检索结果-内蒙古大学图书馆

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

作者： Xiangyu Ma Jing Bai Jinzhe Jiang Bin Peng The School of Computer Science and Engineering North Minzu University The Key Laboratory of Images Processing and Pattern Recognition Laboratory Yinchuan China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Fine-grained 3D shape classification (FGSC) remains challenging due to the difficulty of adaptively capturing global structure differences and subtle inter-class distinctions. This paper directly extends Vision Transformer (ViT) to FGSC, proposing a pure Transformer network FG3DFormer that fully leverages ViT’s global correlation and local attention abilities. FG3Dformer comprises the Hierarchical Feature Extraction (HFE) and the Hierarchical Feature Refinement (HFR), interconnected through the Adaptive View Region Selection (AVRS). Firstly, the HFE comprehensively evaluates the significance of intra-view patches and views driven by inter-view and intraview attention. Then, the AVRS adaptively selects crucial patch Tokens from different views to serve as sources of subtle local features. Finally, the HFR refines the 3D shape descriptor, capturing more discriminative global and subtle local features by leveraging both the view and selected crucial patch Tokens. Extensive experiments on FG3D and ModelNet40 demonstrate the superiority of FG3Dformer in FGSC and meta-category 3D shape classification tasks.

关键词： Computer vision Visualization Solid modeling Three-dimensional displays Correlation Shape Signal processing Transformers Feature extraction Speech processing

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks Based on MLP 14

Generative Adversarial Networks Based on MLP

引用

14th International Conference on Digital Image processing, ICDIP 2022

作者： Ding, Hui Chen, Weifeng Li, Bo He, Zhifen School of Mathematics and Information Science Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China

ISBN: (纸本)9781510657564

Inspired by the state-of-the-art performance of MLP-Mixer on image classification task, multilayer perceptron (MLP) model attracts a number of researcher's attention again. Although various MLP architectures have been proposed, most of them focus on image classification domain. In this paper, we extend MLP to the task of image generation based on generative adversarial network (GAN). The pure MLP model is not friendly to small dataset because it is a data-hungry architecture. Thus, we leverage a hybrid model to solve the problem which uses MLP blocks as generator and CNN blocks as discriminator. Experimental results demonstrate that our model outperforms the pure CNN network on CIFAR-10 dataset in view of two different evaluation metrics. Besides, we apply eight widely popular MLP structures to our generator to validate which one achieves the most excellent performance in image generation task. © 2022 SPIE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Tasks-oriented channel optimization and resource allocation in vehicular networks: a hierarchical reinforcement learning based approach

引用

IEEE Transactions on Vehicular Technology 2024年第5期74卷 7624-7636页

作者： Lin, Runtao Guo, Caili Zhang, Biling Chen, Jiujiu Li, Hanyang Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing100876 China Nanchang Hangkong University Key Laboratory of Processing and Pattern Recognition of Jiangxi Province School of Information Engineering Nanchang330063 China China Mobile Communication Co. Ltd Wireless and Terminal Technology Research Institute Beijing100053 China

The number of devices, data volume, and pictures and videos in the vehicular networks have all increased significantly as a result of the continued development of 6G technology, putting an enormous burden on the edge communication resources. To solve this problem, a good resource allocation scheme is necessary. Existing resource allocation algorithms often pursue accurate transmission and ignore time-varying channels. In order to further obtain real and reasonable resource allocation results, this paper introduces semantic communication. It then decomposes that problem to further establish a hierarchical framework. The problem is addressed via a task-oriented channel optimization and resource allocation scheme based on a hierarchical reinforcement learning (TCRS-HRL) algorithm. First, a channel optimization and resource allocation problem under an imperfect channel state is developed, and it is divided into two separate sub problems for optimization. Second, the resource allocation problem at the edge is addressed with the introduction of hierarchical reinforcement learning and the TCRSHRL algorithm. The ideal channel state and resource allocation approach are found by constructing the state space, action space, and environmental feedback for each aspect individually. Finally, simulations have demonstrated the superiority and performance benefits of the proposed algorithm compared to current methods, showing that the implementation of TCRS-HRL can result in an accuracy improvement of roughly 8%. © 1967-2012 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

OCF-Layout2Img: Object-Wise Constraint Free Layout to Image Generation 23

OCF-Layout2Img: Object-Wise Constraint Free Layout to Image ...

