检索结果-内蒙古大学图书馆

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

作者： Youhong Peng Weixing Xie Jinwen Li Shaoqi Wu Zefeng Wang Bingbing Hu Junfeng Yao Center for Digital Media Computing School of Film School of Informatics Xiamen University China National Institute for Data Science in Health and Medicine Xiamen University China Ministry of Culture and Tourism Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Recent deformable 3D Gaussians methods achieve high-quality reconstruction and real-time rendering. However, they require multi-view information and are not applicable to single-view dynamic scenes captured from mobile phones. Additionally, the high-dimensional hidden layer of deformation MLP and the excessive number of Gaussian primitives and attributes impose significant storage pressure, greatly limiting their practical application. To address the issues, we propose a novel Lightweight Deformable 3D Gaussians teacher-student framework. Specifically, we initialize Gaussian primitives with an initialization strategy designed for single-view scenes, and then optimize the teacher model using color and depth information. For the trained teacher model, we distill deformation MLP, prune Gaussian primitives and Gaussian attributes, and finally obtain a student model with low storage and high efficiency. Public benchmark experiments demonstrate the effectiveness of our framework, showing a compression rate exceeding 4× while maintaining satisfactory rendering quality. Project page: https://***/ldg/.

关键词： Deformable models Training Three-dimensional displays Deformation Memory management Color Rendering (computer graphics) Real-time systems Mobile handsets Speech processing

来源：评论

学校读者我要写书评

暂无评论

PostoMETRO: Pose Token Enhanced Mesh Transformer for Robust 3D Human Mesh Recovery

PostoMETRO: Pose Token Enhanced Mesh Transformer for Robust ...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Wendi Yang Zihang Jiang Shang Zhao S. Kevin Zhou Division of Life Sciences and Medicine School of Biomedical Engineering University of Science and Technology of China (USTC) Hefei Anhui China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) Suzhou Institute for Advance Research USTC Suzhou Jiangsu China Key Laboratory of Precision and Intelligent Chemistry USTC Hefei Anhui China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

With the recent advancements in single-image-based 3D human pose and shape estimation (3DHPSE), there is a growing amount of works that can achieve good results on standard benchmarks but struggle to yield accurate hu-man mesh in extreme scenarios like occlusion. Previous works propose to leverage 2D poses to help 3D HPSE model improve performance under occlusion, but usually rely on manual design to integrate 2D poses and only aim for specific kinds of occlusion. In this paper, we present PostoMETRO (Pose token enhanced MEsh TRansfOrmer), which integrates 2D pose prior knowledge as tokens into transformers to improve model's performance under occlusion. Using a VQ- VAE-based pose tokenizer; we efficiently represent 2D poses as tokens andfeed them to transformers together with image tokens. Subsequently, these tokens are queried by vertex andJoint tokens to decode 3D coordinates of mesh vertices and human Joints. Our proposed 2D poses integration strategy is manual-design-free and suitable for various kinds of occlusion. Experiments on both standard and occlusion-specific benchmarks demonstrate the effectiveness of PostoMETRO. Code will be made available 1 1 https://***/PostoMETRO/PostoMETRO-Paper.

关键词： Solid modeling Computer vision Three-dimensional displays Shape Estimation Manuals Benchmark testing Transformers Robustness Standards

来源：评论

学校读者我要写书评

暂无评论

Emotional Knowledge Self-Distillation in Dialogue

Emotional Knowledge Self-Distillation in Dialogue

引用

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

作者： Zhongquan Jian Yancheng Wang Weichao Wu Junfeng Yao Meihong Wang Qingqiang Wu School of Informatics Xiamen University Xiamen China School of Computing and Data Science Xiamen University Malaysia Selangor Malaysia School of Mechanics and Civil Engineering China University of Mining & Technology Beijing China School of Film Xiamen University Xiamen China Xiamen Key Laboratory of Intelligent Storage and Computing School of Informatics Xiamen University Xiamen China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism Xiamen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Recognizing emotions in dialogues is vital for effective human-computer interaction, yet remains a challenging task in Natural Language processing (NLP). Previous studies in Emotion Recognition in Conversation (ERC) have primarily focused on contextual features, while overlooking the importance of emotional features in emotion recognition. To address this gap, we focus on the role of emotional features in ERC and propose a novel method, Emotional Knowledge Self-Distillation (EmoKSD 1 ), to enhance the model’s emotional sensitivity. In EmoKSD, utterances are enriched with implicit ⟨mask⟩ tokens to represent conveyed emotions, allowing the distillation of emotional knowledge from explicit emotional tokens to implicit ⟨mask⟩ tokens, thereby enhancing the model’s ability to perceive subtle emotions within the dialogue. Through thorough evaluations on two public ERC datasets (i.e., IEMOCAP and MELD) using proposed coarse-grained utterance distillation and fine-grained token distillation techniques, EmoKSD demonstrates superior performance compared to existing methods, highlighting the significance of emotional features in ERC.

