检索结果-内蒙古大学图书馆

Companion International Conference on Multimodal Interaction

作者： Ishii, Ryo Eitoku, Shinichiro Matsuo, Shohei Makiguchi, Motohiro Hoshi, Ayami Morency, Louis-philippe NTT Corp Labs NTT Human Informat Labs Tokyo Japan Carnegie Mellon Univ Language Technol Inst Pittsburgh PA 15213 USA

ISBN: (纸本)9798400704635

We propose an advanced new system that automatically generates dances according to the user's favorite music and dance style and then presents 3DCG animations of the generated dances on a naked-eye 3D display so that the user can have the experience of actually dancing with the displayed dancer. For automatic dance generation, we developed a new generation model based on the transformer-based diffusion model that generates a dance conditioned on any music audio and dance style of the user's choice. We implemented this generation model in a GUI system that automatically generates dance animations according to the users' specifications. The CG animations are then presented on a naked-eye 3D display system we recently proposed.

关键词： dance generation music-to-dance conditional diffusion model table-top 3D display

来源：评论

学校读者我要写书评

暂无评论

Rethinking Sampling for Music-Driven Long-Term Dance Generation 17th

Rethinking Sampling for Music-Driven Long-Term Dance Genera...

引用

17th Asian Conference on Computer Vision, ACCV 2024

作者： Truong-Thuy, Tuong-Vy Bui-Le, Gia-Cat Nguyen, Hai-Dang Le, Trung-Nghia University of Science VNU-HCM Ho Chi Minh City Viet Nam Vietnam National University Ho Chi Minh City Viet Nam

ISBN: (纸本)9789819609161

Generating dance sequences that synchronize with music while maintaining naturalness and realism is a challenging task. Existing methods often suffer from "freezing" phenomena or abrupt transitions. In this work, we introduce DanceFusion, a conditional diffusion model designed to address the complexities of creating long-term dance sequences. Our method employs a past and future-conditioned diffusion model, leveraging the attention mechanism to learn the dependencies among music, past, and future motions. We also propose a novel sampling method that completes the transitional motions between two dance segments by treating previous and upcoming motions as conditions. Additionally, we address abruptness in dance sequences by incorporating inpainting strategies into a part of the sampling process, thereby improving the smoothness and naturalness of motion generation. Experimental results demonstrate that DanceFusion outperforms state-of-the-art methods in generating high-quality and diverse dance motions. User study results further validate the effectiveness of our approach in generating long dance sequences, with participants consistently rating DanceFusion higher across all key metrics. Code and model are available at https://***/trgvy23/DanceFusion. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： conditional diffusion model Music-to-Dance Sampling Strategy

来源：评论

学校读者我要写书评

暂无评论

Two-stage Content-Aware Layout Generation for Poster Designs 23

Two-stage Content-Aware Layout Generation for Poster Designs

引用

31st ACM International Conference on Multimedia (MM)

作者： Chai, Shang Zhuang, Liansheng Yan, Fengying Zhou, Zihan Univ Sci & Technol China Hefei Peoples R China Tianjin Univ Tianjin Peoples R China Manycore Tech Inc Hong Kong Peoples R China

ISBN: (纸本)9798400701085

Automatic layout generation models can generate numerous design layouts in a few seconds, which significantly reduces the amount of repetitive work for designers. However, most of these models consider the layout generation task as arranging layout elements with different attributes on a blank canvas, thus struggle to handle the case when an image is used as the layout background. Additionally, existing layout generation models often fail to incorporate explicit aesthetic principles such as alignment and non-overlap, and neglect implicit aesthetic principles which are hard to model. To address these issues, this paper proposes a two-stage content-aware layout generation framework for poster layout generation. Our framework consists of an aesthetics-conditioned layout generation module and a layout ranking module. The diffusion model based layout generation module utilizes an aesthetics-guided layout denoising process to sample layout proposals that meet explicit aesthetic constraints. The Auto-Encoder based layout ranking module then measures the distance between those proposals and real designs to determine the layout that best meets implicit aesthetic principles. Quantitative and qualitative experiments demonstrate that our method outperforms state-of-the-art content-aware layout generation models.

