检索结果-内蒙古大学图书馆

7th International Conference on Image and Graphics processing, ICIGP 2024

作者： Yang, Rui Wang, Xiao Xu, Xin Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology China School of Computer Science and Technology Wuhan University of Science and Technology China Hubei Provincial Key Laboratory of Multimedia and Network Communication Engineering Wuhan China

ISBN: (纸本)9798400716720

Magnetic Resonance Imaging (MRI) is an invaluable tool for brain tumor segmentation. However, in clinical practice, certain modalities might be unavailable, leading to potential performance degradation in prediction tasks. According to current implementations, different modalities are treated as independent entities during the feature extraction phase, ignoring their inherent complementary nature. In this paper, inspired by knowledge distillation techniques, we introduce the Fusion-Inspired Modality Distillation (FIMD) framework. FIMD leverages the output from a fused multi-modal model as a teacher to guide the training of individual modalities. Each modality benefits from the collective knowledge of all modalities, enhancing its performance. Our FIMD method, devoid of specific architectural constraints, seamlessly integrates into existing multi-modal brain tumor segmentation frameworks. Notably, extensive experiments on BraTS2020, BraTS2018, and BraTS2015 datasets indicate that FIMD can enhance the performance of current state-of-the-art (SOTA) algorithms on Dice by an average of 0.55-1.60%. Especially in the case of missing modalities, the effectiveness of the FIMD framework in enhancing the robustness and accuracy of brain tumor segmentation is demonstrated. © 2024 ACM.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Spatio-Temporal Transformer for Enhancing the Coherence on 3D Human Motion Prediction 18th

A Spatio-Temporal Transformer for Enhancing the Coherence ...

引用

18th Chinese Conference on Biometric Recognition, CCBR 2024

作者： Xie, Miner Wang, Lei Liu, Feng College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (纸本)9789819610709

Human motion prediction is of great importance for artificial intelligence systems, particularly in fields like autonomous driving and human-computer interaction. Existing methods have achieved good results in simple motions with small changes but still struggle with coherence in predicting complex motions with large changes in a short time. Regarding the issue in current methods, this paper proposes a novel network composed of three modules: spatial encoders that captures correlations between joints, temporal encoders that models the movement patterns of joints across frames, and a multi-frame temporal encoder that learns high-level temporal correlations to enhance prediction coherence. In addition, we propose to use Weighted Mean Per-Joint Position Error (WMPJPE) as the loss function by considering that different joints of the human skeleton have different effects on the entire action. We evaluate our method on the Human3.6M, AMASS, and 3DPW datasets. The quantitative results indicate that our method notably outperforms other methods in the prediction range of 160ms to 560ms. The qualitative results show that our method can improve the coherence of prediction. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge 38

FreqBlender: Enhancing DeepFake Detection by Blending Freque...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Li, Hanzhe Zhou, Jiaran Li, Yuezun Wu, Baoyuan Li, Bin Dong, Junyu School of Computer Science and Technology Ocean University of China China School of Data Science The Chinese University of Hong Kong Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

Generating synthetic fake faces, known as pseudo-fake faces, is an effective way to improve the generalization of DeepFake detection. Existing methods typically generate these faces by blending real or fake faces in spatial domain. While these methods have shown promise, they overlook the simulation of frequency distribution in pseudo-fake faces, limiting the learning of generic forgery traces in-depth. To address this, this paper introduces FreqBlender, a new method that can generate pseudo-fake faces by blending frequency knowledge. Concretely, we investigate the major frequency components and propose a Frequency Parsing Network to adaptively partition frequency components related to forgery traces. Then we blend this frequency knowledge from fake faces into real faces to generate pseudo-fake faces. Since there is no ground truth for frequency components, we describe a dedicated training strategy by leveraging the inner correlations among different frequency knowledge to instruct the learning process. Experimental results demonstrate the effectiveness of our method in enhancing DeepFake detection, making it a potential plug-and-play strategy for other methods. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep semantic network for hyperspectral image classification using enhanced bifurcation and light self-Gaussian attention mechanism

引用

Journal of Applied Remote Sensing 2025年第1期19卷

作者： Wan, Xiaoqing Chen, Feng He, Yupeng Hengyang Normal University College of Computer Science and Technology Hengyang China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang China