引用

15th International Conference on Digital Image processing, ICDIP 2023

作者： Lin, Xiao Liu, Bin He, Zhifen Wang, Kang Li, Bo School of Mathematics and Information Science Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University China Jiangxi Science and Technology Infrastructure Center Jiangxi Computing Center China

ISBN: (纸本)9798400708237

Complex scene generation is an important and challenging image synthesis task. Though latent space based conditional generative methods get impressive results, the accurate locating of objects for more detailed situation and editable contiguous synthesis are still a snag. In addition, previous methods with spatial awareness are easy to lose the location information after a series fusion operation. Focusing on such kind of problems, in this paper we propose an object-wise constraint free and location-lossless way of layout embedding by combining VAE and recent high performance VQGAN to achieve a location accurate and stable synthesis for layouts of complex scene. Instead of conditioning on layout, we apply a pretrained VQGAN to define the latent space and project every region of layout to image latent space directly by aligning their distribution with a novel light Cross-VAE structure. Then the quantization and decoder of VQGAN are reused for synthesis. This VAE plugged into VQGAN framework, which is called Layout-DVGAN in this paper. Experimental results demonstrate our method has competitive performance compared with the approaches which applied explicit spatial awareness way. © 2023 ACM.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Image Object Detection Method with Feature Denoising Fusion Module 7

Remote Sensing Image Object Detection Method with Feature De...

引用

7th IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2024

作者： Chen, Penghui Li, Qishen Li, Qiufeng Wu, Zhongyu Nanchang Hangkong University School of Information Engineering Jiangxi Nanchang China Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Jiangxi Nanchang China Nanchang Hangkong University School of Software Jiangxi Nanchang China Jiangxi Nanchang China

ISBN: (纸本)9798350339161

Remote sensing object detection is an important research area in computer vision, widely applied in both military and civilian domains. However, challenges in remote sensing image object detection such as large image sizes, complex backgrounds, and significant variations in target scales are prevalent. To address these issues, this paper proposes a new Feature Denoising and Fusion Module (FDFM) aimed at enhancing the accuracy and robustness of object detection. This module comprises a Multi-Scale Denoising Submodule(MDS) and an Attention Optimization Submodule(AOS). The Multi-Scale Denoising Module aims to suppress lower-level texture noise by utilizing higher-level semantic features before the fusion process, reducing the impact of lower-level noise on subsequent multi-scale feature fusion. Meanwhile, the Attention Optimization Module seeks to enhance the precision of self-attention computations within the Multi-Scale Denoising Module without increasing the parameter count. The efficacy of this method was evaluated on public datasets DOTA, VisDrone, VOC and COCO, showing improvements in comparison to baseline models. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

TOWARDS CODABLE WATERMARKING FOR INJECTING MULTI-BITS INFORMATION TO LLMS 12

TOWARDS CODABLE WATERMARKING FOR INJECTING MULTI-BITS INFORM...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Wang, Lean Yang, Wenkai Chen, Deli Zhou, Hao Lin, Yankai Meng, Fandong Zhou, Jie Sun, Xu National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China Gaoling School of Artificial Intelligence Renmin University of China China Pattern Recognition Center WeChat AI Tencent Inc. China DeepSeek AI China

