检索结果-内蒙古大学图书馆

18th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2021

作者： Luo, Chao Bi, Sheng Dong, Min Nie, Hongxu School of Computer Science and Engineering South China University of Technology Guangdong Guangzhou510006 China Key Laboratory of Big Data and Intelligent Robot Ministry of Education Guangdong Guangzhou510006 China

ISBN: (纸本)9783030893699

Target-driven visual navigation without mapping works to solve navigation problems that given a target object, mobile robots can navigate to the target object. Recently, visual navigation has been researched and improved largely by learning-based methods. However, their methods lack depth information and spatial perception, using only single RGB images. To overcome these problems, two methods are presented in this paper. Firstly, we encode visual features of objects by dynamic graph convolutional network and extract 3D spatial features for objects by 3D geometry, a high level visual feature for agent to easily understand object relationship. Secondly, as human beings, they solve this problem in two steps, first exploring a new environment to find the target object and second planning a path to arrive. Inspired by the way of humans navigation, we propose direction estimation module (DEM) based on RGB-D images. DEM provides direction estimation of the target object to our learning model by a wheel odometry. Given a target object, first stage, our agent explores an unseen scene to detect the target object. Second stage, when detected the target object, we can estimate current location of the target object by 3D geometry, after that, each step of the agent, DEM will estimate new location of target object, and give direction information of the target object from a first-view image. It can guide our agent to navigate to the target object. Our experiment results outperforms the result of state of the art method in the artificial environment AI2-Thor. © 2021, Springer Nature Switzerland AG.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Improve Cross-domain Mixed Sampling with Guidance Training for Adaptive Segmentation

arXiv

引用

arXiv 2024年

作者： Zhou, Wenlve Zhou, Zhiheng Wang, Tianlei Zeng, Delu School of Electronic and Information Engineering South China University of Technology Guangdong Guangzhou510641 China Key Laboratory of Big Data and Intelligent Robot Ministry of Education South China University of Technology Guangzhou510641 China The Department of Intelligent Manufacturing Wuyi University Jiangmen529020 China

Unsupervised Domain Adaptation (UDA) endeavors to adjust models trained on a source domain to perform well on a target domain without requiring additional annotations. In the context of domain adaptive semantic segmentation, which tackles UDA for dense prediction, the goal is to circumvent the need for costly pixel-level annotations. Typically, various prevailing methods baseline rely on constructing intermediate domains via cross-domain mixed sampling techniques to mitigate the performance decline caused by domain gaps. However, such approaches generate synthetic data that diverge from real-world distributions, potentially leading the model astray from the true target distribution. To address this challenge, we propose a novel auxiliary task called Guidance Training. This task facilitates the effective utilization of cross-domain mixed sampling techniques while mitigating distribution shifts from the real world. Specifically, Guidance Training guides the model to extract and reconstruct the target-domain feature distribution from mixed data, followed by decoding the reconstructed target-domain features to make pseudo-label predictions. Importantly, integrating Guidance Training incurs minimal training overhead and imposes no additional inference burden. We demonstrate the efficacy of our approach by integrating it with existing methods, consistently improving performance. The implementation will be available at https://***/Wenlve-Zhou/Guidance-Training. 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

An Encoder-Based Framework for Privacy-Preserving Machine Learning 24th

An Encoder-Based Framework for Privacy-Preserving Machine L...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Wu, Jiayun Ren, Wei Zhang, Xianchao Zheng, Xianghan School of Computer Science China University of Geosciences Wuhan430074 China State Key Laboratory of Geo-Information Engineering and Key Laboratory of Surveying and Mapping Science and Geospatial Information Technology of MNR CASM Beijing China Ministry of Education Chengdu China Key Laboratory of Medical Electronics and Digital Health of Zhejiang Province Jiaxing University Jiaxing China Engineering Research Center of Intelligent Human Health Situation Awareness of Zhejiang Province Jiaxing University Jiaxing China College of Computer and Big Data Fuzhou University Fujian Fuzhou China School of Information and Intelligent Engineering Sanya College Hainan China

