检索结果-内蒙古大学图书馆

End-to-End Paired Ambisonic-Binaural Audio Rendering

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 502-513页

作者： Yin Zhu Qiuqiang Kong Junjie Shi Shilei Liu Xuzhou Ye Ju-Chiang Wang Hongming Shan Junping Zhang Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China Beijing ByteDance Technology Co.Ltd. Shanghai 201102China. Chinese University of Hong Kong Hong KongChina IEEE Institute of Science and Technology for Brain-Inspired Intelligence and MOE Frontiers Center for Brain Science Fudan UniversityShanghai 200433 Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai 200031China

Binaural rendering is of great interest to virtual reality and immersive media. Although humans can naturally use their two ears to perceive the spatial information contained in sounds, it is a challenging task for machines to achieve binaural rendering since the description of a sound field often requires multiple channels and even the metadata of the sound sources. In addition, the perceived sound varies from person to person even in the same sound field. Previous methods generally rely on individual-dependent head-related transferred function(HRTF)datasets and optimization algorithms that act on HRTFs. In practical applications, there are two major drawbacks to existing methods. The first is a high personalization cost, as traditional methods achieve personalized needs by measuring HRTFs. The second is insufficient accuracy because the optimization goal of traditional methods is to retain another part of information that is more important in perception at the cost of discarding a part of the information. Therefore, it is desirable to develop novel techniques to achieve personalization and accuracy at a low cost. To this end, we focus on the binaural rendering of ambisonic and propose 1) channel-shared encoder and channel-compared attention integrated into neural networks and 2) a loss function quantifying interaural level differences to deal with spatial information. To verify the proposed method, we collect and release the first paired ambisonic-binaural dataset and introduce three metrics to evaluate the content information and spatial information accuracy of the end-to-end methods. Extensive experimental results on the collected dataset demonstrate the superior performance of the proposed method and the shortcomings of previous methods.

关键词： Ambisonic attention binaural rendering neural network

来源：评论

学校读者我要写书评

暂无评论

Decoding Musical Neural Activity in Patients With Disorders of Consciousness Through Self-Supervised Contrastive Domain Generalization

引用

IEEE Transactions on Affective Computing 2024年第2期16卷 726-743页

作者： Cai, Honghua Pan, Jiahui Xiao, Qiuyi Jin, Jiarui Li, Yuanqing Xie, Qiuyou South China Normal University School of Software Foshan528225 China South China University of Technology School of Automation Science and Engineering Guangzhou510640 China Southern Medical University Zhujiang Hospital Guangzhou510260 China South China University of Technology Center for Brain-Computer Interfaces and Brain Information Processing Guangzhou510640 China Pazhou Lab Guangzhou510330 China

Identifying the brain responses of patients with disorders of consciousness (DOCs), which include comas, vegetative states (VSs, also called unresponsive wakefulness syndrome (UWS)) and minimally conscious states (MCSs), based on electroencephalography (EEG) has important clinical diagnosis implications. However, due to impaired motor and cognitive abilities, patients with DOCs may not be able to express their feelings and their brain responses to different stimuli, making it difficult to correctly label data. EEG classification algorithms trained with these data cannot make reliable classifications and predictions for clinical diagnosis purposes. To identify the brain responses produced for different types of stimuli in patients with DOCs, we proposed a self-supervised contrastive domain generalization framework (SSCDG) for cross-subject EEG classification. The model was first trained with healthy-subject EEG data induced by different stimuli to learn their corresponding unsupervised representations. Then, we used these representations to train a classifier to predict the emotional states of patients with DOCs under the corresponding stimuli. SSCDG was first evaluated on the SEED dataset, and it achieved an accuracy of 87.6%, which was 1.1% higher than that of the state-of-the-art (SOTA) approaches. Moreover, the SSCDG method was utilized to categorize EEG data acquired from seventeen DOC patients, including eleven in a UWS state and six in an MCS state, with seven patients demonstrating notable accuracy in three-class EEG classification tasks. The SSCDG results indicated that the seven patients with DOCs may have shown classifiable EEG responses to the presented stimuli. © 2010-2012 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Meta Ordinal Regression Forest for Medical Image Classification With Ordinal Labels

引用

IEEE/CAA Journal of Automatica Sinica 2022年第7期9卷 1233-1247页

作者： Yiming Lei Haiping Zhu Junping Zhang Hongming Shan Shanghai Key Laboratory of Intelligent Information Processing the School of Computer ScienceFudan UniversityShanghai 200433China with Huawei Shanghai 200120China Institute of Science and Technology for Brain-Inspired Intelligence and MOE Frontiers Center for Brain Science Fudan UniversityShanghai 200433 Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai 200031China IEEE

