检索结果-内蒙古大学图书馆

masked autoencoder for multiagent trajectories

MACHINE LEARNING 2025年第2期114卷 1-18页

作者： Rudolph, Yannick Brefeld, Ulf Leuphana Univ Luneburg Univ Allee 1 D-21335 Luneburg Germany

Automatically labeling trajectories of multiple agents is key to behavioral analyses but usually requires a large amount of manual annotations. This also applies to the domain of team sport analyses. In this paper, we specifically show how pretraining transformer models improves the classification performance on tracking data from professional soccer. For this purpose, we propose a novel self-supervised masked autoencoder for multiagent trajectories to effectively learn from only a few labeled sequences. Our approach builds upon a factorized transformer architecture for multiagent trajectory data and employs a masking scheme on the level of individual agent trajectories. As a result, our model allows for a reconstruction of masked trajectory segments while being permutation equivariant with respect to the agent trajectories. In addition to experiments on soccer, we demonstrate the usefulness of the proposed pretraining approach on multiagent pose data from entomology. In contrast to related work, our approach is conceptually much simpler, does not require handcrafted features and naturally allows for permutation invariance in downstream tasks.

关键词： Self-supervised learning Multiagent trajectories masked autoencoder Transformer Tracking data Soccer

来源：评论

学校读者我要写书评

暂无评论

Saliency supervised masked autoencoder pretrained salient location mining network for remote sensing image salient object detection

引用

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 2025年 224卷 222-234页

作者： Fu, Yuxiang Fang, Wei Sheng, Victor S. Nanjing Univ Informat Sci & Technol Engn Res Ctr Digital Forens Sch Comp Sci Minist Educ Nanjing Peoples R China Soochow Univ Prov Key Lab Comp Informat Proc Technol Suzhou Peoples R China Texas Tech Univ Dept Comp Sci Lubbock TX 79409 USA

Remote sensing image salient object detection (RSI-SOD), as an emerging topic in computer vision, has significant applications across various sectors, such as urban planning, environmental monitoring and disaster management, etc. In recent years, RSI-SOD has seen significant advancements, largely due to advanced representation learning methods and better architectures, such as convolutional neural networks and vision transformers. While current methods predominantly rely on supervised learning, there is potential for enhancement through self-supervised learning approaches, like masked autoencoder. However, we observed that the conventional use of masked autoencoder for pretraining encoders through masked image reconstruction yields subpar results in the context of RSI-SOD. To this end, we propose a novel approach: saliency supervised masked autoencoder (SSMAE) and a corresponding salient location mining network (SLMNet), which is pre-trained by SSMAE for the task of RSI-SOD. SSMAE first uses masked autoencoder to reconstruct the masked image, and then employs SLMNet to predict saliency map from the reconstructed image, where saliency supervision is adopted to enable SLMNet to learn robust saliency prior knowledge. SLMNet has three major components: encoder, salient location mining module (SLMM) and the decoder. Specifically, SLMM employs residual multi-level fusion structure to mine the locations of salient objects from multi-scale features produced by the encoder. Later, the decoder fuses the multi-level features from SLMM and encoder to generate the prediction results. Comprehensive experiments on three public datasets demonstrate that our proposed method surpasses the state-of-the-art methods. Code is available at: https://***/Voruarn/SLMNet.

关键词： Salient object detection masked autoencoder Deep neural network Remote sensing images

来源：评论

学校读者我要写书评

暂无评论

Signal-Guided masked autoencoder for Wireless Positioning With Limited Labeled Samples

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2025年第1期74卷 1759-1764页

作者： Wang, Ji Fang, Wei Xiao, Jian Zheng, Yi Zheng, Le Liu, Fan Cent China Normal Univ Coll Phys Sci & Technol Dept Elect & Informat Engn Wuhan 430079 Peoples R China Jianghan Univ Sch Artificial Intelligence Wuhan 430056 Peoples R China Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China Beijing Inst Technol Chongqing Innovat Ctr Chongqing 401120 Peoples R China Southeast Univ Natl Mobile Commun Res Lab Nanjing 210096 Peoples R China

