检索结果-内蒙古大学图书馆

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

作者： Ishikawa, Yuchi Komatsu, Tatsuya Aoki, Yoshimitsu LY Corporation Tokyo Japan Keio University Kanagawa Japan

ISBN: (纸本)9798350368741

In this paper, we propose to pre-train audio encoders using synthetic patterns instead of real audio data. Our proposed framework consists of two key elements. The first one is masked autoencoder (MAE), a self-supervised learning framework that learns from reconstructing data from randomly masked counterparts. MAEs tend to focus on low-level information such as visual patterns and regularities within data. Therefore, it is unimportant what is portrayed in the input, whether it be images, audio mel-spectrograms, or even synthetic patterns. This leads to the second key element, which is synthetic data. Synthetic data, unlike real audio, is free from privacy and licensing infringement issues. By combining MAEs and synthetic patterns, our framework enables the model to learn generalized feature representations without real data, while addressing the issues related to real audio. To evaluate the efficacy of our framework, we conduct extensive experiments across a total of 13 audio tasks and 17 synthetic datasets. The experiments provide insights into which types of synthetic patterns are effective for audio. Our results demonstrate that our framework achieves performance comparable to models pre-trained on AudioSet-2M and partially outperforms image-based pre-training methods. © 2025 IEEE.

关键词： audio masked autoencoder self-supervised learning synthetic data

来源：评论

学校读者我要写书评

暂无评论

masked autoencoders for Spatial-Temporal Relationship in Video-Based Group Activity Recognition

引用

IEEE ACCESS 2024年 12卷 132084-132095页

作者： Yadav, Rajeshwar Halder, Raju Banda, Gourinath Indian Inst Technol Patna Dept Comp Sci & Engn Bihta 801106 India Indian Inst Technol Indore Dept Comp Sci & Engn Indore 453552 Madhya Pradesh India

Group Activity Recognition (GAR) is a challenging problem involving several intricacies. The core of GAR lies in delving into spatiotemporal features to generate appropriate scene representations. Previous methods, however, either feature a complex framework requiring individual action labels or need more adequate modelling of spatial and temporal features. To address these concerns, we propose a masking strategy for learning task-specific GAR scene representations through reconstruction. Furthermore, we elucidate how this methodology can effectively capture task-specific spatiotemporal features. In particular, three notable findings emerge from our framework: 1) GAR is simplified, eliminating the need for individual action labels;2) the generation of target-specific spatiotemporal features yields favourable outcomes for various datasets;and 3) this method demonstrates effectiveness even for datasets with a small number of videos, highlighting its capability with limited training data. Further, the existing GAR datasets have fewer videos per class and only a few actors are considered, restricting the existing model from being generalised effectively. To this aim, we introduce 923 videos for a crime activity named IITP Hostage, which contains two categories, hostage and non-hostage. To our knowledge, this is the first attempt to recognize crime-based activities in GAR. Our framework achieves MCA of 96.8%, 97.0%, 97.0% on Collective Activity Dataset (CAD), new CAD, extended CAD datasets and 84.3%, 95.6%, 96.78% for IITP Hostage, hostage+CAD and subset of UCF crime datasets. The hostage and non-hostage scenarios introduce additional complexity, making it more challenging for the model to accurately recognize the activities compared to hostage+CAD and other datasets. This observation underscores the necessity to delve deeper into the complexity of GAR activities.

关键词： Group activity recognition (GAR) hostage crime IITP hostage dataset spatial and temporal interaction vision transformer masked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Partial Reconstruction Error for Deepfake Detection

Partial Reconstruction Error for Deepfake Detection

引用

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

作者： Zhang, Yufei Meng, Zheling Peng, Bo Dong, Jing Chu, Beilin Wang, Wei School of Cyberspace Security Beijing University of Posts and Telecommunications Beijing China Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350368741

The rapid development of deepfake technology poses a formidable challenge to personal privacy and security, underscoring the urgent need for deepfake detection. Recently, the methods based on the reconstruction error, such as DIRE and RECCE, achieve impressive performance in forgery detection. However, their performance on facial forgery datasets is relatively poor. The reconstruction process is performed on the whole images, neglecting contextual information for reconstruction. In this paper, we propose Partial Reconstruction Error to perform deepfake detection based on the reconstruction of masked regions in an image. In this way, contextual information helps to reveal the inconsistencies between the original and reconstructed regions thereby improving the detection performance. This method outperforms the best global reconstruction-based approaches on the FF++, Celeb-DF, and DiFF datasets by 4.00%, 2.83%, and 2.67%, respectively. © 2025 IEEE.

