The paper considers a mathematical model for managing a scientific digital ecosystem exemplified by the agriculture case;the model enables assessing the impact science exerts on the regions' socioeconomic position in order to build an adequate response to the advanced economies' regime of severe sanctions against Russia. For these purposes, a systemic analysis of the subject identification and classification of ecosystems was conducted to address the critical issue of determining the basic concepts and terms of the country's digitalization. © 2023 IEEE.

关键词： Agriculture

来源：评论

学校读者我要写书评

暂无评论

Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells

Constraining Depth Map Geometry for Multi-View Stereo: A Dua...

引用

International Conference on computer Vision (ICCV)

作者： Xinyi Ye Weiyue Zhao Tianqi Liu Zihao Huang Zhiguo Cao Xin Li Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Department of Computer Science University of Albany Albany NY

Learning-based multi-view stereo (MVS) methods deal with predicting accurate depth maps to achieve an accurate and complete 3D representation. Despite the excellent performance, existing methods ignore the fact that a suitable depth geometry is also critical in MVS. In this paper, we demonstrate that different depth geometries have significant performance gaps, even using the same depth prediction error. Therefore, we introduce an ideal depth geometry composed of Saddle-Shaped Cells, whose predicted depth map oscillates upward and downward around the ground-truth surface, rather than maintaining a continuous and smooth depth plane. To achieve it, we develop a coarse-to-fine framework called Dual-MVSNet (DMVSNet), which can produce an oscillating depth plane. Technically, we predict two depth values for each pixel (Dual-Depth), and propose a novel loss function and a checkerboard-shaped selecting strategy to constrain the predicted depth geometry. Compared to existing methods, DMVSNet achieves a high rank on the DTU benchmark and obtains the top performance on challenging scenes of Tanks and Temples, demonstrating its strong performance and generalization ability. Our method also points to a new research direction for considering depth geometry in MVS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks based Skin Lesion Segmentation

arXiv

引用

arXiv 2023年

作者： Innani, Shubham Dutande, Prasad Baid, Ujjwal Pokuri, Venu Bakas, Spyridon Talbar, Sanjay Baheti, Bhakti Guntuku, Sharath Chandra Center of Excellence in Signal and Image Processing Shri Guru Gobind Singhji Institute of Engineering and Technology Maharashtra Nanded India Center for Biomedical Image Computing and Analytics University of Pennsylvania Philadelphia United States Department of Computer and Information Science University of Pennsylvania Philadelphia United States

Skin cancer is a serious condition that requires accurate diagnosis and treatment. One way to assist clinicians in this task is using computer-aided diagnosis (CAD) tools that automatically segment skin lesions from dermoscopic images. We propose a novel adversarial learning-based framework called Efficient-GAN (EGAN) that uses an unsupervised generative network to generate accurate lesion masks. It consists of a generator module with a top-down squeeze excitation-based compound scaled path, an asymmetric lateral connection-based bottom-up path, and a discriminator module that distinguishes between original and synthetic masks. A morphology-based smoothing loss is also implemented to encourage the network to create smooth semantic boundaries of lesions. The framework is evaluated on the International Skin Imaging Collaboration (ISIC) Lesion Dataset 2018. It outperforms the current state-of-the-art skin lesion segmentation approaches with a Dice coefficient, Jaccard similarity, and Accuracy of 90.1%, 83.6%, and 94.5%, respectively. We also design a lightweight segmentation framework (MGAN) that achieves comparable performance as EGAN but with an order of magnitude lower number of training parameters, thus resulting in faster inference times for low compute resource settings. Copyright © 2023, The Authors. All rights reserved.

关键词： Generative adversarial networks

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：