In this paper, a signal-guided masked autoencoder (S-MAE) based semi-supervised learning framework is proposed for high-precision positioning with limited labeled channel impulse response (CIR) samples. To release the overfiting effect of the neural network under insufficient labeled samples, we design a two-stage training strategy based on the proposed S-MAE model, which can be divided into pre-training and fine-tuning stage. In the pre-training stage, we design an effective masking pattern in the antenna domain to learn the latent representation of CIR by utilizing a large number of unlabeled CIR samples. Besides, we introduce the channel attention mechanism to enhance the feature extraction ability in the S-MAE. In the fine-tuning stage, we use limited labeled CIR samples to fine-tune the pre-training model in a manner of supervised learning, where the long short term memory (LSTM) network is introduced to realize the mapping from CIR to user coordinates. Experiment results show that: 1) for the case of limited labeled samples, the proposed S-MAE model has superior positioning accuracy compared to conventional positioning models. 2) For the case of non-ideal CIR scenarios, the robustness performance of the S-MAE is better than that of other benchmark models. 3) The performance gain of the proposed S-MAE under different masking patterns/ratios on the CIR sample is presented, which verifies the effectiveness of the proposed masking strategy.

关键词： Channel impulse response Antennas Accuracy Training Feature extraction Decoding Vectors masked autoencoder high-precision positioning semi-supervised channel impulse response

来源：评论

学校读者我要写书评

暂无评论

Reversible data hiding in encrypted images based on pixel-level masked autoencoder and polar code

引用

SIGNAL PROCESSING 2025年 226卷

作者： Cheng, Zhangpei Chen, Kaimeng Guan, Qingxiao Jimei Univ Coll Comp Engn Xiamen 361021 Peoples R China Guangzhou Univ Sch Comp Sci & Cyber Engn Guangzhou 510006 Peoples R China

In the study of vacating-room-after-encryption reversible data hiding in encrypted images (VRAE RDHEI), pixel prediction is an important mechanism to achieve reversibility, which has a crucial impact on the capacity and fidelity. In this paper, we propose a novel pixel-level masked autoencoders (PLMAE) as a high-performance pixel predictor for RDHEI. Unlike the original masked autoencoders (MAE), PLMAE focuses on pixel-level reconstruction rather than semantic patch-level reconstruction. The purpose of PLMAE is to spare more carrier pixels while maintaining relatively high prediction accuracy, thereby improving the RDHEI capacity. Based on PLMAE, a novel RDHEI method is proposed. In the proposed method, the data hider encodes the secret data using a polar code and then embeds the encoded data. After the image is decrypted, the receiver considers the carrier pixels as masked pixels, predicts the original states of the carrier pixels using PLMAE to extract the secret data, and then decodes the secret data and recovers the image based on the decoding results. The experimental results demonstrate that the proposed method in this paper can achieve better performance than the existing methods.

关键词： Reversible data hiding Image encryption masked autoencoder Polar code

来源：评论

学校读者我要写书评

暂无评论

Contrastive Semantic-Aware masked autoencoder for Point Cloud Self-Supervised Learning

引用

IEEE SIGNAL PROCESSING LETTERS 2025年 32卷 1760-1764页

作者： He, Yuan Hu, Guyue Yu, Shan Chinese Acad Sci Inst Automat Lab Brain Atlas & Brain Inspired Intelligence Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Anhui Univ Sch Artificial Intelligence Hefei 230039 Peoples R China Chinese Acad Sci State Key Lab Brain Cognit & Brain Inspired Intell Beijing 100049 Peoples R China Univ Chinese Acad Sci Sch Future Technol Beijing 100049 Peoples R China

masked autoencoder (MAE) has shown remarkable potential in self-supervised representation learning for 3D point clouds. However, these methods primarily rely on point-level or low-level feature reconstruction, forcing the model to focus on local regions while lacking enough global discriminability in the feature representation. Moreover, conventional masking strategies randomly mask some point patches, thereby neglecting the semantic structure of the point cloud and hindering the holistic understanding of global information and geometric structures. To address these challenges, we proposed a Contrastive Semantic-aware masked autoencoder (Point-CSMAE), which is equipped with a semantic-aware masking (SAM) strategy and a contrastive regularization (CR) mechanism. Specifically, the semantic-aware masking strategy adaptively selects patches with richer semantic information for masking and reconstruction, enhancing the understanding of global geometric structure. Furthermore, the contrastive regularization mechanism adaptively aligns the global information between the masked and visible parts, thus improving the learned global semantic representation. Meanwhile, the CR mechanism assists the SAM strategy with effective global semantic representations. Extensive experiments on various downstream tasks, including shape classification, few-shot classification, and part segmentation, demonstrate the superiority of the proposed approach.