As large language models (LLMs) generate texts with increasing fluency and realism, there is a growing need to identify the source of texts to prevent the abuse of LLMs. Text watermarking techniques have proven reliable in distinguishing whether a text is generated by LLMs by injecting hidden patterns. However, we argue that existing LLM watermarking methods are encoding-inefficient and cannot flexibly meet the diverse information encoding needs (such as encoding model version, generation time, user id, etc.). In this work, we conduct the first systematic study on the topic of Codable Text Watermarking for LLMs (CTWL) that allows text watermarks to carry multi-bit customizable information. First of all, we study the taxonomy of LLM watermarking technologies and give a mathematical formulation for CTWL. Additionally, we provide a comprehensive evaluation system for CTWL: (1) watermarking success rate, (2) robustness against various corruptions, (3) coding rate of payload information, (4) encoding and decoding efficiency, (5) impacts on the quality of the generated text. To meet the requirements of these non-Pareto-improving metrics, we follow the most prominent vocabulary partition-based watermarking direction, and devise an advanced CTWL method named Balance-Marking. The core idea of our method is to use a proxy language model to split the vocabulary into probability-balanced parts, thereby effectively maintaining the quality of the watermarked text. Extensive experimental results show that our method outperforms the baseline under comprehensive evaluation. Our code is available at https://***/lancopku/codable-watermarking-for-llm. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Visual Prompt Flexible-Modal Face Anti-Spoofing

引用

IEEE Transactions on Dependable and Secure Computing 2025年第3期22卷 2597-2606页

作者： Yu, Zitong Cai, Rizhao Cui, Yawen Liu, Ajian Chen, Changsheng Great Bay University School of Computing and Information Technology Dongguan523000 China Nanyang Technological University ROSE Lab School of EEE 639798 Singapore Hong Kong Polytechnic University Kowloon Hong Kong Chinese Academy of Sciences University of Chinese Academy of Sciences National Laboratory of Pattern Recognition Institute of Automation Beijing100190 China Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security College of Electronics and Information Engineering Shenzhen518060 China

Recently, vision transformer based multimodal learning methods have been proposed to improve the robustness of face anti-spoofing (FAS) systems. However, multimodal face data collected from the real world is often imperfect due to missing modalities from various imaging sensors. Recently, flexible-modal FAS (Yu et al. 2023) has attracted more attention, which aims to develop a unified multimodal FAS model using complete multimodal face data but is insensitive to test-time missing modalities. In this paper, we tackle one main challenge in flexible-modal FAS, i.e., when missing modality occurs either during training or testing in real-world situations. Inspired by the recent success of the prompt learning in language models, we propose Visual Prompt flexible-modal FAS (VP-FAS), which learns the modal-relevant prompts to adapt the frozen pre-trained foundation model to downstream flexible-modal FAS task. Specifically, both vanilla visual prompts and residual contextual prompts are plugged into multimodal transformers to handle general missing-modality cases, while only requiring less than 4% learnable parameters compared to training the entire model. Furthermore, missing-modality regularization is proposed to force models to learn consistent multimodal feature embeddings when missing partial modalities. Extensive experiments conducted on two multimodal FAS benchmark datasets demonstrate the effectiveness of our VP-FAS framework that improves the performance under various missing-modality cases while alleviating the requirement of heavy model re-training. © 2004-2012 IEEE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Video Compression Artifacts Removal With Spatial-Temporal Attention-Guided Enhancement

引用

IEEE Transactions on Multimedia 2024年 26卷 5657-5669页

作者： Jiang, Nanfeng Chen, Weiling Lin, Jielian Zhao, Tiesong Lin, Chia-Wen Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information Fuzhou University Fuzhou350108 China Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen University of Technology Xiamen361024 China Fujian Science and Technology Innovation Laboratory for Optoelectronic Information of China Fuzhou350116 China Department of Electrical Engineering National Tsing Hua University Hsinchu30013 Taiwan Institute of Communications Engineering National Tsing Hua University Hsinchu30013 Taiwan