关键词： Representation learning Human computer interaction Emotion recognition Sensitivity Speech recognition Signal processing Natural language processing Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

EDA: Enhanced Domain-Adversarial Training for Anatomical Landmark Detection

EDA: Enhanced Domain-Adversarial Training for Anatomical Lan...

引用

IEEE International Symposium on Biomedical imaging

作者： Fan Yang S. Kevin Zhou School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Hefei Anhui China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou Jiangsu China Key Laboratory of Precision and Intelligent Chemistry USTC Hefei Anhui China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Manually annotating anatomical landmarks in medical images requires experienced clinicians and is a labor-intensive process. However, recent AI-assisted methods for landmark detection often rely on the training and test data originating from the same domain. This work introduces a novel unsupervised domain adaptation (UDA) framework aimed at anatomical landmark detection from a medical image, designed to bridge the gap between a source domain with labels and an unlabeled target domain. Specifically, we have developed a new Domain-Adversarial Network that incorporates skip connections to transfer and fuse high-resolution feature maps. Additionally, we proposed Dynamic Gaussian Learning, which allows the model to escape from local error regions. We carry out experiments on landmark detection for both head and chest, and the results demonstrate that our method achieves state-of-the-art performances in each experiment.

关键词： Training Measurement Adaptation models Three-dimensional displays Smoothing methods Head Kernel Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

PD-SDF: Dynamic Surface Reconstruction Based on Plane Decomposition for Single View RGB-D Videos

PD-SDF: Dynamic Surface Reconstruction Based on Plane Decomp...

引用

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

作者： Jinwen Li Weixing Xie Junfeng Yao Shaoqi Wu Youhong Peng Mengyuan Ge Xiao Dong Center for Digital Media Computing School of Film School of Informatics Xiamen University National Institute for Data Science in Health and Medicine Xiamen University Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism Jiujiang Research Institute of Xiamen University Jiujiang China Guangdong Provincial/Zhuhai Key Laboratory of IRADS BNU-HKBU United International College Zhuhai China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Surface reconstruction of dynamic scenes from single view videos is a challenging task due to the highly ill-posed and under-constrained nature. Existing single view reconstruction methods suffer from severe quality issues, such as surface distortion and mesh adherison. In this paper, we propose an efficient dynamic representation network, PD-SDF, which consists of a 4D motion field and a 3D geometry field. The explicit disentanglement of motion and geometry based on planar factorization guarantees the mesh consistency across frames. Specifically, to address the mesh adhesion problem, we design a depth-guided sampling strategy to focus on optimizing the SDF field near the object surface. Due to insufficient geometric cues, we design various regularization strategies to constrain smoothness and topological correcness of the scene geometry. Extensive experiments show that our method outperforms existing methods in both appearance and geometry reconstruction. The project page: https://***/

关键词： Geometry Training Surface reconstruction Three-dimensional displays Noise Reconstruction algorithms Stability analysis Speech processing Surface treatment Videos

来源：评论

学校读者我要写书评

暂无评论

MS-Glance: Bio-Inspired Non-Semantic Context Vectors and Their Applications in Supervising Image Reconstruction

MS-Glance: Bio-Inspired Non-Semantic Context Vectors and The...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Ziqi Gao Wendi Yang Yujia Li Lei Xing S. Kevin Zhou Division of Life Sciences and Medicine School of Biomedical Engineering University of Science and Technology of China (USTC) Hefei Anhui China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) Suzhou Institute for Advance Research USTC Suzhou Jiangsu China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology China Department of Radiation Oncology Stanford University Stanford CA USA Key Laboratory of Precision and Intelligent Chemistry USTC CAS Hefei Anhui