关键词： Point cloud compression Semantics autoencoders Three-dimensional displays Self-supervised learning Shape Image reconstruction Artificial intelligence Nearest neighbor methods Brain 3D point cloud masked autoencoder masking strategy contrastive regularization

来源：评论

学校读者我要写书评

暂无评论

AnCoGen: Analysis, Control and Generation of Speech with a masked autoencoder

AnCoGen: Analysis, Control and Generation of Speech with a M...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Sadok, Samir Leglaive, Simon Girin, Laurent Richard, Gaël Alameda-Pineda, Xavier Inria at Univ. Grenoble Alpes CNRS LJK France CentraleSupélec IETR UMR CNRS 6164 France Univ. Grenoble Alpes CNRS Grenoble INP GIPSA-Lab France LTCI Télécom Paris Institut Polytechnique de Paris France

ISBN: (纸本)9798350368741

This article introduces AnCoGen, a novel method that leverages a masked autoencoder to unify the analysis, control, and generation of speech signals within a single model. AnCoGen can analyze speech by estimating key attributes, such as speaker identity, pitch, content, loudness, signal-to-noise ratio, and clarity index. In addition, it can generate speech from these attributes and allow precise control of the synthesized speech by modifying them. Extensive experiments demonstrated the effectiveness of AnCoGen across speech analysis-resynthesis, pitch estimation, pitch modification, and speech enhancement. Code and audio examples are available online. © 2025 IEEE.

关键词： masked autoencoder pitch estimation and modification Speech analysis/transformation/synthesis speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Spatial-Spectral Hierarchical Multiscale Transformer-Based masked autoencoder for Hyperspectral Image Classification

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 12150-12165页

作者： Liu, Haipeng Ye, Zhen Hu, Wen-Shuai Cao, Zhan Li, Wei Changan University School of Electronics and Control Engineering Xi'an 710064 China Beijing Institute of Technology School of Information and Electronics Beijing 100081 China Beijing Institute of Technology Zhuhai 519088 China

Due to the excellent feature extraction capabilities, deep learning has become the mainstream method for hyperspectral image (HSI) classification. Transformer, with its powerful long-range relationship modeling ability, has become a popular model;however, it usually requires a large number of labeled data for parameter training, which may be costly and impractical for HSI classification. As such, based on the self-supervised learning, this paper proposes a spatial-spectral hierarchical multiscale transformer-based masked autoencoder (SSHMT-MAE) for HSI classification. Firstly, after the spatial-spectral feature embedding with a spatial-spectral feature extraction module, to solve the increased computational complexity caused by filling invisible patches in traditional MAE, the grouped window attention module is introduced to process only the visible patches of HSIs during spatial-spectral reconstruction, avoiding unnecessary computations for masked ones. After that, a spatial-spectral hierarchical transformer is designed to build a hierarchical MAE framework, followed by a cross-feature fusion module to extract the multiscale spatial-spectral fusion features. It can not only assist the whole model in learning the fine-grained local spatial-spectral features within each local region but also capture the long-range dependencies between different regions, generating rich multiscale spatial-spectral features with high-level semantic and low-level detail information for HSI classification. Extensive experiments are conducted on the five public HSI datasets, evaluating the superiority of the proposed SSHMT-MAE model over several state-of-the-art methods. © 2008-2012 IEEE.

关键词： feature fusion Grouped window attention hierarchical vision transformer hyperspectral image classification masked autoencoder multiscale learning

来源：评论

学校读者我要写书评

暂无评论

Multimodal masked autoencoder Based on Adaptive Masking for Vitiligo Stage Classification

引用

JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2025年 1-14页

作者： Xiang, Fan Li, Zhiming Jiang, Shuying Li, Chunying Li, Shuli Gao, Tianwen He, Kaiqiao Chen, Jianru Zhang, Junpeng Zhang, Junran Sichuan Univ Coll Elect Engn Dept Automat Chengdu 610065 Peoples R China Fourth Mil Med Univ Xijing Hosp Dept Dermatol Xian 710032 Peoples R China

