Visual Computing for Industry Biomedicine and Art最新文献_第6页

Local imperceptible adversarial attacks against human pose estimation networks. 针对人体姿态估计网络的局部难以察觉的对抗攻击。

IF 2.8 4区计算机科学

Visual Computing for Industry Biomedicine and Art Pub Date : 2023-11-21 DOI: 10.1186/s42492-023-00148-1

Fuchang Liu, Shen Zhang, Hao Wang, Caiping Yan, Yongwei Miao

{"title":"Local imperceptible adversarial attacks against human pose estimation networks.","authors":"Fuchang Liu, Shen Zhang, Hao Wang, Caiping Yan, Yongwei Miao","doi":"10.1186/s42492-023-00148-1","DOIUrl":"10.1186/s42492-023-00148-1","url":null,"abstract":"Deep neural networks are vulnerable to attacks from adversarial inputs. Corresponding attack research on human pose estimation (HPE), particularly for body joint detection, has been largely unexplored. Transferring classification-based attack methods to body joint regression tasks is not straightforward. Another issue is that the attack effectiveness and imperceptibility contradict each other. To solve these issues, we propose local imperceptible attacks on HPE networks. In particular, we reformulate imperceptible attacks on body joint regression into a constrained maximum allowable attack. Furthermore, we approximate the solution using iterative gradient-based strength refinement and greedy-based pixel selection. Our method crafts effective perceptual adversarial attacks that consider both human perception and attack effectiveness. We conducted a series of imperceptible attacks against state-of-the-art HPE methods, including HigherHRNet, DEKR, and ViTPose. The experimental results demonstrate that the proposed method achieves excellent imperceptibility while maintaining attack effectiveness by significantly reducing the number of perturbed pixels. Approximately 4% of the pixels can achieve sufficient attacks on HPE.","PeriodicalId":29931,"journal":{"name":"Visual Computing for Industry Biomedicine and Art","volume":"6 1","pages":"22"},"PeriodicalIF":2.8,"publicationDate":"2023-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10661673/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138177479","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Reliable knowledge graph fact prediction via reinforcement learning. 通过强化学习进行可靠的知识图谱事实预测。

IF 2.8 4区计算机科学

Visual Computing for Industry Biomedicine and Art Pub Date : 2023-11-20 DOI: 10.1186/s42492-023-00150-7

Fangfang Zhou, Jiapeng Mi, Beiwen Zhang, Jingcheng Shi, Ran Zhang, Xiaohui Chen, Ying Zhao, Jian Zhang

{"title":"Reliable knowledge graph fact prediction via reinforcement learning.","authors":"Fangfang Zhou, Jiapeng Mi, Beiwen Zhang, Jingcheng Shi, Ran Zhang, Xiaohui Chen, Ying Zhao, Jian Zhang","doi":"10.1186/s42492-023-00150-7","DOIUrl":"10.1186/s42492-023-00150-7","url":null,"abstract":"Knowledge graph (KG) fact prediction aims to complete a KG by determining the truthfulness of predicted triples. Reinforcement learning (RL)-based approaches have been widely used for fact prediction. However, the existing approaches largely suffer from unreliable calculations on rule confidences owing to a limited number of obtained reasoning paths, thereby resulting in unreliable decisions on prediction triples. Hence, we propose a new RL-based approach named EvoPath in this study. EvoPath features a new reward mechanism based on entity heterogeneity, facilitating an agent to obtain effective reasoning paths during random walks. EvoPath also incorporates a new postwalking mechanism to leverage easily overlooked but valuable reasoning paths during RL. Both mechanisms provide sufficient reasoning paths to facilitate the reliable calculations of rule confidences, enabling EvoPath to make precise judgments about the truthfulness of prediction triples. Experiments demonstrate that EvoPath can achieve more accurate fact predictions than existing approaches.","PeriodicalId":29931,"journal":{"name":"Visual Computing for Industry Biomedicine and Art","volume":"6 1","pages":"21"},"PeriodicalIF":2.8,"publicationDate":"2023-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10657918/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138048083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Application and prospects of AI-based radiomics in ultrasound diagnosis. 基于人工智能的放射组学在超声诊断中的应用与展望。

