检索结果-内蒙古大学图书馆

3D hand pose and shape estimation from monocular RGB via efficient 2D cues

Computational Visual Media 2024年第1期10卷 79-96页

作者： Fenghao Zhang Lin Zhao Shengling Li Wanjuan Su Liman Liu Wenbing Tao Hubei Key Laboratory of Medical Information Analysis and Tumor Diagnosis&Treatment School of Biomedical EngineeringSouth Central Minzu UniversityWuhan430074China National Key Laboratory of Science and Technology of Multi-spectral Information Processing School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhan430074China

Estimating 3D hand shape from a single-view RGB image is important for many ***,the diversity of hand shapes and postures,depth ambiguity,and occlusion may result in pose errors and noisy hand *** full use of 2D cues such as 2D pose can effectively improve the quality of 3D human hand shape *** this paper,we use 2D joint heatmaps to obtain spatial details for robust pose *** also introduce a depth-independent 2D mesh to avoid depth ambiguity in mesh regression for efficient hand-image *** method has four cascaded stages:2D cue extraction,pose feature encoding,initial reconstruction,and reconstruction ***,we first encode the image to determine semantic features during 2D cue extraction;this is also used to predict hand joints and for ***,during the pose feature encoding stage,we use a hand joints encoder to learn spatial information from the joint ***,a coarse 3D hand mesh and 2D mesh are obtained in the initial reconstruction step;a mesh squeeze-and-excitation block is used to fuse different hand features to enhance perception of 3D hand ***,a global mesh refinement stage learns non-local relations between vertices of the hand mesh from the predicted 2D mesh,to predict an offset hand mesh to fine-tune the reconstruction *** and qualitative results on the FreiHAND benchmark dataset demonstrate that our approach achieves state-of-the-art performance.

关键词： hand 3D reconstruction deep learning image features 3D mesh

来源：评论

学校读者我要写书评

暂无评论

Distribution Mining and Noise Correction for Facial Expression Recognition 5

Distribution Mining and Noise Correction for Facial Expressi...

引用

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

作者： Huang, Hailan Tan, Yihua Huazhong University of Science and Technology National Key Laboratory of Science & Technology on Multi-spectral Information Processing School of Artificial Intelligence and Automation Wuhan430074 China

ISBN: (纸本)9798350373820

Due to the high annotation cost and inter-class ambiguity, many facial expression datasets only offer noisy one-hot labels. This creates two challenges for facial expression recognition (FER) as the one-hot labels only represent limited single semantics, and the noisy labels will mislead the model. Our study proposes a novel method to perform both label Distribution Mining and Noise Correction (DMNC) on the FER dataset. That is, while eliminating the disturbance of noisy samples, we start from the original one-hot labels and gradually refine them to distributions of expressions close to the real world. Specifically, DMNC uses the network forgetting property to select noisy samples. Then based on clean samples, an expression feature space is learned by contrastive learning. Finally, the labels of clean and noisy samples are refined or relabelled in a divide-and-conquer manner using the learned feature space. Experiments show that our method exhibits leading performance on both real-world FER benchmarks and synthetic noisy datasets. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Anti-interference object detection algorithm based on spatio-Temporal behavior perception 12

Anti-interference object detection algorithm based on spatio...

引用

SPIE 12th International Symposium on multispectral Image processing and Pattern Recognition, MIPPR 2023

作者： Chen, Guo Han, Peng Mei, Jianwei Zuo, Zhengrong School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan Hubei China National Key Laboratory of Science and Technology on Multi-Spectral Information Processing China

ISBN: (数字)9781510674943

ISBN: (纸本)9781510674936

In a military scenario, targets release decoy projectiles to achieve cover, then escape, evading the attack range of the guidance system. Therefore, recognizing target behaviors such as releasing decoys, escaping, and maneuvering, and locating the spatial position and behavior of the target can provide richer information for the precise targeting of the guidance system. Based on the behaviors of both the target and decoy, a behavioraware anti-interference algorithm is proposed. The core idea of this method is to link event recognition with spatio-Temporal action localization tasks. It extracts spatio-Temporal features of consecutive frames through a 3D backbone network and utilizes a 2D backbone network with a feature pyramid to extract spatial features at different levels of key frames for behavior detection at different scales. Additionally, a context extraction network is introduced in the key frames to achieve global context awareness, improving the accuracy of event recognition. Taking into account the correlation between spatial information, temporal information, and contextual information, this paper introduces channel attention mechanisms to fuse various feature components. Simultaneously, a non-local attention module is incorporated into the 3D backbone network to enhance the understanding of global content and the connection between different frames. Experimental results demonstrate that the proposed algorithm outperforms other algorithms, achieving a frame mean Average Precision (mAP) of 92.69% on our anti-interference dataset,enabling better resistance to interference. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Masking Cascaded Self-attentions for Few-Shot Font-Generation Transformer 17th

Masking Cascaded Self-attentions for Few-Shot Font-Generati...