Vitiligo, a prevalent skin condition characterized by depigmentation, presents challenges in staging due to its inherent complexity. Multimodal skin images can provide complementary information, and in this study, the integration of clinical images of vitiligo and those obtained under Wood's lamp is conducive to the classification of vitiligo stages. However, difficulties in annotating multimodal data and the scarcity of multimodal data limit the performance of deep learning models in related classification tasks. To address these issues, a Multimodal masked autoencoder (Multi-MAE) based on adaptive masking is proposed in annotating multimodal data and the problem of multimodal data scarcity, and enhances the model's ability to extract characteristics from multimodal data. Specifically, an image reconstruction task is constructed to diminish reliance on annotated multimodal data, and a pre-training strategy is employed to alleviate the scarcity of multimodal data. Experimental results demonstrate that the proposed model achieves a vitiligo stage classification accuracy of 95.48% on a dataset of unlabeled dermatological images, an improvement of 5.16%, 4.51%, 3.87%, 2.58%, 4.51%, 4.51%, 3.87%, and 2.58% over that of MobileNet, DenseNet, VGG, ResNet-50, BEIT, MaskFeat, SimMIM, and MAE, respectively. These results verify the effectiveness of the proposed Multi-MAE model in assessing the stable and active vitiligo stages, making it a suitable clinical aid for evaluating the severity of vitiligo lesions.

关键词： Multimodal masked autoencoder Adaptive Masking Vitiligo Stage

来源：评论

学校读者我要写书评

暂无评论

masked Graph autoencoder for Self-Supervised Transportation Mode Recognition

引用

TRANSACTIONS IN GIS 2025年第1期29卷

作者： Zeng, Ziyi Wang, Guanwen Zhang, Yifan Guan, Qingfeng Yu, Wenhao China Univ Geosci Sch Geog & Informat Engn Wuhan Peoples R China China Univ Geosci Natl Engn Res Ctr Geog Informat Syst Wuhan Peoples R China

Transportation mode recognition reveals the traveling patterns of urban residents and plays an important role in travel analysis and city planning. Research has been done to identify transportation modes using deep learning methods. However, large-scale and far-ranging labeled trajectory data are hard to acquire, which hinders the training and application of supervised models. In this study, we propose a self-supervised method for trajectory transportation modes recognition. First, we construct sequence and dependency graph for trajectory points. Next, we apply mask and remask strategy to graph node features to enhance its learning ability in semantic information. Notably, in order to learn features without labeled data, we introduce graph autoencoder into the framework. This method is able to learn the sequence and dependency feature reconstruction of the travel paths. It can obtain underlying semantic information with the mask and remask strategy. We applied our model to GPS trajectory dataset from the Microsoft GeoLife Project, achieving an average accuracy of 68.26% in identifying the transportation modes among seven categories. The result indicates that the proposed method offers a solution to identifying transportation modes without abundant labeled data. This method can also help to extract space-time features at different scales from trajectory data, which could be applied to various downstream tasks.

关键词： masked autoencoder trajectory data transportation mode transportation recognition

来源：评论

学校读者我要写书评

暂无评论

masked autoencoder for Distribution Estimation on Small Structured Data Sets

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2021年第11期32卷 4997-5007页

作者： Khajenezhad, Ahmad Madani, Hatef Beigy, Hamid Sharif Univ Technol Dept Comp Engn Tehran *** Iran

Autoregressive models are among the most successful neural network methods for estimating a distribution from a set of samples. However, these models, such as other neural methods, need large data sets to provide good estimations. We believe that knowing structural information about the data can improve their performance on small data sets. masked autoencoder for distribution estimation (MADE) is a well-structured density estimator, which alters a simple autoencoder by setting a set of masks on its connections to satisfy the autoregressive condition. Nevertheless, this model does not benefit from extra information that we might know about the structure of the data. This information can especially be advantageous in case of training on small data sets. In this article, we propose two autoencoders for estimating the density of a small set of observations, where the data have a known Markov random field (MRF) structure. These methods modify the masking process of MADE, according to conditional dependencies inferred from the MRF structure, to reduce either the model complexity or the problem complexity. We compare the proposed methods with some related binary, discrete, and continuous density estimators on MNIST, binarized MNIST, OCR-letters, and two synthetic data sets.

关键词： Estimation Computational modeling Data models Neural networks Complexity theory Training Markov processes Deep learning density estimation Markov random field (MRF) masked autoencoder

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：