检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Xingyi Cao, Zhiguo Sun, Huiqiang Zhang, Jianming Xian, Ke Lin, Guosheng Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Adobe Research S-Lab Nanyang Technological University Singapore

We present 3D Cinemagraphy, a new technique that marries 2D image animation with 3D photography. Given a single still image as input, our goal is to generate a video that contains both visual content animation and camera motion. We empirically find that naively combining existing 2D image animation and 3D photography methods leads to obvious artifacts or inconsistent animation. Our key insight is that representing and animating the scene in 3D space offers a natural solution to this task. To this end, we first convert the input image into feature-based layered depth images using predicted depth values, followed by unprojecting them to a feature point cloud. To animate the scene, we perform motion estimation and lift the 2D motion into the 3D scene flow. Finally, to resolve the problem of hole emergence as points move forward, we propose to bidirectionally displace the point cloud as per the scene flow and synthesize novel views by separately projecting them into target image planes and blending the results. Extensive experiments demonstrate the effectiveness of our method. A user study is also conducted to validate the compelling rendering results of our method. Copyright © 2023, The Authors. All rights reserved.

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells

Constraining Depth Map Geometry for Multi-View Stereo: A Dua...

引用

International Conference on Computer Vision (ICCV)

作者： Xinyi Ye Weiyue Zhao Tianqi Liu Zihao Huang Zhiguo Cao Xin Li Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Department of Computer Science University of Albany Albany NY

Learning-based multi-view stereo (MVS) methods deal with predicting accurate depth maps to achieve an accurate and complete 3D representation. Despite the excellent performance, existing methods ignore the fact that a suitable depth geometry is also critical in MVS. In this paper, we demonstrate that different depth geometries have significant performance gaps, even using the same depth prediction error. Therefore, we introduce an ideal depth geometry composed of Saddle-Shaped Cells, whose predicted depth map oscillates upward and downward around the ground-truth surface, rather than maintaining a continuous and smooth depth plane. To achieve it, we develop a coarse-to-fine framework called Dual-MVSNet (DMVSNet), which can produce an oscillating depth plane. Technically, we predict two depth values for each pixel (Dual-Depth), and propose a novel loss function and a checkerboard-shaped selecting strategy to constrain the predicted depth geometry. Compared to existing methods, DMVSNet achieves a high rank on the DTU benchmark and obtains the top performance on challenging scenes of Tanks and Temples, demonstrating its strong performance and generalization ability. Our method also points to a new research direction for considering depth geometry in MVS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

InferEM: Inferring the Speaker’s Intention for Empathetic Dialogue Generation

arXiv

引用

arXiv 2022年

作者： Lv, Guoqing Li, Jiang Wang, Xiaoping Zeng, Zhigang The School of Artificial Intelligence and Automation The Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China The Hubei Key Laboratory of Brain-inspired Intelligent Systems Huazhong University of Science and Technology Wuhan430074 China

Current approaches to empathetic response generation typically encode the entire dialogue history directly and put the output into a decoder to generate friendly feedback. These methods focus on modelling contextual information but neglect capturing the direct intention of the speaker. We argue that the last utterance in the dialogue empirically conveys the intention of the speaker. Consequently, we propose a novel model named InferEM for empathetic response generation. We separately encode the last utterance and fuse it with the entire dialogue through the multi-head attention based intention fusion module to capture the speaker’s intention. Besides, we utilize previous utterances to predict the last utterance, which simulates human’s psychology to guess what the interlocutor may speak in advance. To balance the optimizing rates of the utterance prediction and response generation, a multitask learning strategy is designed for InferEM. Experimental results demonstrate the plausibility and validity of InferEM in improving empathetic expression. Copyright © 2022, The Authors. 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

Multi-scale convolutional neural networks for brain disease diagnosis

Multi-scale convolutional neural networks for brain disease ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Zhongyi Hu Libin Gao Yinsheng Tong Xingjin Lu Rui Li Lei Xiao Zuoyong Li College of Computer Science and Aritificial Intelligence Wenzhou University Wenzhou China Key Laboratory of Intelligent Image Processing and Analysis Wenzhou China College of Computer and Control Engineering Minjiang University Fuzhou China

