检索结果-内蒙古大学图书馆

IEEE International Conference on Multimedia and Expo (ICME)

作者： Liang He Zhida Song Shuanghong Liu Mengqi Niu Ying Hu Hao Huang School of Computer Science and Technology Xinjiang University Urumqi China School of Intelligence Science and Technology Xinjiang University Urumqi China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China Department of Electronic Engineering Tsinghua University Beijing China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

In this paper, we propose a novel loss by integrating a deep clustering (DC) loss at the frame-level and a speaker recognition loss at the segment-level into a single network without additional data requirements and exhaustive computation. The DC loss implicitly generates soft pseudo-phoneme labels for each frame-level feature, which facilitates extracting more discriminant speaker representation by suppressing phonetic content information. We study the DC loss not only on the acoustic feature, but also on the features extracted by the pre-trained models, such as wav2vec 2.0, HuBERT and WavLM. Experimental results on the VoxCeleb dataset shows that the overall system performance based on the pre-trained model features are better than the one on the acoustic feature. The proposed loss is significantly effective for systems on the acoustic feature and has a marginal improvement for systems on the pre-trained model feature.

关键词： Training Costs Computational modeling System performance Phonetics Multimedia databases Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Speaker Recognition Method Based on Stable Learning

A Speaker Recognition Method Based on Stable Learning

引用

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

作者： Jian Zhang Jing Ma Xiaochen Guo Lin Li Liang He School of Computer Science and Technology Xinjiang University China Xinjiang Key Laboratory of Signal Detection and Processing China School of Electronic Science and Engineering Xiamen University China Department of Electronic Engineering Tsinghua University China

With the development of deep learning, speaker recognition systems have shown increasingly better performance. The generalization ability of the models is also an important aspect of performance evaluation. Typically, a baseline system is used to compare against the improved models to demonstrate performance enhancements. However, we cannot determine the differences in learned voiceprint features between the improved models and the baseline system. This paper introduces an improved speaker recognition system based on the ECAPA-TDNN model. It utilizes stable learning to eliminate sample correlation and employs attribution analysis to compare the differences in voiceprint feature learning between the improved and baseline systems. Experimental results demonstrate that stable learning improves the model’s generalization performance and helps it learn better voiceprint features. The effectiveness and generalization capability of the proposed method are verified through experiments on the VoxCeleb, CNCeleb, and LibriSpeech datasets. This work is important for enhancing speaker recognition performance, analyzing differences in voiceprint feature learning, and promoting advancements in the field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

From Pixels to Insights: Image Datasets for AI/ML in Software-Defined Networking

From Pixels to Insights: Image Datasets for AI/ML in Softwar...

引用

Information technology (OCIT), OITS International Conference on

作者： Pranav Pant Rishikant Mallick Santosh Kumar Sahu Lalit Kumar Vashishtha Department of Computer Science Kalinga Institute of Industrial Technology Bhubaneswar India Geodata Processing and Interpretation Center Oil and Natural Gas Corporation Dehradun Uttarakhand

In the modern landscape of pervasive digital data, the need for robust intrusion detection systems (IDS) has become paramount to safeguard networks from malicious activities. This research explores the synergistic integration of big data analytics and AI/ML techniques, with a focus on leveraging Apache Spark as a platform for intrusion detection. The study delves into the core principles underlying intelligent IDS systems enhanced by AI, leading to heightened accuracy and adaptability in countering dynamic cyber threats. The research introduces an innovative SDN DDoS attack image dataset, refined to optimize machine learning and deep learning models for IDS. Through novel image generation methodologies, the dataset is enriched, substantially enhancing model performance. Comparative analyses are conducted, contrasting the original dataset with the refined versions, utilizing diverse learning strategies. The findings underscore the substantial advancements achieved, revealing notably improved model accuracy. The research also hints at the potential adoption of convolutional neural networks to further elevate classification capabilities, instigating prospective investigations into optimizing IDS models. This study not only contributes to the evolution of intrusion detection systems but also sheds light on the symbiotic interplay between big data analytics, AI/ML, and the realm of cybersecurity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Instruction Tuning-free Visual Token Complement for Multimodal LLMs

arXiv

引用

arXiv 2024年

作者： Wang, Dongsheng Cui, Jiequan Li, Miaoge Lin, Wang Chen, Bo Zhang, Hanwang College of Computer Science and Software Engineering Shenzhen University China School of Computer Science and Engineering Nanyang Technological University Singapore Department of Computing Hong Kong Polytechnic University Hong Kong College of Computer Science and Technology Zhejiang University China National Key Lab of Radar Signal Processing Xidian University China