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Non-semantic context information is crucial for visual recognition, as the human visual perception system first uses global statistics to process scenes rapidly before identifying specific objects. However, while semantic information is increasingly incorporated into computer vision tasks such as image reconstruction, non-semantic information, such as global spatial structures, is often overlooked. To bridge the gap, we propose a biologically informed non-semantic context descriptor, MS-Glance, along with the Glance Index Measure for comparing two images. A Global Glance vector is formulated by randomly retrieving pixels based on a perception-driven rule from an image to form a vector representing non-semantic global context, while a local Glance vector is a flattened local image window, mimicking a zoom in observation. The Glance Index is defined as the inner product of two standardized sets of Glance vectors. We evaluate the effectiveness of incorporating Glance supervision in two reconstruction tasks: image fitting with implicit neural representation (INR) and undersampled MRI reconstruction. Extensive experimental results show that MS-Glance outperforms existing image restoration losses across both natural and medical images. The code is available at https://***/Z7Gao/MSGlance.

关键词： Computer vision Visualization Magnetic resonance imaging Fitting Vectors Image restoration Indexes Image reconstruction Biomedical imaging Visual perception

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-aware Superpoint Graph Transformer for Weakly Supervised 3D Semantic Segmentation

引用

IEEE Transactions on Fuzzy Systems 2025年

作者： Fan, Yan Wang, Yu Zhu, Pengfei Hui, Le Xie, Jin Hu, Qinghua Tianjin University College of Intelligence and Computing Tianjin300350 China Ministry of Education of the People's Republic of China Engineering Research Center of City Intelligence and Digital Governance China Haihe Laboratory of Itai Tianjin China Northwestern Polytechnical University School of Electronics and Information Shaanxi Key Laboratory of Information Acquisition and Processing China Nanjing University of Science and Technology Pca Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Nanjing University State Key Laboratory for Novel Software Technology Nanjing China

Weakly supervised 3D semantic segmentation has successfully mitigated the labor-intensive and time-consuming task of annotating 3D point clouds. However, reliably utilizing the minimal point-wise annotations for unlabeled data in complex and large-scale scenes is still challenging, such as only 20 points labeled in 2 million points. To tackle this challenge, we propose a new Uncertainty-aware Superpoint Graph Transformer (UaSGT) framework that utilizes minimal annotations for unlabeled data learning through reliable long-range supervision propagation from labeled superpoints to unlabeled superpoints. First, we propose a superpoint graph transformer to achieve long-range supervision propagation along the attention-based fuzzy subsets defined on superpoints. The attention-based fuzzy subset measures the membership of unlabeled superpoints to clusters centered on labeled superpoints. Second, we employ an uncertainty-aware membership rectification technique on the fuzzy subset to ensure reliable propagation among superpoints within the same category. This technique integrates an uncertainty prediction module to mask the influence of unreliable membership and a spatial prior refinement module to reduce uncertainty in intra-class membership degrees. Finally, experimental results on two large-scale benchmarks S3DIS and ScanNet-V2 demonstrate the superiority of our approach compared to the state-of-the-art with at least 90% annotation reduction, and our method also achieves comparable performance to fully supervised methods with less than 0.1% labeled points. Our code is available at https://***/fanyan0411/UaSGT. © 2025 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Towards Accurate Unified Anomaly Segmentation

Towards Accurate Unified Anomaly Segmentation

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Wenxin Ma Qingsong Yao Xiang Zhang Zhelong Huang Zihang Jiang S. Kevin Zhou Division of Life Sciences and Medicine School of Biomedical Engineering University of Science and Technology of China (USTC) Hefei Anhui China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) USTC Suzhou Institute for Advance Research Suzhou Jiangsu China Stanford University Palo Alto California United State School of Medicine Shanghai University Shanghai China Key Laboratory of Precision and Intelligent Chemistry USTC Hefei Anhui China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Unsupervised anomaly detection (UAD) from images strives to model normal data distributions, creating discriminative representations to distinguish and precisely localize anomalies. Despite recent advancements in the efficient and unified one-for-all scheme, challenges persist in accurately segmenting anomalies for further monitoring. Moreover, this problem is obscured by the widely-used AUROC metric under imbalanced UAD settings. This motivates us to emphasize the significance of precise segmentation of anomaly pixels using pAP and DSC as metrics. To address the unsolved segmentation task, we introduce the Unified Anomaly Segmentation (UniAS). UniAS presents a multi-level hybrid pipeline that progressively enhances normal information from coarse to fine, incorporating a novel multi-granularity gated CNN (MGG-CNN) into Transformer layers to explicitly aggregate local details from different granularities. UniAS achieves state-of-the-art anomaly segmentation performance, attaining 65.12/59.33 and 40.06/32.50 in pAP/DSC on the MVTec-AD and VisA datasets, respectively, surpassing previous methods significantly. The codes are shared at https://***/Mwxinnn/UniAS.