The brain is the most sophisticated and complex organ in the human body. Nowadays, diagnosing complex and diverse brain diseases is a hot topic. Alzheimer's Disease (AD), Autism Spectrum Disorder (ASD), and others are common brain diseases. With the increased usage of Artificial Intelligence (AI) in medical image analysis, the endeavor to make AI comprehend brain images for assisting doctors in making objective diagnoses of brain diseases has gained considerable attention. Resting-state functional magnetic resonance imaging (rs-fMRI) is a widely used tool for diagnosing and analyzing brain ***, the Pearson correlation coefficient (PCC) method constructs a dynamic functional connectivity (dFC) network using a fixed window size. However, this method has limitations as it is challenging to extract potential high-level features from the dFC and determine local feature relevance. This paper presents a method for constructing dFC based on multi-scale sliding windows and proposes Multi-scale Convolutional Neural Networks (MsCNN) for learning and analyzing dFC at various scales. Finally, a deep fusion of features learned at different scales is employed for the diagnostic classification of brain *** to the rs-fMRI dataset from ADNI, the classification accuracy was 84.0% for eMCI/lMCI, 84.4% for lMCI/AD, and 58.4% for NC/eMCI/lMCI/AD. Applied to rs-fMRI data from ABIDE, the accuracy was 74.7% for ASD/NC. The proposed method exhibits robust classification performance and introduces a new approach to diagnosing other brain diseases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast Full-frame Video Stabilization with Iterative Optimization

Fast Full-frame Video Stabilization with Iterative Optimizat...

引用

International Conference on Computer Vision (ICCV)

作者： Weiyue Zhao Xin Li Zhan Peng Xianrui Luo Xinyi Ye Hao Lu Zhiguo Cao Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Department of Computer Science University of Albany Albany NY

Video stabilization refers to the problem of transforming a shaky video into a visually pleasing one. The question of how to strike a good trade-off between visual quality and computational speed has remained one of the open challenges in video stabilization. Inspired by the analogy between wobbly frames and jigsaw puzzles, we propose an iterative optimization-based learning approach using synthetic datasets for video stabilization, which consists of two interacting submodules: motion trajectory smoothing and full-frame outpainting. First, we develop a two-level (coarse-to-fine) stabilizing algorithm based on the probabilistic flow field. The confidence map associated with the estimated optical flow is exploited to guide the search for shared regions through backpropagation. Second, we take a divide-and-conquer approach and propose a novel multi-frame fusion strategy to render full-frame stabilized views. An important new insight brought about by our iterative optimization approach is that the target video can be interpreted as the fixed point of nonlinear mapping for video stabilization. We formulate video stabilization as a problem of minimizing the amount of jerkiness in motion trajectories, which guarantees convergence with the help of fixed-point theory. Extensive experimental results are reported to demonstrate the superiority of the proposed approach in terms of computational speed and visual quality. The code will be available on GitHub.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Small Object Detection via a Dense Connection and Feature Enhancement Network

Small Object Detection via a Dense Connection and Feature En...

引用

International Conference on Computer and Communications (ICCC)

作者： Baohua Qiang Lirui Chen Shuiping Guo Lingzhi Liu Shihao Zhang Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China The 7th Research Institute of China Electrics Technology Group Corporation Guangzhou China

When detecting small objects in complex environment, the features of small objects will become blurred or even lost as the number of network layers increases. To address this problem, we constructed a Dense Connection and Feature Extraction Network, termed DCFEN. First, we designed a dense-connected multi-scale feature enhancement framework, which can effectively extract and fuse multi-scale features. Second, we constructed a dense-connected subnet using dense connections, which enhances the propagation of features and the utilization of shallow feature information, improving the detection performance of small objects. Finally, extensive experimental results demonstrated the detection precision and superiority of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Maritime Obstacle Detection Based on YOLOv5 for Autonomous Berthing 16th

Real-Time Maritime Obstacle Detection Based on YOLOv5 for Au...

引用

16th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2021

作者： Chen, Guotong Qi, Jiangtao Dai, Zeyu Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China China Ship Scientific Research Center No. 222 Shanshui East Road Binhu District Wuxi214082 China

ISBN: (纸本)9789811912528

The shipping industry is developing towards intelligence, in which autonomous berthing and docking systems play an important role. Real-time maritime obstacle detection is essential for autonomous berthing, which can protect ships from collisions. In the field of real-time objection detection, YOLOv5s is one of the most effective networks. To solve the real-time maritime obstacle detection for autonomous berthing, we propose an improved network, named YOLOv5s-CBAM, which employs the convolutional block attention module to boost the representation power of YOLOv5s. In addition, we propose another network, named YOLOv5-SE, in which a squeeze-and-excitation block is introduced to recalibrate the channel-wise features adaptively. The experimental results demonstrate that YOLOv5s-CBAM outperforms YOLOv5s in the detection of large obstacles. Both YOLOv5s-CBAM and YOLOv5s-SE achieve state-of-the-art performance in various metrics compared with previous related work for maritime obstacle detection. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Ships

来源：评论

学校读者我要写书评

暂无评论

Evolutionary attraction–repulsion algorithm embedded with LLM for UAV task allocation

