检索结果-内蒙古大学图书馆

Spatial Residual Layer and Dense Connection Block Enhanced Spatial Temporal Graph Convolutional Network for Skeleton-Based Action recognition

学校读者我要写书评

暂无评论

Spatial Residual Layer and Dense Connection Block Enhanced S...

International Conference on Computer Vision Workshops (ICCV Workshops)

作者： Cong Wu Xiao-Jun Wu Josef Kittler School of IOT Engineering Jiangnan University China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence CVSSP University of Surrey UK

ISBN: (数字)9781728150239

ISBN: (纸本)9781728150246

Recent research has shown that modeling the dynamic joint features of the human body by a graph convolutional network (GCN) is a groundbreaking approach for skeleton-based action recognition, especially for the recognition of the body-motion, human-object and human-human interactions. Nevertheless, how to model and utilize coherent skeleton information comprehensively is still an open problem. In order to capture the rich spatiotemporal information and utilize features more effectively, we introduce a spatial residual layer and a dense connection block enhanced spatial temporal graph convolutional network. More specifically, our work introduces three aspects. Firstly, we extend spatial graph convolution to spatial temporal graph convolution of cross-domain residual to extract more precise and informative spatiotemporal feature, and reduce the training complexity by feature fusion in the, so-called, spatial residual layer. Secondly, instead of simply superimposing multiple similar layers, we use dense connection to take full advantage of the global information. Thirdly, we combine the above mentioned two components to create a spatial temporal graph convolutional network (ST-GCN), referred to as SDGCN. The proposed graph representation has a new structure. We perform extensive experiments on two large datasets: Kinetics and NTU-RGB+D. Our method achieves a great improvement in performance compared to the mainstream methods. We evaluate our method quantitatively and qualitatively, thus proving its effectiveness.

关键词： Convolution Spatiotemporal phenomena Joints Feature extraction Two dimensional displays Three-dimensional displays

CL-Flow:Strengthening the Normalizing Flows by Contrastive Learning for Better Anomaly Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Shunfeng Li, Yueyang Luo, Haichi Bi, Chenyang Faculty of Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiang-nan University 1800 Lihu Avenue Jiangsu Wuxi214122 China

In the anomaly detection field, the scarcity of anomalous samples has directed the current research emphasis towards unsupervised anomaly detection. While these unsupervised anomaly detection methods offer convenience, they also overlook the crucial prior information embedded within anomalous samples. Moreover, among numerous deep learning methods, supervised methods generally exhibit superior performance compared to unsupervised methods. Considering the reasons mentioned above, we propose a self-supervised anomaly detection approach that combines contrastive learning with 2D-Flow to achieve more precise detection outcomes and expedited inference processes. On one hand, we introduce a novel approach to anomaly synthesis, yielding anomalous samples in accordance with authentic industrial scenarios, alongside their surrogate annotations. On the other hand, having obtained a substantial number of anomalous samples, we enhance the 2D-Flow framework by incorporating contrastive learning, leveraging diverse proxy tasks to fine-tune the network. Our approach enables the network to learn more precise mapping relationships from self-generated labels while retaining the lightweight characteristics of the 2D-Flow. Compared to mainstream unsupervised approaches, our self-supervised method demonstrates superior detection accuracy, fewer additional model parameters, and faster inference speed. Furthermore, the entire training and inference process is end-to-end. Our approach showcases new state-of-the-art results, achieving a performance of 99.6% in image-level AUROC on the MVTecAD dataset and 96.8% in image-level AUROC on the BTAD dataset. Copyright © 2023, The Authors. All rights reserved.