关键词： layout generation graphic design conditional diffusion model

来源：评论

学校读者我要写书评

暂无评论

Improving orbital bone segmentation with diffusion models and consensus-based refinement in facial CT images

Improving orbital bone segmentation with diffusion models an...

引用

2025 Conference on Medical Imaging

作者： An, Jinseo Lee, Min Jin Shim, Kyu Won Hong, Helen Seoul Womens Univ Dept Software Convergence Seoul 01797 South Korea Yonsei Univ Coll Med Severance Childrens Hosp Dept Pediat Neurosurg Seoul 03722 South Korea

ISBN: (纸本)9781510685925;9781510685932

Accurate segmentation of orbital bones in facial computed tomography (CT) images is essential for craniomaxillofacial surgery planning and the creation of bone implants. However, it has challenging issues that thin bones of orbital medial wall and floor are difficult to segment due to their ambiguous boundaries and low contrast with surrounding soft tissues. Furthermore, this issue leads to inter-observer variability in manual annotation masks. In this paper, we propose a novel segmentation framework based on a conditional diffusion model with consensus-driven correction. The framework consists of three main components: conditional diffusion model-based segmentation, consensus-driven accumulation map generation, and context-aware consensus correction. The conditional diffusion model leverages diverse annotation masks to generate multiple plausible segmentation results, addressing the inter-observer variability associated with manual annotations. These results are aggregated into a consensus-driven accumulation map, which captures the agreement among possible segmentations, offering a robust alternative to simple averaging. Finally, the segmentation is refined through context-aware consensus correction, which integrates consensus information with CT image features, considering spatial and intensity-based characteristics. Experimental results show the effectiveness of the proposed method, achieving Dice Similarity Coefficients (DSCs) of 84.38% and 90.37% and precisions of 88% and 92.28% for the medial wall and floor, respectively. Compared to CNN-based methods, the proposed framework improves precision by up to 4.74% and 4.49%, significantly reducing false positives while preserving the continuity of thin structures.

关键词： Segmentation conditional diffusion model Consensus Correction Orbital bone Facial CT

来源：评论

学校读者我要写书评

暂无评论

A novel diffusion model with Shapley value analysis for anomaly detection and identification of wind turbine

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 284卷

作者： Yao, Qingtao Chen, Bohua Hu, Aijun Zhen, Dong Xiang, Ling North China Elect Power Univ Dept Mech Engn Baoding 071003 Peoples R China Hebei Univ Technol Sch Mech Engn Tianjin 300401 Peoples R China

Anomaly detection and identification methods for wind turbine based on deep learning have become a current research hotspot due to their superior performance in feature extraction. However, the existed methods have limitations in fusion mechanisms of different physical features, and the logical relationships between parameters are difficult to interpret. To address these issues, an innovative Physical Information Dynamic Fusion (PIDF) mechanism and a Dynamic Fusion conditional diffusion (DFCD) model are proposed, along with a new operational state evaluation indicator derived from Shapley (SHAP) value analysis, for anomaly detection and fault identification in wind turbines. First, this proposed DFCD model based on PIDF mechanism enables the deep fusion of multiple physical parameters and overcomes the limitations of traditional models, which often struggle to effectively handle diverse information sources. Next, a quantitative approach based on SHAP values is proposed to analyze the relationship between condition parameters and the target parameter for evaluating the wind turbine's operating status. Finally, a new evaluation indicator for operational state of wind turbines is proposed based on the logical relationship. This indicator provides an intuitive and easily comprehensible way to assess the system behavior learned by the model. Through the analysis of datasets from two real wind farms, this method is capable of effectively identifying the anomaly state and fault locations, which enhances the operational efficiency of wind turbine. This work provides a new scientific tool for technology transfer, which will contribute to intelligent condition monitoring and information management in advanced engineering.