IF 2.8 4区计算机科学

Visual Computing for Industry Biomedicine and Art Pub Date : 2023-10-13 DOI: 10.1186/s42492-023-00147-2

Haoyan Zhang, Zheling Meng, Jinyu Ru, Yaqing Meng, Kun Wang

引用次数: 0

Focus-RCNet: a lightweight recyclable waste classification algorithm based on focus and knowledge distillation. Focus RCNet：一种基于Focus和知识蒸馏的轻量级可回收垃圾分类算法。

IF 2.8 4区计算机科学

Visual Computing for Industry Biomedicine and Art Pub Date : 2023-10-11 DOI: 10.1186/s42492-023-00146-3

Dashun Zheng, Rongsheng Wang, Yaofei Duan, Patrick Cheong-Iao Pang, Tao Tan

{"title":"Focus-RCNet: a lightweight recyclable waste classification algorithm based on focus and knowledge distillation.","authors":"Dashun Zheng, Rongsheng Wang, Yaofei Duan, Patrick Cheong-Iao Pang, Tao Tan","doi":"10.1186/s42492-023-00146-3","DOIUrl":"10.1186/s42492-023-00146-3","url":null,"abstract":"Waste pollution is a significant environmental problem worldwide. With the continuous improvement in the living standards of the population and increasing richness of the consumption structure, the amount of domestic waste generated has increased dramatically, and there is an urgent need for further treatment. The rapid development of artificial intelligence has provided an effective solution for automated waste classification. However, the high computational power and complexity of algorithms make convolutional neural networks unsuitable for real-time embedded applications. In this paper, we propose a lightweight network architecture called Focus-RCNet, designed with reference to the sandglass structure of MobileNetV2, which uses deeply separable convolution to extract features from images. The Focus module is introduced to the field of recyclable waste image classification to reduce the dimensionality of features while retaining relevant information. To make the model focus more on waste image features while keeping the number of parameters small, we introduce the SimAM attention mechanism. In addition, knowledge distillation was used to further compress the number of parameters in the model. By training and testing on the TrashNet dataset, the Focus-RCNet model not only achieved an accuracy of 92[Formula: see text] but also showed high deployment mobility.","PeriodicalId":29931,"journal":{"name":"Visual Computing for Industry Biomedicine and Art","volume":"6 1","pages":"19"},"PeriodicalIF":2.8,"publicationDate":"2023-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10567611/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41214664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Novel 3D local feature descriptor of point clouds based on spatial voxel homogenization for feature matching. 一种新的基于空间体素均匀化的点云三维局部特征描述符用于特征匹配。

IF 2.8 4区计算机科学

Visual Computing for Industry Biomedicine and Art Pub Date : 2023-09-28 DOI: 10.1186/s42492-023-00145-4

Jiong Yang, Jian Zhang, Zhengyang Cai, Dongyang Fang

{"title":"Novel 3D local feature descriptor of point clouds based on spatial voxel homogenization for feature matching.","authors":"Jiong Yang, Jian Zhang, Zhengyang Cai, Dongyang Fang","doi":"10.1186/s42492-023-00145-4","DOIUrl":"10.1186/s42492-023-00145-4","url":null,"abstract":"Obtaining a 3D feature description with high descriptiveness and robustness under complicated nuisances is a significant and challenging task in 3D feature matching. This paper proposes a novel feature description consisting of a stable local reference frame (LRF) and a feature descriptor based on local spatial voxels. First, an improved LRF was designed by incorporating distance weights into Z- and X-axis calculations. Subsequently, based on the LRF and voxel segmentation, a feature descriptor based on voxel homogenization was proposed. Moreover, uniform segmentation of cube voxels was performed, considering the eigenvalues of each voxel and its neighboring voxels, thereby enhancing the stability of the description. The performance of the descriptor was strictly tested and evaluated on three public datasets, which exhibited high descriptiveness, robustness, and superior performance compared with other current methods. Furthermore, the descriptor was applied to a 3D registration trial, and the results demonstrated the reliability of our approach.","PeriodicalId":29931,"journal":{"name":"Visual Computing for Industry Biomedicine and Art","volume":"6 1","pages":"18"},"PeriodicalIF":2.8,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10539243/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41177182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Vector textures derived from higher order derivative domains for classification of colorectal polyps 基于高阶导数域的矢量纹理用于结直肠息肉的分类