Convolutional neural networks (CNNs) are widely used in hyperspectral image (HSI) classification due to their strong feature extraction capabilities. Nevertheless, CNN-based classification methods face challenges in capturing deep semantic features effectively, and as the number of layers increases, computational expenses escalate significantly. In addition, spatial locations and spectral bands in HSI data have varying discriminative power. To address these challenges, we propose a novel approach, DSNet, which integrates a multiway attention mechanism with a CNN-based deep semantic network to improve HSI classification. First, we extract shallow abstract features using a module that combines 3D and 2D convolution layers, followed by transformation through a Gaussian-weighted feature tokenizer. Second, we introduce an enhanced bifurcation attention mechanism with dynamically adjustable perceptual ranges to capture spatial semantic information from both horizontal and vertical perspectives. Third, a convolutional multilayer perceptron module is employed to extract high-level feature representations in both spatial and spectral dimensions, which are then refined by a light self-Gaussian attention module. Finally, a linear layer is used to determine the sample labels. Experiments conducted on three publicly available hyperspectral datasets illustrate that the proposed DSNet achieves superior performance compared with several contemporary state-of-the-art methods, even when trained with limited samples. © 2025 Society of Photo-Optical Instrumentation Engineers (SPIE).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Nonlinear Adaptive Manifold Learning for Global and Local information

引用

Tsinghua Science and technology 2021年第2期26卷 163-171页

作者： Jiajun Gao Fanzhang Li Bangjun Wang Helan Liang School of Computer Science and Technology Soochow UniversitySuzhou 215006China Joint International Research Laboratory of Machine Learning and Neuromorphic Computing Provincial Key Laboratory for Computer Information Processing TechnologySoochow UniversitySuzhou 215006China

In this paper,we propose an Unsupervised Nonlinear Adaptive Manifold Learning method(UNAML)that considers both global and local *** this approach,we apply unlabeled training samples to study nonlinear manifold features,while considering global pairwise distances and maintaining local topology *** method aims at minimizing global pairwise data distance errors as well as local structural *** order to enable our UNAML to be more efficient and to extract manifold features from the external source of new data,we add a feature approximate error that can be used to learn a linear ***,we add a feature approximate error that can be used to learn a linear *** addition,we use a method of adaptive neighbor selection to calculate local structural *** paper uses the kernel matrix method to optimize the original *** algorithm proves to be more effective when compared with the experimental results of other feature extraction methods on real face-data sets and object data sets.

关键词： unsupervised manifold learning global and local information,adaptive neighbor selection method kernel matrix

来源：评论

学校读者我要写书评

暂无评论

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion 38

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent D...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Zeng, Yu Zhang, Yang Liu, Jiachen Shen, Linlin Deng, Kaijun He, Weizhao Wang, Jinbao Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lightweight 6-bit S-boxes with DPA Resistance

引用

IEEE Transactions on Network Science and Engineering 2025年

作者： Yan, Liuyan Li, Lang Song, Qingling Hengyang Normal University College of Computer Science and Technology Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002 China

Lightweight S-boxes have a significant impact on cryptographic algorithms for resource-constrained devices in the Internet of Things (IoT). Previous research on such S-oxes has focused on low area and good cryptographic properties, which neglects the resistance to side-channel analysis, especially differential power analysis (DPA). The reVisited transparency order (VTO) is one of the best indicators for evaluating S-boxes against DPA attacks so far. Therefore, this paper presents a scheme for designing 6-bit S-boxes. The designed S-boxes are suitable for lightweight block ciphers and have a certain ability to resist DPA attacks. Specifically, we first identify 23 3-bit S-boxes with the optimal cryptographic properties and the smallest hardware area through systematic screening. Then, the paper investigates the constructions of lightweight 6-bit S-boxes based on traditional algorithm structures. Finally, a novel structure named F-LM-F is proposed for designing lightweight 6-bit S-boxes by combining Feistel structure and Lai-Massey structure. It has been proven through comparison that the S-boxes under F-LM-F structure achieve fewer fixed points and lower VTO than the 6-bit S-box of BipBip cipher, with a 17.61% reduction in hardware area and a 13.58% decrease in CPU cycles © 2013 IEEE.

关键词： Side channel attack

来源：评论

学校读者我要写书评

暂无评论

OCTAMamba: A State-Space Model Approach for Precision OCTA Vasculature Segmentation

OCTAMamba: A State-Space Model Approach for Precision OCTA V...