关键词： Deepfake Detection masked autoencoder Partial Reconstruction

来源：评论

学校读者我要写书评

暂无评论

Parallel segmentation network for real-time semantic segmentation

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 148卷

作者： Chen, Guanke Li, Haibin Li, Yaqian Zhang, Wenming Song, Tao Yanshan Univ Key Lab Ind Comp Control Engn Heibei Prov Qinhuangdao 066004 Peoples R China Yanshan Univ Sch Elect Engn Hebei Prov Key Lab Test Measurement Technol & Inst Qinhuangdao 066004 Peoples R China

Real-time semantic segmentation holds extensive application prospects in autonomous driving and robot navigation. Recently, real-time semantic segmentation networks mainly adopt encoder-decoder architecture and multi-branch architecture. However, both approaches have their own advantages and limitations. Encoder- decoder models are generally better at extracting contextual information, but may face challenges in capturing fine details and local spatial information. On the other hand, the multi-branch structure excels at capturing boundary and spatial detail information, but it requires an efficient and flexible feature fusion strategy to prevent information redundancy. To leverage the strengths of both approaches, we propose a Parallel Segmentation Network (PaSeNet) which adopts the unsymmetrical encoder-decoder structure to introduce novel ideas for research and applications in real-time semantic segmentation. Specifically, we design a main branch with a spatial information enhancement path during the encoding phase and introduce mask autoencoder based on self-supervised learning as an auxiliary branch to supplement the main branch in extracting details as well as local spatial information. Additionally, we propose the Grouped Aggregation Pyramid Pooling Module to optimize the extraction of contextual information. In the decoding phase, we introduce the Coordinate-Attention- Guided Decoder to effectively integrate diverse information from different branches. A large number of experiments on the Cityscapes, Cambridge-driving Labeled Video database (CamVid), NightCity and instance Segmentation in Aerial Images Dataset demonstrate that our method achieves competitive results. Specifically, PaSeNet-Base obtains 79.9% mean Intersection Over Union (mIOU) at 55.6 Frames Per Second (FPS) on Cityscapes test dataset and 80.2% mIOU at 96.8 FPS on CamVid test dataset.

关键词： Semantic segmentation Real-time processing Parallel segmentation network masked autoencoder

来源：评论

学校读者我要写书评

暂无评论

masked autoencoders for Low-dose CT Denoising 20

Masked Autoencoders for Low-dose CT Denoising

引用

20th IEEE International Symposium on Biomedical Imaging (ISBI)

作者： Wang, Dayang Xu, Yongshun Han, Shuo Yu, Hengyong Univ Massachusetts Lowell Dept Elect & Comp Engn Lowell MA 01854 USA

ISBN: (纸本)9781665473583

Low-dose computed tomography (LDCT) reduces the X-ray radiation but compromises image quality with more noises and artifacts. A plethora of transformer models have been developed recently to improve LDCT image quality. However, the success of a transformer model relies on a large amount of paired noisy and clean data, which is often unavailable in clinical applications. In computer vision and natural language processing fields, masked autoencoders (MAE) have been proposed as an effective label-free self-pretraining method for transformers, due to its excellent feature representation ability. Here, we redesign the classical encoder-decoder learning model based on SwinIR to match the denoising task and apply it to LDCT denoising problem. Then, the redesigned MAE can leverage the unlabeled data and facilitate structural preservation for the LDCT denoising model when there are insufficient target data. Experiments on the Mayo dataset validate that the MAE can boost the transformer's denoising performance and relieve the dependence on the ground truth data.