The performance of medical image classification has been enhanced by deep convolutional neural networks(CNNs),which are typically trained with cross-entropy(CE)***,when the label presents an intrinsic ordinal property in nature,e.g.,the development from benign to malignant tumor,CE loss cannot take into account such ordinal information to allow for better *** improve model generalization with ordinal information,we propose a novel meta ordinal regression forest(MORF)method for medical image classification with ordinal labels,which learns the ordinal relationship through the combination of convolutional neural network and differential forest in a meta-learning *** merits of the proposed MORF come from the following two components:A tree-wise weighting net(TWW-Net)and a grouped feature selection(GFS)***,the TWW-Net assigns each tree in the forest with a specific weight that is mapped from the classification loss of the corresponding ***,all the trees possess varying weights,which is helpful for alleviating the tree-wise prediction ***,the GFS module enables a dynamic forest rather than a fixed one that was previously used,allowing for random feature *** training,we alternatively optimize the parameters of the CNN backbone and TWW-Net in the meta-learning framework through calculating the Hessian *** results on two medical image classification datasets with ordinal labels,i.e.,LIDC-IDRI and Breast Ultrasound datasets,demonstrate the superior performances of our MORF method over existing state-of-the-art methods.

关键词： Terms-Convolutional neural network(CNNs) medical image classification meta-learning ordinal regression random forest

来源：评论

学校读者我要写书评

暂无评论

Denoising Diffusion Path: Attribution Noise Reduction with An Auxiliary Diffusion Model 38

Denoising Diffusion Path: Attribution Noise Reduction with A...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Lei, Yiming Li, Zilong Zhang, Junping Shan, Hongming Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University China Institute of Science and Technology for Brain-Inspired Intelligence MOE Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence MOE Frontiers Center for Brain Science Fudan University China

The explainability of deep neural networks (DNNs) is critical for trust and reliability in AI systems. Path-based attribution methods, such as integrated gradients (IG), aim to explain predictions by accumulating gradients along a path from a baseline to the target image. However, noise accumulated during this process can significantly distort the explanation. While existing methods primarily concentrate on finding alternative paths to circumvent noise, they overlook a critical issue: intermediate-step images frequently diverge from the distribution of training data, further intensifying the impact of noise. This work presents a novel Denoising Diffusion Path (DDPath) to tackle this challenge by harnessing the power of diffusion models for denoising. By exploiting the inherent ability of diffusion models to progressively remove noise from an image, DDPath constructs a piece-wise linear path. Each segment of this path ensures that samples drawn from a Gaussian distribution are centered around the target image. This approach facilitates a gradual reduction of noise along the path. We further demonstrate that DDPath adheres to essential axiomatic properties for attribution methods and can be seamlessly integrated with existing methods such as IG. Extensive experimental results demonstrate that DDPath can significantly reduce noise in the attributions-resulting in clearer explanations-and achieves better quantitative results than traditional path-based 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

Prompt learning in computer vision: a survey

引用

Frontiers of information Technology & Electronic Engineering 2024年第1期25卷 42-63页

作者： Yiming LEI Jingqi LI Zilong LI Yuan CAO Hongming SHAN Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200438China Institute of Science and Technology for Brain-Inspired Intelligence Fudan UniversityShanghai 200433China MOE Frontiers Center for Brain Science Fudan UniversityShanghai 200433China Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai 201210China

Prompt learning has attracted broad attention in computer vision since the large pre-trained visionlanguagemodels (VLMs) exploded. Based on the close relationship between vision and language information builtby VLM, prompt learning becomes a crucial technique in many important applications such as artificial intelligencegenerated content (AIGC). In this survey, we provide a progressive and comprehensive review of visual promptlearning as related to AIGC. We begin by introducing VLM, the foundation of visual prompt learning. Then, wereview the vision prompt learning methods and prompt-guided generative models, and discuss how to improve theefficiency of adapting AIGC models to specific downstream tasks. Finally, we provide some promising researchdirections concerning prompt learning.

关键词： Prompt learning Visual prompt tuning(VPT) Image generation Image classification Artificial intelligence generated content(AIGC)

来源：评论

学校读者我要写书评

暂无评论

Fan-Net: Fourier-Based Adaptive Normalization for Cross-Domain Stroke Lesion Segmentation 48

Fan-Net: Fourier-Based Adaptive Normalization for Cross-Doma...