引用

17th Asian Conference on Computer Vision, ACCV 2024

作者： Ma, Jing Xiang, Xiang He, Yan National Key Lab of Multi-Spectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9789819609161

Few-shot Font Generation (FFG) is a practical technology widely used in designing artistic characters, handwriting imitation, and identification, etc., which aims to generate realistic font images with a few reference samples. Typically, convolutional neural networks (CNNs) are employed to learn the representations of style and content from the font images. However, owing to the locality of convolutional operations, CNNs are not good at capturing the global structure of fonts, which leads to the generated images with blurry components and distorted space layouts. To address this problem, we consider cascading self-attention modules to exploit long-range dependencies for font generation and propose a transformer-based approach called FGTr. Following the style-content disentanglement paradigm, FGTr contains two different transformer encoders to extract the style and content sequences. A multi-layer transformer decoder is adopted to merge the two sequences and generate target images. In order to smoothen the transition of patch edges, we utilize a Local Self-Attention Mask (LSAM) to restrict the attention scope of each patch to a fixed-size sliding window, which plugs into the Transformer with no extra parameters. We also propose an Auxiliary Generation Module (AGM) in favor of generating glyphs closer to the real. Extensive experiments demonstrate the effectiveness and superiority of our method compared with state-of-the-art CNN-based models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A moving infrared small target detection method based on optical flow-guided neural networks 4

A moving infrared small target detection method based on opt...

引用

4th International Conference on Computer Vision, Image and Deep Learning, CVIDL 2023

作者： Zhu, Wenming Tan, Yihua School of Artificial Intelligence and Automation National Key Laboratory of Science & Technology on Multi-spectral Information Processing Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9798350326444

In the practical application scenarios of infrared small dim target detection (IRSTD), the background is complex and changeable, which leads to poor detection performance. The traditional methods based on prior knowledge and the existing deep learning methods can only adapt to a single fixed scene, and cannot be popularized in complex and changeable scenes. Therefore, there is still a lack of a robust infrared small target detection method. In this paper, we propose an optical flow-guided neural network for moving infrared small target detection. Firstly, we design an optical flow capture module (OFCM), which can enhance the characteristics of weak targets, and capture the motion information in the image by calculating the optical flow value of the image. Secondly, we design a pyramid feature interactive network (PFI-Net) to perform feature interaction fusion of optical flow and infrared images. PFI-Net can analyse the motion information expressed by the optical flow and the contour information expressed by the infrared image on multiple scales to extract features and perform target detection and segmentation. Experimental results on public datasets show that our method can effectively detect moving targets, and has better performance than other methods. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Radio-Frequency Interference Source Detection Based on Enhanced YOLOv8 for Synthetic Aperture Interferometric Radiometers

Radio-Frequency Interference Source Detection Based on Enhan...

引用

2023 Cross Strait Radio science and Wireless technology Conference, CSRSWTC 2023

作者： Lu, Shimeng Yang, Mingjin Wang, Huanyu Li, Fanxiang Zhu, Dong School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan430074 China National Key Laboratory of Science and Technology on Multi-Spectral Information Processing Wuhan China

ISBN: (纸本)9798350358971

The presence of radio-frequency interference (RFI) contaminates data collected by synthetic aperture interferometric radiometers (SAIRs). The performances of current RFI detection methods are limited due to insufficient exploration of RFI characteristics. This paper proposes a new RFI source detection method based on a convolutional neural network (CNN) that exploits side-lobe characteristics of the array factor of SAIR systems. Based on the common characteristic observed in RFI images, namely the presence of hexagonal tailings extended from a local peak of the RFI source, this method incorporates the hexagonal tailing feature into the detection scope, thereby expanding the capability to identify RFI. By including the hexagonal tailing feature, the method enhances the comprehensiveness and accuracy of RFI detection. This inclusion leads to a more comprehensive and accurate detection range for RFI sources. Results using real SMOS satellite data demonstrate that the proposed method has improved detection performance compared with traditional approaches that are commonly used in RFI detection tasks for SAIRs. © 2023 IEEE.

关键词： Deep learning Radio frequency interference (RFI) RFI detection

来源：评论

学校读者我要写书评

暂无评论

Robust diffractive neural networks for resilient all-optical intelligent imaging detection 12

Robust diffractive neural networks for resilient all-optical...

引用

SPIE 12th International Symposium on multispectral Image processing and Pattern Recognition, MIPPR 2023

作者： Shi, Jiashuo Zhang, Xinyu National Key Laboratory of Science & Technology on Multi-spectral Information Processing Huazhong University of Science & Technology Wuhan430074 China School of Artificial Intelligence & Automation Huazhong University of Science & Technology Wuhan430074 China

ISBN: (数字)9781510675001

ISBN: (纸本)9781510674998

Conventional imaging detection relies on electrical modulation, but it grapples with limitations in speed and adaptability within complex environments. Intelligent imaging detection, capable of manipulating micro-nano-lightfields generated by imaging objective lenses, is essential. The all-optical deep diffractive neural network (D2NN) offers a potential solution, enabling swift spatial information transformation and recognition. However, existing D2NN versions are vulnerable to optical disturbances due to their reliance on computer-based backpropagation. This paper introduces a robust diffractive neural network (SRNN) mathematical model designed to mitigate the impact of structural errors and lightwave frequency shifting without necessitating hardware modifications. The SRNN model incorporates Gaussian noise at various levels during training to emulate the error distribution of the phase mask, augmenting the network's resilience to hardware errors. Weight-Noise-Injection training assists the network in locating an error-insensitive region, thereby enhancing its robustness. © 2024 SPIE.