关键词： Low-dose CT masked autoencoder Self-pretraining Transformer

来源：评论

学校读者我要写书评

暂无评论

Enhancement of Optical Wireless Discrete Multitone Channel Capacity Based on Li-Fi Using Sparse Coded Mask Modeling

引用

PHOTONICS 2025年第4期12卷 395-395页

作者： Won, Yong-Yuk Han, Heetae Choi, Dongmin Yoon, Sang Min Myongji Univ Dept Elect Engn 116 Myongji Ro Yongin 17058 South Korea Kookmin Univ Sch Comp Sci 77 Jeongneung Ro Seoul 02707 South Korea

A sparse coded mask modeling technique is proposed to increase the transmission capacity of an optical wireless link based on Li-Fi. The learning model for the discrete multitone (DMT) signal waveform is implemented using the proposed technique, which is designed based on a masked auto-encoder. The entire length of the DMT signal waveform, encoded using quadrature phase shift keying (QPSK) or 16-quadrature amplitude modulation (16-QAM) symbols, is divided into equal intervals to generate DMT patches, which are subsequently compressed based on the specified masking ratio. After 1-m optical wireless transmission, the DMT signal waveform is reconstructed from the received DMT patch through a decoding process and then QPSK or 16-QAM symbols are recovered. Using the proposed technique, we demonstrate that we can increase the transmission capacity by up to 1.85 times for a 10 MHz physical bandwidth. Additionally, we verify that the proposed technique is feasible in Li-Fi networks with illumination environments above 240 lux.

关键词： discrete multi-tone modulation light-fidelity masked autoencoder sparse coded mask modeling

来源：评论

学校读者我要写书评

暂无评论

PersonMAE: Person Re-Identification Pre-Training With masked autoencoders

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2024年 26卷 10029-10040页

作者： Hu, Hezhen Dong, Xiaoyi Bao, Jianmin Chen, Dongdong Yuan, Lu Chen, Dong Li, Houqiang Univ Sci & Technol China Hefei 230027 Peoples R China Microsoft Res Asia Beijing 100080 Peoples R China Microsoft Redmond WA 98052 USA

Pre-training is playing an increasingly important role in learning generic feature representation for Person Re-identification (ReID). We argue that a high-quality ReID representation should have three properties, namely, multi-level awareness, occlusion robustness, and cross-region invariance. To this end, we propose a simple yet effective pre-training framework, namely PersonMAE, which involves two core designs into masked autoencoders to better serve the task of Person Re-ID. 1) PersonMAE generates two regions from the given image with RegionA as the input and RegionB as the prediction target. RegionA is corrupted with block-wise masking to mimic common occlusion in ReID and its remaining visible parts are fed into the encoder. 2) Then PersonMAE aims to predict the whole RegionB at both pixel level and semantic feature level. It encourages its pre-trained feature representations with the three properties mentioned above. These properties make PersonMAE compatible with downstream Person ReID tasks, leading to State-of-the-Art performance on four downstream ReID tasks, i.e., supervised (holistic and occluded setting), and unsupervised (UDA and USL setting). Notably, on the commonly adopted supervised setting, PersonMAE with ViT-B backbone achieves 79.8% and 69.5% mAP on the MSMT17 and OccDuke datasets, surpassing the previous State-of-the-Art by a large margin of +8.0 mAP, and +5.3 mAP, respectively.

关键词： Task analysis Pedestrians Semantics Robustness Decoding Visualization Image color analysis High-quality ReID representation masked autoencoder pre-training

来源：评论

学校读者我要写书评

暂无评论

Dynamic background reconstruction via masked autoencoders for infrared small target detection

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年 135卷

作者： Peng, Jingchao Zhao, Haitao Zhao, Kaijie Wang, Zhongze Yao, Lujian East China Univ Sci & Technol Sch Informat Sci & Engn Automat Dept 130 Meilong Rd Shanghai 200237 Peoples R China

Infrared small target detection (ISTD) under complex backgrounds is a difficult problem, for the differences between targets and backgrounds are not easy to distinguish. Background reconstruction is one of the methods to deal with this problem. This paper proposes an ISTD method based on background reconstruction called Dynamic Background Reconstruction (DBR). DBR consists of three modules: a dynamic shift window module (DSW), a background reconstruction module (BR), and a detection head (DH). BR takes advantage of masked autoencoders in reconstructing missing patches and adopts a grid masking strategy with a masking ratio of 50% to reconstruct clean backgrounds without targets. To avoid dividing one target into two neighboring patches, resulting in reconstructing failure, DSW is performed before input embedding. DSW calculates offsets, according to which infrared images dynamically shift. To reduce False Positive (FP) cases caused by regarding reconstruction errors as targets, DH utilizes a structure of densely connected Transformer to further improve the detection performance. Experimental results show that DBR achieves the best F 1-score on the two ISTD datasets, which can be widely used in anti-unmanned aerial vehicles, surveillance, and automatic driving systems. The model and dataset will be available at https://***/PengJingchao/DBR.