引用

48th IEEE International Conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Yu, Weiyi Lei, Yiming Shan, Hongming Fudan University School of Computer Science Shanghai Key Lab of Intelligent Information Processing Shanghai200433 China Institute of Science and Technology for Brain-Inspired Intelligence China Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai201210 China

ISBN: (纸本)9781728163277

Since stroke is the main cause of various cerebrovascular diseases, deep learning-based stroke lesion segmentation on magnetic resonance (MR) images has attracted considerable attention. However, the existing methods often neglect the domain shift among MR images collected from different sites, which has limited performance improvement. To address this problem, we intend to change style information without affecting high-level semantics via adaptively changing the low-frequency amplitude components of the Fourier transform so as to enhance model robustness to varying domains. Thus, we propose a novel FAN-Net, a U-Net-based segmentation network incorporated with a Fourier-based adaptive normalization (FAN) and a domain classifier with a gradient reversal layer. The FAN module is tailored for learning adaptive affine parameters for the amplitude components of different domains, which can dynamically normalize the style information of source images. Then, the domain classifier provides domain-agnostic knowledge to endow FAN with strong domain generalizability. The experimental results on the ATLAS dataset, which consists of MR images from 9 sites, show the superior performance of the proposed FAN-Net compared with baseline methods. © 2023 IEEE.

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

Extending generalized unsupervised manifold alignment

引用

Science China(information Sciences) 2022年第7期65卷 139-156页

作者： Xiaoyi YIN Zhen CUI Hong CHANG Bingpeng MA Shiguang SHAN Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences School of Computer Science and Engineering Nanjing University of Science and Technology CAS Center for Excellence in Brain Science and Intelligence Technology

Building connections between different data sets is a fundamental task in machine learning and related application community. With proper manifold alignment, the correspondences between data sets will assist us with comprehensive study of data processes and analyses. Despite the several progresses in semi-supervised and unsupervised scenarios, potent manifold alignment methods in generalized and realistic circumstances remain in absence. Besides, theretofore unsupervised algorithms seldom prove themselves mathematically. In this paper, we devise an efficient method to properly solve the unsupervised manifold alignment problem and denominate it as extending generalized unsupervised manifold alignment(EGUMA)method. More specifically, an explicit relaxed integer programming method is adopted to solve the unsupervised manifold alignment problem, which reconciles three factors covering the updated local structure matching, the the feature comparability and geometric preservation. An additional effort is retained on extending the Frank Wolfe algorithm to tacking our optimization problem. Besides our previous endeavors we adopt a new strategy for neighborhood discovery in the manifolds. The main advantages over previous methods accommodate(1) simultaneous alignment and discovery of manifolds;(2) complete unsupervised learning structure without any prerequisite correspondence;(3) more concise local geometry for the embedding space;(4) efficient alternative optimization;(5) strict mathematical analysis on the convergence and efficiency issues. Experiments on real-world applications verify the high accuracy and efficiency of our proposed method.

关键词： unsupervised manifold alignment relaxed integer programming Frank Wolfe algorithm

来源：评论

学校读者我要写书评

暂无评论

Radiologist-in-the-Loop Self-Training for Generalizable CT Metal Artifact Reduction

引用

IEEE Transactions on Medical Imaging 2025年第6期44卷 2504-2514页

作者： Ma, Chenglong Li, Zilong Li, Yuanlin Han, Jing Zhang, Junping Zhang, Yi Liu, Jiannan Shan, Hongming Fudan University Institute of Science and Technology for Brain-inspired Intelligence Moe Frontiers Center for Brain Science Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Shanghai200433 China Fudan University Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Shanghai200433 China Shanghai Ninth People's Hospital Department of Oral Maxillofacial Head and Neck Oncology China Shanghai Jiao Tong University School of Medicine College of Stomatology China Shanghai Key Laboratory of Stomatology Shanghai Research Institute of Stomatology National Center for Stomatology National Clinical Research Center for Oral Diseases Shanghai200011 China Sichuan University School of Cyber Science and Engineering Chengdu Sichuan610065 China