引用

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

作者： Zou, Shun Zhang, Zhuo Gao, Guangwei College of Artificial Intelligence Nanjing Agricultural University Nanjing China College of Computer Science and Technology National University of Defense Technology Changsha China Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou China

ISBN: (纸本)9798350368741

Optical Coherence Tomography Angiography (OCTA) is a crucial imaging technique for visualizing retinal vasculature and diagnosing eye diseases such as diabetic retinopathy and glaucoma. However, precise segmentation of OCTA vasculature remains challenging due to the multi-scale vessel structures and noise from poor image quality and eye lesions. In this study, we proposed OCTAMamba, a novel U-shaped network based on the Mamba architecture, designed to segment vasculature in OCTA accurately. OCTAMamba integrates a Quad Stream Efficient Mining Embedding Module for local feature extraction, a Multi-Scale Dilated Asymmetric Convolution Module to capture multi-scale vasculature, and a Focused Feature Recalibration Module to filter noise and highlight target areas. Our method achieves efficient global modeling and local feature extraction while maintaining linear complexity, making it suitable for low-computation medical applications. Extensive experiments on the OCTA 3M, OCTA 6M, and ROSSA datasets demonstrated that OCTAMamba outperforms state-of-the-art methods, providing a new reference for efficient OCTA segmentation. Code is available at https://***/zs1314/OCTAMamba. © 2025 IEEE.

关键词： Mamba OCTA image State Space Model

来源：评论

学校读者我要写书评

暂无评论

A Multi-Stage Goal-Driven Network for Pedestrian Trajectory Prediction 5

A Multi-Stage Goal-Driven Network for Pedestrian Trajectory ...

引用

5th International Conference on computer Vision, Image and Deep Learning, CVIDL 2024

作者： Wu, Xiuen Wang, Tao Cai, Yuanzheng Liang, Lingyu Papageorgiou, George Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou China Fuzhou University College of Computer and Data Science Fuzhou China South China University of Technology School of Electronic and Information Engineering Guangzhou China European University Cyprus Department of Computer Science and Engineering Nicosia Cyprus

ISBN: (纸本)9798350373820

Pedestrian trajectory prediction plays a pivotal role in ensuring the safety and efficiency of various applications, including autonomous vehicles and traffic management systems. This paper proposes a novel method for pedestrian trajectory prediction, called multi-stage goal-driven network (MGNet). Diverging from prior approaches relying on stepwise recursive prediction and the singular forecasting of a long-term goal, MGNet directs trajectory generation by forecasting intermediate stage goals, thereby reducing prediction errors. The network comprises three main components: a conditional variational autoencoder (CVAE), an attention module, and a multi-stage goal evaluator. Trajectories are encoded using conditional variational autoencoders to acquire knowledge about the approximate distribution of pedestrians' future trajectories, and combined with an attention mechanism to capture the temporal dependency between trajectory sequences. The pivotal module is the multi-stage goal evaluator, which utilizes the encoded feature vectors to predict intermediate goals, effectively minimizing cumulative errors in the recursive inference process. The effectiveness of MGNet is demonstrated through comprehensive experiments on the JAAD and PIE datasets. Comparative evaluations against state-of-the-art algorithms reveal significant performance improvements achieved by our proposed method. © 2024 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

NEAT-Net: An Unsupervised Cross-View Prior Inpainting Network for CBCT Metal Artifact Reduction 46

NEAT-Net: An Unsupervised Cross-View Prior Inpainting Networ...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Yang, Yang Tong, Zhan Zhong, Xinyun Shi, Yijie Xi, Yan Yu, Wenxue Wu, Zhan Chen, Yang First-Imaging Tech Shanghai China Southeast University Laboratory of Image Science and Technology The School of Computer Science and Engineering Nanjing China Southeast University Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing The Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Nanjing China

ISBN: (纸本)9798350371499

Intraoperative Cone-Beam Computed Tomography (CBCT) facilitates intraoperative navigation for Minimally Invasive Spine Surgery (MISS). However, high-attenuation metal implants used in MISS often cause metal artifacts in the reconstructed CBCT images. Current algorithms do not consider the cross-view information in the projection-domain for metal artifact reduction (MAR). Inaccurate projection-domain inpainting results in CBCT MAR lead to tissue blurring and secondary artifacts, significantly compromising the accuracy of CBCT-guided MISS and increasing surgical risks. To address the above challenge, in this paper, we propose a novel unsupervised cross-view prior inpainting network for CBCT Metal Artifact Reduction named NEAT-Net. Firstly, a cross-view prior multi-scale inpainting module is constructed to learn the inter-view complementary information. Secondly, a hybrid feature attention module is proposed to adaptively fuse cross-view features. In addition, an unsupervised training approach is proposed to directly learn from metal-affected data. Extensive experiments are conducted to verify the effectiveness of our algorithm on a real clinical dataset. © 2024 IEEE.

关键词： computerized tomography

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：