ISBN: (纸本)9789819615506

As a data-driven science, machine learning requires vast amounts of training data and computational resources. However, for highly privacy-sensitive data, it is crucial to protect the privacy of the data during both the training and utilization of machine learning models. In this paper, we propose a privacy-preserving machine learning approach using autoencoders and differential privacy mechanisms to safeguard data privacy while minimizing the impact on data availability. Specifically, we augment logistic regression and ResNet18 models with different architectures of autoencoders to perform data encryption? without compromising the machine learning tasks. Additionally, we employ differential privacy mechanisms to introduce gradient perturbations in the encoding part of the autoencoder, enhancing the algorithm’s security and further protecting data privacy. We also design the cosine similarity between the encoded and original data as a metric for evaluating data privacy, considering model performance, privacy budget, and data privacy collectively to balance data availability and privacy. Extensive experiments conducted on MNIST, CIFAR-10, PathMNIST, and BloodMNIST datasets demonstrate that for simple logistic regression models handling easily classifiable datasets, employing simple autoencoder structures can enhance classification accuracy, with significant performance impact after adding differential privacy. For ResNet18, utilizing convolutional autoencoders for data encryption generally has minimal impact on model classification performance and can even improve accuracy in most cases. Adding differential privacy has minor effects on model classification performance. Selecting appropriate model structures and privacy budgets for different usage scenarios can ensure both data availability and privacy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Sign-Mamba: Advanced Mamba-Based Sign Language Generation

Sign-Mamba: Advanced Mamba-Based Sign Language Generation

引用

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

作者： Guanwen Feng Yilin Zhang Yunan Li An Liu Qiguang Miao School of Computer Science and Technology Xidian University Xi’an China Xi’an Key Laboratory of Big Data and Intelligent Vision Xidian University Xi’an China Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi’an China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In the field of sign language generation, Transformer-based models have been widely studied, but their quadratic computational complexity poses challenges. State Space Models (SSMs), like Mamba, offer a promising alternative with efficient long-range interaction modeling and linear complexity. In this study, we propose a two-stage generative framework for sign language generation, called Sign-Mamba, based on the state selection mechanism of SSM. In the first stage, we designed a Mamba-based encoder-decoder architecture, where the encoder captures the latent space representation and a symmetric decoder reconstructs it back into sign language skeletal points. In the second stage, the sign language latent space predicted by the Mamba-based latent predictor is used as a condition to guide the reconstruction network in generating more precise skeletal point sequences. We conducted comprehensive experiments on the PHOENIX and How2Sign datasets, and the results indicate that Sign-Mamba demonstrates competitive performance in sign language generation tasks. Project page: https://***/Sign-Mamba/

关键词： Sign language Computational modeling Semantics Computer architecture Signal processing Transformers Acoustics Decoding Speech processing Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Gaussian-Face: Talking Head Generation with Hybrid Density via 3D Gaussian Splatting

Gaussian-Face: Talking Head Generation with Hybrid Density v...

引用

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

作者： Guanwen Feng Yilin Zhang Yunan Li Siyu Jin Qiguang Miao School of Computer Science and Technology Xidian University Xi’an China Xi’an Key Laboratory of Big Data and Intelligent Vision Xidian University Xi’an China Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi’an China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In recent years, audio-driven neural radiance field (NeRF)-based talking head generation techniques have achieved impressive results. However, these methods still have some limitations, such as unsynchronized lip movements and visual jitter. Recently, 3D Gaussian splatting has gradually replaced NeRF. Compared to NeRF, 3D Gaussian offers notable advantages, including higher efficiency and better reconstruction quality. Based on this, we propose Gaussian-Face, an audio-driven Gaussian-based facial avatar. With just a few minutes of monocular video and audio, a high-fidelity, driveable facial avatar can be reconstructed within hours. To achieve this, we first use FLAME to obtain the 3D representation of the face and then design a Lip Motion Translator to map audio to 3D lip representations. To model higher-quality facial details, we propose a hybrid density modeling method that balances rendering speed and quality, enabling our approach to render high-fidelity facial avatars at more than 160 FPS. Project page: https://***/Gaussian-Face/

关键词： Visualization Three-dimensional displays Lips Avatars Fires Rendering (computer graphics) Neural radiance field Synchronization Speech processing Faces