Recently, many compression algorithms are applied to decrease the cost of video storage and transmission. This will introduce undesirable artifacts, which severely degrade visual quality. Therefore, Video Compression Artifacts Removal (VCAR) aims at reconstructing a high-quality video from its corrupted version of compression. Generally, this task is considered as a vision-related instead of media-related problem. In vision-related research, the visual quality has been significantly improved while the computational complexity and bitrate issues are less considered. In this work, we review the performance constraints of video coding and transfer to evaluate the VCAR outputs. Based on the analyses, we propose a Spatial-Temporal Attention-Guided Enhancement Network (STAGE-Net). First, we employ dynamic filter processing, instead of conventional optical flow method, to reduce the computational cost of VCAR. Second, we introduce self-attention mechanism to design Sequential Residual Attention Blocks (SRABs) to improve visual quality of enhanced video frames with bitrate constraints. Both quantitative and qualitative experimental results have demonstrated the superiority of our proposed method, which achieves high visual qualities and low computational costs. © 2023 IEEE.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

C2DFL: cross-view cross-layer discriminative feature learning for fine-grained 3D shape classification

引用

Neural Computing and Applications 2025年

作者： Jiang, Jinzhe Bai, Jing Ma, Xiangyu The School of Computer Science and Engineering North Minzu University Yinchuan750021 China The Key Laboratory of Images Processing and Pattern Recognition Laboratory North Minzu University Yinchuan750021 China

Fine-grained 3D shape classification poses challenges in effectively capturing and integrating discriminative features residing in subtle local regions. Previous methods typically extract features independently from individual views of 3D shapes, with a focus on various strategies for fusing these extracted view features. However, this approach neglects interview correlations and potential redundancies among different views. In this study, we introduce C2DFL, which consists of two primary modules: cross-view discriminative feature extraction (CV-DFE) and cross-layer discriminative feature fusion (CL-DFF). CV-DFE integrates discriminative features by merging inputs from multiple views, mitigating limitations associated with isolated feature extraction. CL-DFF dynamically selects key tokens using a transformer model to interactively fuse discriminative features from various levels. Extensive experiments conducted on three categories of the FG3D dataset demonstrate the exceptional efficacy of C2DFL in capturing and integrating discriminative features of 3D shapes. The proposed method achieves state-of-the-art accuracy in fine-grained 3D shape classification (FGSC). © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： 3D shape classification Cross-layer feature fusion Cross-view attention Fine-grained classification Token selection Transformer

来源：评论

学校读者我要写书评

暂无评论

RBP-Former: Joint Prediction of RNA-protein Binding Sites on Full-length RNA Transcripts for Multiple RBPs

RBP-Former: Joint Prediction of RNA-protein Binding Sites on...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Li, Yichong Liu, Xiaojian Cheng, Fan Pan, Xiaoyong Yang, Yang Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200240 China Shanghai Jiao Tong University Institute of Image Processing and Pattern Recognition Shanghai200240 China Ministry of Education of China Key Laboratory of System Control and Information Processing Shanghai200240 China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai200240 China

ISBN: (纸本)9798350386226

RNA-binding proteins (RBPs) are essential for gene expression, and the complex RNA-protein interaction mechanisms require analysis of global RNA information. Therefore, accurate prediction of RBP binding sites on full-length RNA transcripts is crucial for understanding these mechanisms and their roles in diseases. While machine learning methods can predict RBP binding to RNA fragments, extending this to full-length transcripts presents challenges due to sequence length and data imbalance. In this paper, we introduce RBP-Former, a binding site joint prediction model designed specifically for full-length RNA transcripts that can be used for multiple RBPs. This model processes information at both coarse and fine-grained levels to fully exploit sequence data and its interactions with multiple RBPs. We develop multi-level imbalance learning strategies, achieving favorable results on imbalanced data. Our method outperforms existing methods in predicting binding sites on full-length RNA transcripts for multiple RBPs, demonstrating its effectiveness in handling imbalanced label and sample distributions. © 2024 IEEE.

关键词： Binding sites

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：