关键词： Measurement Image segmentation Computer vision Codes Pipelines Logic gates Transformers Data models Monitoring Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Stfi: Structure-Aware and Time-Frequency Domain Interaction Network for Deformable Medical Image Registration

SSRN

引用

SSRN 2025年

作者： Hu, Rui Wang, Nian Zhang, Yuxin Li, Teng Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Electrical Engineering and Automation Anhui University Hefei230601 China Advanced Imaging Research Center University of Texas Southwestern Medical Center 5323 Harry Hines Blvd Dallas75390 United States School of Cyber Science and Engineering Southeast University No.2 Southeast University Road Nanjing211189 China

Deformable image registration is crucial in medical image analysis. Recently, unsupervised methods using intensity matching have shown promising results without labeled data. However, these methods still face challenges: (1) They often encounter local optima when handling anatomical structures with significant variations in intensity distribution;(2) Time domain convolution in decoders leads to loss of high-frequency fine features, limiting the effectiveness of generating fine deformation vector fields. To address these issues, we propose a novel structure-aware and time-frequency domain interaction (STFI) network. STFI integrates a structure-aware frequency domain loss and a time-frequency domain interaction module. The former leverages principal structural information from the weighted phase spectrum to guide the registration process, thereby reducing the risk of local optima. The latter processes and amalgamates information from both the time and frequency domains, effectively preserving high-frequency details. The efficacy and adaptability of our approach have been demonstrated on two types of data, offering a new perspective on exploiting time-frequency domain information for medical image registration. © 2025, The Authors. All rights reserved.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

Multi-views Emotional Knowledge Extraction for Emotion Recognition in Conversation

引用

Knowledge-Based Systems 2025年 322卷

作者： Jian, Zhongquan Wu, Daihang Wang, Shaopan He, Jiezhou Yao, Junfeng Liu, Kunhong Wu, Qingqiang Institute of Artificial Intelligence Xiamen University Xiamen Fujian 361005 China School of Informatics Xiamen University Xiamen Fujian 361005 China School of Film Xiamen University Xiamen Fujian 361005 China College of Management Mahidol University Phayathai Bangkok 10400 Thailand Xiamen Key Laboratory of Intelligent Storage and Computing School of Informatics Xiamen University Xiamen Fujian 361005 China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism Xiamen University Xiamen Fujian 361005 China

Emotion Recognition in Conversation (ERC) is a challenging task due to the scarcity and dispersion of contextual information across utterances. Most existing methods attempt to integrate comprehensive information to enhance utterance semantics, which, however, also introduces noise and irrelevant content, misleading the model and limiting its potential in emotion recognition. To this end, we introduce the concept of Conversational Clique (ConvClique) and propose CC-ERC, a multi-view emotional knowledge extraction method designed to capture the most relevant emotional cues within the ConvClique from complementary perspectives and collaboratively predict utterance emotions. Specifically, CC-ERC comprises two modules: 1) the Utterance Spatial Relationship (USR) module, which predicts emotions by modeling structural correlations among utterances, and 2) the Emotion Temporal Relationship (ETR) module, which captures emotion sequence patterns to determine utterance emotions. These modules are integrated to obtain the final prediction, contributing to the robustness and accuracy of emotion recognition. The effectiveness of CC-ERC is validated on three widely used ERC datasets, evaluated in both online and offline settings. Compared to the state-of-the-art methods, CC-ERC achieves average improvements of 0.63% in accuracy and 0.94% in weighted F1 scores. Ablation studies further validate the significance of ConvClique-based knowledge extraction and demonstrate the effectiveness of the USR and ETR modules in modeling utterance structural correlations and emotion sequence patterns. © 2025

关键词： Conversation clique Emotion recognition in conversation Graph attention network Hidden Markov model Natural language processing

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：