关键词： Infrared modality Small target detection Background reconstruction Dynamic shift window masked autoencoder

来源：评论

学校读者我要写书评

暂无评论

MaskRecon: High-quality human reconstruction via masked autoencoders using a single RGB-D image

引用

NEUROCOMPUTING 2024年 609卷

作者： Li, Xing Fan, Yangyu Guo, Zhe Rao, Zhibo Duan, Yu Liu, Shiya Northwestern Polytech Univ Sch Elect & Informat Xian 710129 Peoples R China Nanchang Hangkong Univ Sch Informat Engn Nanchang 330063 Peoples R China Northwestern Polytech Univ Sch Comp Sci Xian 710129 Peoples R China Content Prod Ctr Virtual Real Beijing 101318 Peoples R China

In this paper, we explore reconstructing high-quality clothed 3D humans from a single RGB-D image, assuming that virtual humans can be represented by front-view and back-view depths. Due to the scarcity of captured real RGB-D human images, we employ rendered images to train our method. However, rendered images lack background with significant depth variation in silhouettes, leading to shape prediction inaccuracies and noise. To mitigate this issue, we introduce a pseudo-multi-task framework, which incorporates a Conditional Generative Adversarial Network (CGAN) to infer back-view RGB-D images and a self-supervised masked autoencoder (MAE) to capture latent structural information of the human body. Additionally, we propose a Multi-scale Feature Fusion (MFF) module to effectively merge structural information and conditional features at various scales. Our method surpasses many existing techniques, as demonstrated through evaluations on the Thuman, RenderPeople, and BUFF datasets. Notably, our approach excels in reconstructing high-quality human models, even under challenging conditions such as complex poses and loose clothing, both on rendered and real-world images. Codes are available at https://***/Archaic-Atom/MaskRecon.

关键词： Reconstruct clothed 3D human Single RGB-D image Pseudo-multi-task framework masked autoencoder Multi-scale feature fusion

来源：评论

学校读者我要写书评

暂无评论

LoMAE: Simple Streamlined Low-Level masked autoencoders for Robust, Generalized, and Interpretable Low-Dose CT Denoising

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2024年第11期28卷 6815-6827页

作者： Wang, Dayang Han, Shuo Xu, Yongshun Wu, Zhan Zhou, Li Morovati, Bahareh Yu, Hengyong Univ Massachusetts Lowell Dept Elect & Comp Engn Lowell MA 01854 USA Southeast Univ Lab Image Sci & Technol Nanjing 210096 Peoples R China Southeast Univ Key Lab Comp Network & Informat Integrat Minist Educ Nanjing 210096 Peoples R China

Low-dose computed tomography (LDCT) offers reduced X-ray radiation exposure but at the cost of compromised image quality, characterized by increased noise and artifacts. Recently, transformer models emerged as a promising avenue to enhance LDCT image quality. However, the success of such models relies on a large amount of paired noisy and clean images, which are often scarce in clinical settings. In computer vision and natural language processing, masked autoencoders (MAE) have been recognized as a powerful self-pretraining method for transformers, due to their exceptional capability to extract representative features. However, the original pretraining and fine-tuning design fails to work in low-level vision tasks like denoising. In response to this challenge, we redesign the classical encoder-decoder learning model and facilitate a simple yet effective streamlined low-level vision MAE, referred to as LoMAE, tailored to address the LDCT denoising problem. Moreover, we introduce an MAE-GradCAM method to shed light on the latent learning mechanisms of the MAE/LoMAE. Additionally, we explore the LoMAE's robustness and generability across a variety of noise levels. Experimental findings show that the proposed LoMAE enhances the denoising capabilities of the transformer and substantially reduce their dependency on high-quality, ground-truth data. It also demonstrates remarkable robustness and generalizability over a spectrum of noise levels. In summary, the proposed LoMAE provides promising solutions to the major issues in LDCT including interpretability, ground truth data dependency, and model robustness/generalizability.

关键词： Noise reduction Noise Transformers Computed tomography Decoding Robustness Data models Low-dose CT masked autoencoder self-pretraining transformer

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：