来源：评论

学校读者我要写书评

暂无评论

RegMixMatch: Optimizing Mixup Utilization in Semi-Supervised Learning

arXiv

引用

arXiv 2024年

作者： Han, Haorong Yuan, Jidong Wei, Chixuan Yu, Zhongyang Key Laboratory of Big Data and Artificial Intelligence in Transportation Ministry of Education China School of Computer Science and Technology Beijing Jiaotong University China School of Data Science and Intelligent Media Communication University of China China

Consistency regularization and pseudo-labeling have significantly advanced semi-supervised learning (SSL). Prior works have effectively employed Mixup for consistency regularization in SSL. However, our findings indicate that applying Mixup for consistency regularization may degrade SSL performance by compromising the purity of artificial labels. Moreover, most pseudo-labeling based methods utilize thresholding strategy to exclude low-confidence data, aiming to mitigate confirmation bias;however, this approach limits the utility of unlabeled samples. To address these challenges, we propose RegMixMatch, a novel framework that optimizes the use of Mixup with both high- and low-confidence samples in SSL. First, we introduce semi-supervised RegMixup, which effectively addresses reduced artificial labels purity by using both mixed samples and clean samples for training. Second, we develop a class-aware Mixup technique that integrates information from the top-2 predicted classes into low-confidence samples and their artificial labels, reducing the confirmation bias associated with these samples and enhancing their effective utilization. Experimental results demonstrate that RegMixMatch achieves state-of-the-art performance across various SSL benchmarks. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

KAN-Face: Efficient Resource Usage and Precision Lip-Sync in Talking Head Generation

KAN-Face: Efficient Resource Usage and Precision Lip-Sync in...

引用

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

作者： Guanwen Feng Siyu Jin Zhihao Qian Yunan Li Qiguang Miao School of Computer Science and Technology Xidian University Xi’an China Xi’an Key Laboratory of Big Data and Intelligent Vision Xidian University Xi’an China Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi’an China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Despite significant progress in NeRF-based talking head generation, problems like poor lip synchronization and inefficient resource usage remain. To solve these, we propose KANFace, a lightweight framework. In preprocessing, we introduce a Lip-Sync Enhancement Module that uses Wav2Lip to extract high-resolution audio features and map them to an explicit intermediate representation, ensuring precise lip movement alignment with the speaker’s identity. These predicted lip-sync features are combined with fundamental audio-extracted lip features and injected into the rendering module to improve synchronization. For rendering, we introduce FastKAN to map spatial points to color values. As a variant of KAN, FastKAN’s sensitivity to 3D scenes and efficient structure enable precise, fast color prediction. Our framework reduces resource consumption while enhancing lip-sync accuracy and facial reconstruction, making it ideal for talking head generation tasks in resource-limited settings. Project: https://***/KAN-Face/

关键词： Accuracy Three-dimensional displays Lips Color Signal processing Rendering (computer graphics) Feature extraction Synchronization Speech processing Faces

来源：评论

学校读者我要写书评

暂无评论

MambaLCT: Boosting Tracking via Long-term Context State Space Model

arXiv

引用

arXiv 2024年

作者： Li, Xiaohai Zhong, Bineng Liang, Qihua Li, Guorong Mo, Zhiyi Song, Shuxiang Key Laboratory of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin541004 China Guangxi Colleges Universities Key Laboratory of Intelligent Software Wuzhou University Wuzhou543002 China Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing100101 China

Effectively constructing context information with long-term dependencies from video sequences is crucial for object tracking. However, the context length constructed by existing work is limited, only considering object information from adjacent frames or video clips, leading to insufficient utilization of contextual information. To address this issue, we propose MambaLCT, which constructs and utilizes target variation cues from the first frame to the current frame for robust tracking. First, a novel unidirectional Context Mamba module is designed to scan frame features along the temporal dimension, gathering target change cues throughout the entire sequence. Specifically, target-related information in frame features is compressed into a hidden state space through selective scanning mechanism. The target information across the entire video is continuously aggregated into target variation cues. Next, we inject the target change cues into the attention mechanism, providing temporal information for modeling the relationship between the template and search frames. The advantage of MambaLCT is its ability to continuously extend the length of the context, capturing complete target change cues, which enhances the stability and robustness of the tracker. Extensive experiments show that long-term context information enhances the model’s ability to perceive targets in complex scenarios. MambaLCT achieves new SOTA performance on six benchmarks while maintaining real-time running speeds. Code and models are available at https://***/GXNU-ZhongLab/MambaLCT. Copyright © 2024, The Authors. All rights reserved.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