IF 2.8 4区计算机科学

Visual Computing for Industry Biomedicine and Art Pub Date : 2022-06-14 DOI: 10.1186/s42492-022-00108-1

Cao, Weiguo, Pomeroy, Marc J., Liang, Zhengrong, Abbasi, Almas F., Pickhardt, Perry J., Lu, Hongbing

{"title":"Vector textures derived from higher order derivative domains for classification of colorectal polyps","authors":"Cao, Weiguo, Pomeroy, Marc J., Liang, Zhengrong, Abbasi, Almas F., Pickhardt, Perry J., Lu, Hongbing","doi":"10.1186/s42492-022-00108-1","DOIUrl":"https://doi.org/10.1186/s42492-022-00108-1","url":null,"abstract":"Textures have become widely adopted as an essential tool for lesion detection and classification through analysis of the lesion heterogeneities. In this study, higher order derivative images are being employed to combat the challenge of the poor contrast across similar tissue types among certain imaging modalities. To make good use of the derivative information, a novel concept of vector texture is firstly introduced to construct and extract several types of polyp descriptors. Two widely used differential operators, i.e., the gradient operator and Hessian operator, are utilized to generate the first and second order derivative images. These derivative volumetric images are used to produce two angle-based and two vector-based (including both angle and magnitude) textures. Next, a vector-based co-occurrence matrix is proposed to extract texture features which are fed to a random forest classifier to perform polyp classifications. To evaluate the performance of our method, experiments are implemented over a private colorectal polyp dataset obtained from computed tomographic colonography. We compare our method with four existing state-of-the-art methods and find that our method can outperform those competing methods over 4%-13% evaluated by the area under the receiver operating characteristics curves.","PeriodicalId":29931,"journal":{"name":"Visual Computing for Industry Biomedicine and Art","volume":"21 5","pages":""},"PeriodicalIF":2.8,"publicationDate":"2022-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138495077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Collision-aware interactive simulation using graph neural networks 基于图神经网络的碰撞感知交互仿真

IF 2.8 4区计算机科学

Visual Computing for Industry Biomedicine and Art Pub Date : 2022-06-07 DOI: 10.1186/s42492-022-00113-4

Zhu, Xin, Qian, Yinling, Wang, Qiong, Feng, Ziliang, Heng, Pheng-Ann

引用次数: 0

Robust facial expression recognition system in higher poses 鲁棒的高姿态面部表情识别系统

IF 2.8 4区计算机科学

Visual Computing for Industry Biomedicine and Art Pub Date : 2022-05-16 DOI: 10.1186/s42492-022-00109-0

Owusu, Ebenezer, Appati, Justice Kwame, Okae, Percy

引用次数: 1

Analytical study of two feature extraction methods in comparison with deep learning methods for classification of small metal objects 两种特征提取方法与深度学习方法在小金属物体分类中的对比分析研究

IF 2.8 4区计算机科学

Visual Computing for Industry Biomedicine and Art Pub Date : 2022-05-10 DOI: 10.1186/s42492-022-00111-6

S. Amraee, Maryam Chinipardaz, Mohammadali Charoosaei

引用次数: 5

Correction: DCAU-Net: dense convolutional attention U-Net for segmentation of intracranial aneurysm images 校正:dcaunet:用于颅内动脉瘤图像分割的密集卷积注意U-Net

IF 2.8 4区计算机科学

Visual Computing for Industry Biomedicine and Art Pub Date : 2022-05-08 DOI: 10.1186/s42492-022-00110-7

Wenwen Yuan, Yanjun Peng, Yanfei Guo, Yande Ren, Qianwen Xue

引用次数: 2