As the open community of large language models (LLMs) matures, multimodal LLMs (MLLMs) have promised an elegant bridge between vision and language. However, current research is inherently constrained by challenges such as the need for high-quality instruction pairs and the loss of visual information in image-to-text training objectives. To this end, we propose a Visual Token Complement framework (VTC) that helps MLLMs regain the missing visual features and thus improve response accuracy. Specifically, our VTC integrates text-to-image generation as a guide to identifying the text-irrelevant features, and a visual selector is then developed to generate complementary visual tokens to enrich the original visual input. Moreover, an iterative strategy is further designed to extract more visual information by iteratively using the visual selector without any additional training. Notably, the training pipeline requires no additional image-text pairs, resulting in a desired instruction tuning-free property. Both qualitative and quantitative experiments demonstrate the superiority and efficiency of our VTC. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual BASIC

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

arXiv

引用

arXiv 2024年

作者： Deng, Kaijun Zheng, Dezhi Xie, Jindong Wang, Jinbao Xie, Weicheng Shen, Linlin Song, Siyang 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 Guangdong Provincial Key Laboratory of Intelligent Information Processing China Department of Computer Science University of Exeter United Kingdom

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 will be publicly available at https://***/CVI-SZU/DEGSTalk. Copyright © 2024, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Evaluation of LoRaWAN for Remote Health Monitoring: A Preliminary Study

Evaluation of LoRaWAN for Remote Health Monitoring: A Prelim...

引用

IEEE Conference on Standards for Communications and Networking (CSCN)

作者： Konstantinos Katzis Nina Evetovic Brian Cloteaux Kamran Sayrafian Dragana Bajić Department of Computer Science and Engineering European University Cyprus Nicosia Cyprus Department of Communications & Signal Processing University of Novi Sad Novi Sad Serbia Currently with the Institute of Measurement science Slovak Academy of Sciences Information Technology Laboratory National Institute of Standards & Technology Maryland USA

ISBN: (数字)9798331507428

ISBN: (纸本)9798331507435

Lack of sufficient patient monitoring data patterns and scenarios are among the challenges for accurate traffic modeling and network performance optimization when considering IoT medical devices. This paper examines how health data-traffic models can be used to investigate the capability and proper configuration of Long-Range Wide Area Networks (LoRaWAN) for remotely monitoring patients in a hospital environment or at home. For the hospital environment, it is assumed that there are two types of patients at any given time i.e., patients in the intensive care unit (ICU) or surgical wards and those located in the general medical wards. The transmission times of the health data from patients in the ICU/Surgical wards and those in general wards are randomly distributed within one and four-hour periods, respectively. For personal health monitoring devices that people use at their homes, a two-state Markov chain is used to model the generated traffic pattern. Preliminary results indicate that LoRaWAN may be used to support a significant number of nodes with sufficient reliability in both scenarios.

关键词： Wide area networks Patient monitoring Medical devices Hospitals LoRaWAN Surgery Traffic control Reliability Standards Optimization

来源：评论

学校读者我要写书评

暂无评论

Select Informative Samples for Night-Time Vehicle Detection Benchmark in Urban Scenes

引用

Remote Sensing 2023年第17期15卷 4310-4310页

作者： Wang, Xiao Tu, Xingyue Al-Hassani, Baraa Lin, Chia-Wen Xu, Xin School of Computer Science and Technology Wuhan University of Science and Technology Wuhan430081 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology Wuhan430081 China School of Computer Science Wuhan University Wuhan430081 China Department of Electrical Engineering Industrial Technology Research Institute National Tsing Hua University Hsinchu30013 Taiwan

Night-time vehicle detection plays a vital role due to the high incidence of abnormal events in our daily security field. However, existing studies mainly focus on vehicle detection in autonomous driving and traffic intersection scenes, but ignore urban scenes. There are vast differences between these scenes, such as viewpoint, position, illumination, etc. In this paper, the authors present a night-time vehicle detection dataset collected from urban scenes, named Vehicle Detection in Night-Time Urban Scene (VD-NUS). The VD-NUS dataset consists of more than 100 K challenging images, comprising a total of about 500 K labelled vehicles. This paper introduces a vehicle detection framework via an active auxiliary mechanism (AAM) to reduce the annotation workload. The proposed AAM framework can actively select the informative sample for annotation by estimating its uncertainty and locational instability. Furthermore, this paper proposes a computer-assisted detection module embedded in the AAM framework to help human annotators to rapidly and accurately label the selected data. AAM outperformed the baseline method (random sampling) by up to 0.91 AP and 3.0 MR−2 on the VD-NUS dataset. © 2023 by the authors.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