Extracting Named Entity Using Entity Labeling in Geological Text Using Deep Learning Approach

引用

Journal of Earth Science 2023年第5期34卷 1406-1417页

作者： Qinjun Qiu Miao Tian Zhong Xie Yongjian Tan Kai Ma Qingfang Wang Shengyong Pan Liufeng Tao State Key Laboratory of Geo-Information Engineering and Key Laboratory of Surveying and Mapping Science and Geospatial Information Technology of MNR Chinese Academy of Surveying and MappingBeijing 100036China Key Laboratory of Spatial-Temporal Big Data Analysis and Application of Natural Resources in Megacities MNRShanghai 20063China Key Laboratory of Geological Survey and Evaluation of Ministry of Education China University of GeosciencesWuhan 430074China Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges UniversityYichang 443002China College of Computer and Information Technology China Three Gorges UniversityYichang 443002China Chengdu Geological Environment Monitoring Station Chengdu 610036China Wuhan Zondy Cyber Science&Technology Co. Ltd.Wuhan 430074China

Artificial intelligence(AI) is the key to mining and enhancing the value of big data, and knowledge graph is one of the important cornerstones of artificial intelligence, which is the core foundation for the integration of statistical and physical representations. Named entity recognition is a fundamental research task for building knowledge graphs, which needs to be supported by a high-quality corpus, and currently there is a lack of high-quality named entity recognition corpus in the field of geology, especially in Chinese. In this paper, based on the conceptual structure of geological ontology and the analysis of the characteristics of geological texts, a classification system of geological named entity types is designed with the guidance and participation of geological experts, a corresponding annotation specification is formulated, an annotation tool is developed, and the first named entity recognition corpus for the geological domain is annotated based on real geological reports. The total number of words annotated was 698 512 and the number of entities was 23 345. The paper also explores the feasibility of a model pre-annotation strategy and presents a statistical analysis of the distribution of technical and term categories across genres and the consistency of corpus annotation. Based on this corpus, a Lite Bidirectional Encoder Representations from Transformers(ALBERT)-Bi-directional Long Short-Term Memory(BiLSTM)-Conditional Random Fields(CRF) and ALBERT-BiLSTM models are selected for experiments, and the results show that the F1-scores of the recognition performance of the two models reach 0.75 and 0.65 respectively, providing a corpus basis and technical support for information extraction in the field of geology.

关键词： ontology geological reports named entity recognition geological corpus construction semi-automated annotation platforms deep learning

来源：评论

学校读者我要写书评

暂无评论

Each Fake News is Fake in its Own Way: An Attribution Multi-Granularity Benchmark for Multimodal Fake News Detection

arXiv

引用

arXiv 2024年

作者： Guo, Hao Ma, Zihan Zeng, Zhi Luo, Minnan Zeng, Weixin Tang, Jiuyang Zhao, Xiang Laboratory for Big Data and Decision Nation University of Defence Technology China School of Computer Science and Technology Xi’an Jiaotong University China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University China

Social platforms, while facilitating access to information, have also become saturated with a plethora of fake news, resulting in negative consequences. Automatic multimodal fake news detection is a worthwhile pursuit. Existing multimodal fake news datasets only provide binary labels of real or fake. However, real news is alike, while each fake news is fake in its own way. These datasets fail to reflect the mixed nature of various types of multimodal fake news. To bridge the gap, we construct an attributing multi-granularity multimodal fake news detection dataset AMG, revealing the inherent fake pattern. Furthermore, we propose a multi-granularity clue alignment model MGCA to achieve multimodal fake news detection and attribution. Experimental results demonstrate that AMG is a challenging dataset, and its attribution setting opens up new avenues for future research. © 2024, CC BY-NC-ND.

关键词： Fake detection

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：