关键词： Anomaly detection

Robust Pedestrian detection for semi-automatic construction of a crowded person re-identification dataset 1

学校读者我要写书评

暂无评论

10th International Conference on Articulated Motion and Deformable Objects, AMDO 2018

作者： Huang, Zengxi Feng, Zhen-Hua Yan, Fei Kittler, Josef Wu, Xiao-Jun School of Computer and Software Engineering Xihua University Chengdu China Centre for Vision Speech and Signal Processing University of Surrey Guildford United Kingdom Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Machine Intelligence Jiangnan University Wuxi China

ISBN: (数字)9783319945446

ISBN: (纸本)9783319945439

The problem of re-identification of people in a crowd commonly arises in real application scenarios, yet it has received less attention than it deserves. To facilitate research focusing on this problem, we have embarked on constructing a new person re-identification dataset with many instances of crowded indoor and outdoor scenes. This paper proposes a two-stage robust method for pedestrian detection in a complex crowded background to provide bounding box annotations. The first stage is to generate pedestrian proposals using Faster R-CNN and locate each pedestrian using Non-maximum Suppression (NMS). Candidates in dense proposal regions are merged to identify crowd patches. We then apply a bottom-up human pose estimation method to detect individual pedestrians in the crowd patches. The locations of all subjects are achieved based on the bounding boxes from the two stages. The identity of the detected subjects throughout each video is then automatically annotated using multiple features and spatial-temporal clues. The experimental results on a crowded pedestrians dataset demonstrate the effectiveness and efficiency of the proposed method. © Springer International Publishing AG, part of Springer Nature 2018.

关键词： Gesture recognition

A Deep Decomposition Network for Image Processing: A Case Study of Image Fusion

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Fu, Yu Xu, Tianyang Wu, Xiao-Jun Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence School of Artificial Intelligence and Computer Science Jiangnan University Wuxi214122 China

Image decomposition into constituent components has many applications in the field of image processing. It aims to extract salient features from the source image for subsequent pattern recognition. In this paper, we propose a new image decomposition method based on a convolutional neural network. It is applied to the task of image fusion. In particular, a pair of infrared and visible light images are decomposed into three high-frequency feature images and a low-frequency feature images respectively. The two sets of feature images are fused using a novel fusion strategy to obtain fused feature maps. The feature maps are subsequently reconstructed to obtain the fused image. Compared with the state-of-the-art fusion methods, the proposed approach achieves betterperformance in both subjective and objective evaluation. © 2022, The Authors. All rights reserved.

关键词： Image fusion

LE2Fusion: A novel local edge enhancement module for infrared and visible image fusion

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xiao, Yongbiao Li, Hui Cheng, Chunyang Song, Xiaoning Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence School of Artificial Intelligence and Computer Science Jiangnan University Wuxi214122 China

Infrared and visible image fusion task aims to generate a fused image which contains salient features and rich texture details from multi-source images. However, under complex illumination conditions, few algorithms pay attention to the edge information of local regions which is crucial for downstream tasks. To this end, we propose a fusion network based on the local edge enhancement, named LE2Fusion. Specifically, a local edge enhancement (LE2) module is proposed to improve the edge information under complex illumination conditions and preserve the essential features of image. For feature extraction, a multi-scale residual attention (MRA) module is applied to extract rich features. Then, with LE2, a set of enhancement weights are generated which are utilized in feature fusion strategy and used to guide the image reconstruction. To better preserve the local detail information and structure information, the pixel intensity loss function based on the local region is also presented. The experiments demonstrate that the proposed method exhibits better fusion performance than the state-of-the-art fusion methods on public datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Image fusion

Lace Fabric Image Retrieval Using Siamese Neural Network

学校读者我要写书评

暂无评论

Lace Fabric Image Retrieval Using Siamese Neural Network

IEEE International Conference on Signal and Image Processing (ICSIP)

作者： DongDong Xu Yueyang Li HaiChi Luo Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi China College of Internet of Things Engineering Jiangnan University Wuxi China

ISBN: (纸本)9781665446006

An efficient lace fabric image retrieval method based on DCNN learning features is proposed in this paper. Fine-tuning with Siamese Neural Network is used to learn effective feature of lace fabric image. During the process of training the Siamese Neural Network, hard negative pairs are selective to achieve fast convergence and good performance. The DCNN learning features are combined with the unique shape feature to enable accurate and efficient retrieval of massive image data. Experimental results demonstrate the effectiveness of retrieval performance of the proposed algorithm and possible practical application of the retrieval system in lace fabric industry to improve management efficiency.