关键词： Wind turbine Anomaly detection Dynamic fusion conditional diffusion model Shapley value

来源：评论

学校读者我要写书评

暂无评论

Generative inverse modeling for improved geological CO2 storage prediction via conditional diffusion models

引用

APPLIED ENERGY 2025年 395卷

作者： Wang, Zhongzheng Chen, Yuntian Fu, Wenhao Du, Mengge Chen, Guodong Ma, Xiaopeng Zhang, Dongxiao Peking Univ Dept Energy & Resources Engn Beijing 100871 Peoples R China Eastern Inst Technol Eastern Inst Adv Study Ningbo 315200 Zhejiang Peoples R China Univ Hong Kong Dept Earth Sci Hong Kong 999077 Peoples R China Xian Shiyou Univ Sch Petr Engn Xian 710065 Peoples R China

Geological CO2 storage is expected to play a pivotal role in achieving climate-neutrality targets by 2050. Accurate prediction of long-term CO2 storage performance relies on inverse modeling procedures that precisely characterize spatially varying geological properties using practically available observed data. Traditional inversion methods necessitate extensive forward simulations to iteratively calibrate uncertain geological parameters, which can impose a significant computational burden. In this work, an end-to-end generative inversion framework based on the conditional diffusion model is proposed for efficiently characterizing heterogeneous geological properties and accelerating the inversion process. By employing an improved U-net to learn the conditional denoising diffusion process, the proposed framework enables the direct generation of high-dimensional property fields that closely match the observed data. Additionally, the probabilistic nature inherent in the diffusion approach allows for producing an ensemble of plausible geological realizations, facilitating effective quantification of parametric and predictive uncertainties. The performance of the proposed framework is validated by estimating stochastic permeability fields for both two-dimensional and three-dimensional carbon storage models. Comprehensive comparisons with the conditional generative adversarial network-based method demonstrate that the proposed framework yields more accurate inversion results and better quantifies the uncertainty in the predicted flow responses. This work offers a promising tool for subsurface inverse modeling and uncertainty quantification, potentially paving the way for broader adoption and exploration of generative diffusion models in the realm of energy system management.

关键词： Geological CO2 storage Inverse modeling Uncertainty quantification conditional diffusion model Generative inversion

来源：评论

学校读者我要写书评

暂无评论

KEDM: Knowledge-Embedded diffusion model for Infrared Image Destriping

IEEE PHOTONICS JOURNAL

引用

IEEE PHOTONICS JOURNAL 2025年第3期17卷

作者： Li, Lingxiao Wang, Xin Huang, Dan He, Yunan Zhong, Zhuqiang Xia, Qingling Chongqing Univ Technol Sch Sci Chongqing 400054 Peoples R China China Res & Dev Acad Machinery Equipment Beijing 100089 Peoples R China Chongqing Univ Technol Sch Artificial Intelligence Chongqing 401135 Peoples R China

Infrared imaging systems are widely used across industries. However, their output images often exhibit striped noise due to the nonuniform response of the detection system, which significantly affects image quality and visual fidelity. To address challenges such as incomplete stripe removal, potential loss of image details and textures, and the generation of artificial artifacts during destriping, we propose a novel stripe removal method based on a knowledge-embedded diffusion model (KEDM). This approach effectively integrates the spatial distribution characteristics of stripe noise with an innovative, data-driven diffusion network model, creating a hybrid knowledge and data-driven framework for stripe correction. The core components of KEDM are the latent diffusion model (LDM) architecture and the directional wavelet convolution module (DWCM). Specifically, LDM leverages a pretrained variational autoencoder (VAE) to transform the input image into latent feature space for efficient diffusion propagation, reducing computational complexity while preserving image restoration quality. Meanwhile, DWCM uses wavelet convolution operations to construct prior loss functions for stripe noise, precisely guiding the diffusion reconstruction process to achieve a clean, stripe-free image. Empirical evaluations on several benchmark datasets demonstrate that the proposed KEDM outperforms other state-of-the-art destriping algorithms in terms of visual quality and quantitative metrics, validating its excellent performance.

关键词： Noise Training Vectors diffusion models Noise reduction Wavelet transforms Graphical models Feature extraction Distribution functions Imaging conditional diffusion model infrared image destriping knowledge-embedded diffusion model stripe prior wavelet transform

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：