Metal artifacts in computed tomography (CT) images can significantly degrade image quality and impede accurate diagnosis. Supervised metal artifact reduction (MAR) methods, trained using simulated datasets, often struggle to perform well on real clinical CT images due to a substantial domain gap. Although state-of-the-art semi-supervised methods use pseudo ground-truths generated by a prior network to mitigate this issue, their reliance on a fixed prior limits both the quality and quantity of these pseudo ground-truths, introducing confirmation bias and reducing clinical applicability. To address these limitations, we propose a novel radiologist-in-the-loop self-training framework for MAR, termed RISE-MAR, which can integrate radiologists' feedback into the semi-supervised learning process, progressively improving the quality and quantity of pseudo ground-truths for enhanced generalization on real clinical CT images. For quality assurance, we introduce a clinical quality assessor model that emulates radiologist evaluations, effectively selecting high-quality pseudo ground-truths for semi-supervised training. For quantity assurance, our self-training framework iteratively generates additional high-quality pseudo groundtruths, expanding the clinical dataset and further improving model generalization. Extensive experimental results on multiple clinical datasets demonstrate the superior generalization performance of our RISE-MAR over state-of-the-art methods, advancing the development of MAR models for practical application. © 2025 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

DMNER: Biomedical Named Entity Recognition by Detection and Matching

DMNER: Biomedical Named Entity Recognition by Detection and ...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Bian, Junyi Jiang, Rongze Zhai, Weiqi Huang, Tianyang Huang, Xiaodi Zhou, Hong Zhu, Shanfeng Fudan University School of Computer Science Shanghai China Fudan University Institute of Science and Technology for Brain-Inspired Intelligence Shanghai China Charles Sturt University School of Computing Mathematics and Engineering Nsw Australia Atypon Systems Llc United Kingdom Zhangjiang Fudan International Innovation Center Fudan University Institute of Science and Technology for Brain-Inspired Intelligence Moe Frontiers Center for Brain Science Shanghai Key Lab of Intelligent Information Processing Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Shanghai China

ISBN: (纸本)9798350386226

Biomedical Named Entity Recognition (NER) is a crucial task in extracting information from biomedical texts. However, the diversity of professional terminology, semantic complexity, and the widespread presence of synonyms pose significant challenges. Traditional methods that rely on sequence labeling training datasets often struggle to handle these complexities. To address this, we introduce a novel framework for BioNER, termed DMNER, which leverages external knowledge and operates in two steps: entity boundary detection and entity category identification through matching. The core of DMNER is its second step, which determines the entity category by retrieving similar entities and their categories from a knowledge dictionary using semantic similarity matching. Our experiments on 10 biomedical datasets demonstrate that DMNER outperforms baselines across these tasks, proving its effectiveness and adaptability. DMNER is versatile and can be applied to various NER tasks, including supervised NER, distantly supervised NER, and NER on multiple datasets with disjoint label sets. The DMNER code is publicly available. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

TaMMa: Target-driven Multi-subscene Mobile Manipulation 8

TaMMa: Target-driven Multi-subscene Mobile Manipulation

引用

8th Conference on Robot Learning, CoRL 2024

作者： Hou, Jiawei Wang, Tianyu Pan, Tongying Wang, Shouyan Xue, Xiangyang Fu, Yanwei School of Computer Science Fudan University China Institute of Science and Technology for Brain-Inspired Intelligence Fudan University China School of Data Science Fudan University China Fudan ISTBI-ZJNU Algorithm Centre for Brain-inspired Intelligence Shanghai Key Lab of Intelligent Information Processing Technology Innovation Center of Calligraphy and Painting Digital Generation Ministry of Culture and Tourism China

For everyday service robotics, the ability to navigate back and forth based on tasks in multi-subscene environments and perform delicate manipulations is crucial and highly practical. While existing robotics primarily focus on complex tasks within a single scene or simple tasks across scalable scenes individually, robots consisting of a mobile base with a robotic arm face the challenge of efficiently representing multiple subscenes, coordinating the collaboration between the mobile base and the robotic arm, and managing delicate tasks in scalable environments. To address this issue, we propose Target-driven Multi-subscene Mobile Manipulation (TaMMa), which efficiently handles mobile base movement and fine-grained manipulation across subscenes. Specifically, we obtain a reliable 3D Gaussian initialization of the whole scene using a sparse 3D point cloud with encoded semantics. Through querying the coarse Gaussians, we acquire the approximate pose of the target, navigate the mobile base to approach it, and reduce the scope of precise target pose estimation to the corresponding subscene. Optimizing while moving, we employ diffusion-based depth completion to optimize fine-grained Gaussians and estimate the target's refined pose. For target-driven manipulation, we adopt Gaussians inpainting to obtain precise poses for the origin and destination of the operation in an imagine before you do it manner, enabling fine-grained manipulation. We conduct various experiments on a real robotic to demonstrate our method in effectively and efficiently achieving precise operation tasks across multiple tabletop subscenes. © 2024 Proceedings of Machine Learning Research.

关键词： Gaussian distribution

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：