关键词： Training Industries Shape Image processing Conferences Neural networks Image retrieval

Unsupervised concatenation hashing via combining subspace learning and graph embedding for cross-Modal image retrieval

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yu, Jun Wu, Xiao-Jun School of IoT Engineering Jiangnan University Wuxi214122 China The Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China

Different from the content-based image retrieval methods, cross-modal image retrieval methods uncover the rich semantic-level information of social images to further understand image contents. As multiple modal data depict a common object from multiple perspectives, many works focus on learning the unified subspace representation. Recently, hash representation has received much attention in the retrieval field. In common Hamming space, how to directly preserve the local manifold structure among objects become an interesting problem. Most of the unsupervised hashing methods attempt to solve it by constructing a neighborhood graph on every modality respectively. However, it is hard to decide the weight factor of each graph to get the optimal graph. To overcome this problem, we adopt the concatenated features to represent the common object since the information implied by different modalities is complementary. In our framework, Locally Linear Embedding and Locality Preserving Projection are introduced to reconstruct the manifold structure of the original space. Besides, The 2,1-norm constraint is imposed on the projection matrices to explore the discriminative hashing functions. Extensive experiments are performed on three public datasets and the experimental results show that our method outperforms several classic unsupervised hashing models. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantics

Cross-modal subspace learning via Kernel correlation maximization and discriminative structure preserving

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yu, Jun Wu, Xiao-Jun School of IoT Engineering Jiangnan University Wuxi214122 China The Jiangsu Provincial Engineering Laboratory of Pattern Recognition Computational Intelligence Jiangnan University Wuxi214122 China

The measure between heterogeneous data is still an open problem. Many research works have been developed to learn a common subspace where the similarity between different modalities can be calculated directly. However, most of existing works focus on learning a latent subspace but the semantically structural information is not well preserved. Thus, these approaches cannot get desired results. In this paper, we propose a novel framework, termed Cross-modal subspace learning via Kernel correlation maximization and Discriminative structure-preserving (CKD), to solve this problem in two aspects. Firstly, we construct a shared semantic graph to make each modality data preserve the neighbor relationship semantically. Secondly, we introduce the Hilbert-Schmidt Independence Criteria (HSIC) to ensure the consistency between feature-similarity and semantic-similarity of samples. Our model not only considers the inter-modality correlation by maximizing the kernel correlation but also preserves the semantically structural information within each modality. The extensive experiments are performed to evaluate the proposed framework on the three public datasets. The experimental results demonstrated that the proposed CKD is competitive compared with the classic subspace learning methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantics

Dual-Branch Reconstruction Network for Industrial Anomaly Detection with RGB-D Data

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bi, Chenyang Li, Yueyang Luo, Haichi Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi China College of Internet of Things Engineering Jiangnan University 1800 Lihu Avenue Jiangsu Wuxi China

Unsupervised anomaly detection methods are at the forefront of industrial anomaly detection efforts and have made notable progress. Previous work primarily used 2D information as input, but multi-modal industrial anomaly detection based on 3D point clouds and RGB images is just beginning to emerge. The regular approach involves utilizing large pre-trained models for feature representation and storing them in memory banks. However, the above methods require a longer inference time and higher memory usage, which cannot meet the real-time requirements of the industry. To overcome these issues, we propose a lightweight dual-branch reconstruction network(DBRN) based on RGB-D input, learning the decision boundary between normal and abnormal examples. The requirement for alignment between the two modalities is eliminated by using depth maps instead of point cloud input. Furthermore, we introduce an importance scoring module in the discriminative network to assist in fusing features from these two modalities, thereby obtaining a comprehensive discriminative result. DBRN achieves 92.8% AUROC with high inference efficiency on the MVTec 3D-AD dataset without large pre-trained models and memory banks. Copyright © 2023, The Authors. All rights reserved.

关键词： Anomaly detection