MOSMOS: Multi-organ segmentation facilitated by medical report supervision

arXiv

引用

arXiv 2024年

作者： Tian, Weiwei Huang, Xinyu Hou, Junlin Ren, Caiyue Jiang, Longquan Zhao, Rui-Wei Jin, Gang Zhang, Yuejie Geng, Daoying Academy for Engineering and Technology Fudan University Shanghai200433 China School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai200433 China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China Shanghai200433 China Department of Computer Science and Engineering The Hong Kong University of Science and Technology China

Owing to a large amount of multi-modal data in modern medical systems, such as medical images and reports, Medical Vision-Language Pre-training (Med-VLP) has demonstrated incredible achievements in coarse-grained downstream tasks (i.e., medical classification, retrieval, and visual question answering). However, the problem of transferring knowledge learned from Med-VLP to fine-grained multi-organ segmentation tasks has barely been investigated. Multi-organ segmentation is challenging mainly due to the lack of large-scale fully annotated datasets and the wide variation in the shape and size of the same organ between individuals with different diseases. In this paper, we propose a novel pre-training & fine-tuning framework for Multi-Organ Segmentation by harnessing Medical repOrt Supervision (MOSMOS). Specifically, we first introduce global contrastive learning to maximally align the medical image-report pairs in the pre-training stage. To remedy the granularity discrepancy, we further leverage multi-label recognition to implicitly learn the semantic correspondence between image pixels and organ tags. More importantly, our pre-trained models can be transferred to any segmentation model by introducing the pixel-tag attention maps. Different network settings, i.e., 2D U-Net and 3D UNETR, are utilized to validate the generalization. We have extensively evaluated our approach using different diseases and modalities on BTCV, AMOS, MMWHS, and BRATS datasets. Experimental results in various settings demonstrate the effectiveness of our framework. This framework can serve as the foundation to facilitate future research on automatic annotation tasks under the supervision of medical reports. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Multi-View Speaker Embedding Learning for Enhanced Stability and Discriminability

Multi-View Speaker Embedding Learning for Enhanced Stability...

引用

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

作者： Liang He Zhihua Fang Zuoer Chen Minqiang Xu Ying Meng Penghao Wang School of Computer Science and Technology Xinjiang University Urumqi China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China Department of Electronic Engineering Tsinghua University Beijing China iFly Digital Technology Hefei China

Deep neural network models based on x-vector have become the most popular framework for speaker recognition, and the quality of speaker features (embeddings) is important for open-set tasks such as speaker verification and speaker diarization. Currently, the most popular loss function is based on margin penalty, however, it only considers enlarging the inter-class distance while neglecting to reduce the intra-class feature differences. Therefore, we propose a multi-view learning approach that divides the training process into two views from the speaker embedding level. The classification view focuses on distinguishing the discriminability of different speakers, while the clustering view focuses on shrinking the feature boundaries of the same speaker, making intra-class differences smaller. The combined effect of the two perspectives achieves large inter-class distance and small intra-class distances, resulting in the extraction of more discriminative and stable speaker embeddings. We test the performance of the method on both speaker verification and speaker diarization tasks, and the results demonstrate the effectiveness of our approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the Generalization of Machine-Learning-aided QoT Estimation in Optical Networks 32

On the Generalization of Machine-Learning-aided QoT Estimati...

引用

32nd Wireless and Optical Communications Conference, WOCC 2023

作者： Gao, Hanyu Zhang, Liang Zhang, Bin Chen, Xiaoliang Li, Zhaohui School of Electronics and Information Technology Sun Yat-sen University Guangdong Provincial Key Labratory of Optoelectronic Information Processing Chips and Systems Guangzhou China Southern Marine Science and Engineering Guangdong Laboratory Zhuhai China George Mason University Department of Electrical and Computer Engineering FairfaxVA22030 United States

ISBN: (纸本)9798350337150

This paper presents a composable machine learning method for generalizing the quality-of-transmission (QoT) metric estimation in optical networks. The composable machine learning approach characterizes this metric for lightpaths of arbitrary lengths by compositions of launch, propagation and readout modules. Results verify the feasibility of the design and show its successful application in facilitating autonomous lightpath provisioning. © 2023 IEEE.

关键词： Fiber optic 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：