关键词： Optical data processing

来源：评论

学校读者我要写书评

暂无评论

GPS: graph contrastive learning via multi-scale augmented views from adversarial pooling

引用

science China(information sciences) 2025年第1期68卷 145-158页

作者： Wei JU Yiyang GU Zhengyang MAO Ziyue QIAO Yifang QIN Xiao LUO Hui XIONG Ming ZHANG School of Computer Science National Key Laboratory for Multimedia Information ProcessingPeking University Artificial Intelligence Thrust The Hong Kong University of Science and Technology Department of Computer Science University of California

Self-supervised graph representation learning has recently shown considerable promise in a range of fields, including bioinformatics and social networks. A large number of graph contrastive learning approaches have shown promising performance for representation learning on graphs, which train models by maximizing agreement between original graphs and their augmented views(i.e., positive views). Unfortunately, these methods usually involve pre-defined augmentation strategies based on the knowledge of human experts. Moreover, these strategies may fail to generate challenging positive views to provide sufficient supervision signals. In this paper, we present a novel approach named graph pooling contrast(GPS) to address these *** by the fact that graph pooling can adaptively coarsen the graph with the removal of redundancy, we rethink graph pooling and leverage it to automatically generate multi-scale positive views with varying emphasis on providing challenging positives and preserving semantics, i.e., strongly-augmented view and weakly-augmented view. Then, we incorporate both views into a joint contrastive learning framework with similarity learning and consistency learning, where our pooling module is adversarially trained with respect to the encoder for adversarial robustness. Experiments on twelve datasets on both graph classification and transfer learning tasks verify the superiority of the proposed method over its counterparts.

关键词： graph representation learning graph neural networks graph contrastive learning graph augmentations graph pooling

来源：评论

学校读者我要写书评

暂无评论

VAS: An Unsupervised Visible Area Sensing Module for Lane Classification 3

VAS: An Unsupervised Visible Area Sensing Module for Lane Cl...

引用

3rd International Conference on Big Data, information and Computer Network, BDICN 2024

作者： Hong, Xing Zhao, Ruixiang Lv, Wu Ma, Jie National Key Laboratory of Science and Technology on Multi-spectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China CSSC Navigation Technology Co. Ltd Beijing China

ISBN: (纸本)9798350363821

Road lane segmentation and classification play a crucial role in autonomous vehicles. Lane segmentation helps localize the position of the lane boundaries and the category information provides assistance for making decisions such as lane changing. With the development of deep learning, lane segmentation becomes faster and stronger, while classification has not received enough attention. Existing methods separate them into two networks, and can not handle complex scenes such as occlusion well. In this paper, we propose a novel network architecture combining the two tasks. To improve the robustness of classification to the scene, we also design a unsupervised visible area sensing module inspired by the simple lane geometry structure. The model was evaluated on several datasets with lane category information and get competitive results. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Infrared small target detection based on coarse-To-fine feature extraction network 12

Infrared small target detection based on coarse-To-fine feat...

引用

SPIE 12th International Symposium on multispectral Image processing and Pattern Recognition, MIPPR 2023

作者： Han, Peng Zuo, Zhengrong National Key Lab of Science and Technology on Multi-spectral Information Processing Huazhong University of Science and Technology Wuhan China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781510674943

ISBN: (纸本)9781510674936

Infrared small target detection (IRSTD) is a technique that has been developed to detect small and faint targets in cluttered backgrounds. It shows extensive use in medical diagnosis and aircraft navigation. However, due to the limited feature information and low signal-To-noise ratio, accurately detecting infrared targets and avoiding false alarms is a challenging task. Our study presents a Coarse-To-Fine Feature Extraction Network (CFFENet) for accurately classifying targets and backgrounds in blurred images. This network consists of a Two-stream Region Proposal Network (2s-RPN) and a Region Refinement Attention Network (RRAN), specifically designed to tackle the problem of false alarms. Specifically, 2s-RPN adds edge features to the RPN, in order to enable the network to extract discriminative information between targets and false alarms, so as to provide reliable coarse candidate boxes. In RRAN, firstly, attention-based encoder is used to extract the attention-Aware features in candidate boxes, and predicted mask map is output through multi-layer perception (MLP). Subsequently, the refined feature map is further processed by attention encoder, and MLP is utilized to generate the ultimate detection results. The effectiveness of our approach is validated through comparative experiment, which shows its superiority over representative state-of-The-Art IRSTD methods. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Feature extraction

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：