引用

Advanced Engineering Informatics 2025年 66卷

作者： Wu, Bowen Xiao, Renbin School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Institute of Artificial Intelligence Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan430074 China

Labor division provides an adaptive and scalable technique for unmanned systems. However, its designing process usually relies heavily on the manually crafted paradigms, leading to inefficiencies and insufficient performance. To overcome these challenges, this paper introduce an evolutionary approach to labor division algorithm design. Drawing inspiration from the regulatory behaviors observed in natural lion populations, we propose a bipolar feedback-guided attraction–repulsion mechanism. A formal model is developed to encapsulate this mechanism, and we provide an in-depth analysis of the algorithm's evolution through the framework of systems science. In addition, we leverage prompt engineering techniques to integrate a large language model (LLM) with our proposed mechanism, facilitating a bidirectional enhancement between the two. This integration culminates in the development of the ARE-LLM framework, a robust and adaptive solution for designing labor division algorithms. To demonstrate the practical applicability of our approach, we apply the ARE-LLM framework to the UAV-based task allocation problem for enemy air defense suppression. The experimental results indicate that our method outperforms several advanced approaches. In a scenario involving 50 UAVs tasked with completing 300 assignments, the total distance traveled is only 9 % of that required by the ALPDA algorithm, while the processing time is reduced to 8 % of that used by ALPDA. © 2025 Elsevier Ltd

关键词： Target drones

来源：评论

学校读者我要写书评

暂无评论

Design and Optimization of Liquid State Machine for Handwritten Digit Recognition

Design and Optimization of Liquid State Machine for Handwrit...

引用

2022 Workshop on Electronics Communication Engineering

作者： Hou, Aihu Liu, Jie Zhou, Kaibo Zhou, Wenli School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China School of Civil and Hydraulic Engineering Huazhong University of Science and Technology Wuhan430074 China Hubei Key Laboratory of Digital River Basin Science and Technology Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Ministry of Education Wuhan430074 China School of Optical and Electronic information Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781510666634

The most commonly used implementation of handwritten digit recognition based on convolutional neural networks requires equipment with high computing power, which is not suitable for edge devices. Recently, spiking neural network (SNN) has received more attentions due to its low power consumption and real-time performance, but training SNN is very difficult. As a special SNN, liquid state machine (LSM) has the advantages of simple structure and easy training, so it is very suitable for handwritten digit recognition on edge devices. But it has no advantage in recognition accuracy. In order to improve the performance of LSM, its reservoir needs to be optimized. In this paper, an efficient local optimization strategy is proposed, improving the recognition accuracy of LSM by 11.8% with less the training time. In order to reduce the runtime, auto-encoder and feature screening are used to compress the input handwritten digit image. After feature compression, the input storage is reduced by 57%, and the runtime is reduced by 30%. This work provides an effective way to realize handwritten digit recognition on the edge devices. © 2023 SPIE.

关键词： Computing power

来源：评论

学校读者我要写书评

暂无评论

Difference in Uptake Pattern Heterogeneity and Reproducibility of Radiomics Features Between FAPI and FDG Pet/Ct Imaging of Tumors

Difference in Uptake Pattern Heterogeneity and Reproducibili...

引用

IEEE International Symposium on Biomedical Imaging

作者： Tianmeng Xu Yanchao Huang Tingting Ang Shuilin Chu Peiyin Luo Shunfang Wang Yufeng Zhang Lijun Lu Ganghua Tang Wenbing Lv School of Information and Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming China Department of Nuclear Medicine Laboratory for Quality Control and Evaluation of Radiopharmaceuticals Nanfang Hospital Southern Medical University Guangzhou China School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing Southern Medical University Guangzhou China

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

To investigate the difference in uptake pattern heterogeneity between fluorodeoxyglucose (FDG) and fibroblast activation protein inhibitor (FAPI) PET/CT and the reproducibility of radiomics features with respect to different calculation methods of standardized uptake value (SUV). 210 patients with various tumors were involved. Among the extracted 497 radiomics features, there are only 20 features that exhibited an ICC difference of more than 0.25 between the two tracers when using different SUV calculation methods, revealing the similar influence of SUV calculation methods. In contrast, the ICC values for most texture features were generally lower (0.22-0.39) between FDG and FAPI PET images, indicating a large difference in uptake pattern heterogeneity between the two tracers. Our results demonstrated that the influence of SUV calculation methods on the reproducibility of FDG and FAPI PET features is similar. The uptake pattern heterogeneity characterized by radiomics features between FDG and FAPI PET images is significantly different.

关键词： Proteins Protein engineering Inhibitors Fibroblasts Feature extraction Reproducibility of results Radiomics

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：