International Journal of Pattern Recognition and Artificial Intelligence最新文献_第6页

Evolutionary Gravitational Neocognitron Neural Network based Blood Flow Velocity Prediction using Multi-Exposure Laser Speckle Contrast Imaging 利用多曝光激光斑点对比成像进行基于进化引力新认知神经网络的血流速度预测

IF 1.5 4区计算机科学

International Journal of Pattern Recognition and Artificial Intelligence Pub Date : 2023-11-23 DOI: 10.1142/s0218001423560232

Pankaj Jain, Saurabh Gupta

引用次数: 0

Muti-scale feature refined network for human pose estimation 人体姿态估计的多尺度特征细化网络

4区计算机科学

International Journal of Pattern Recognition and Artificial Intelligence Pub Date : 2023-11-09 DOI: 10.1142/s0218001423560220

Qiaoning Yang, Xiaodong Ji, Xiuhui Yang

{"title":"Muti-scale feature refined network for human pose estimation","authors":"Qiaoning Yang, Xiaodong Ji, Xiuhui Yang","doi":"10.1142/s0218001423560220","DOIUrl":"https://doi.org/10.1142/s0218001423560220","url":null,"abstract":"Occlusive keypoints has been a challenge for human pose estimation, especially the mutual occlusion of human bodies. One possible solution to this problem is to utilize multi-scale features, where small scale features are capable of identifying keypoints, while large-scale features can capture the relationship between keypoints. Feature fusion among multi-scale features allows for the exchange of information between keypoints, facilitating the inference of occluded keypoints based on the identified keypoints. However, it’s found that there are invalid features in feature fusion which will interfere valid feature. In this paper, we propose multi-scale feature refined network (MSFRNet) based on HRNet and a new attention module namely multi-resolution attention module (MRAM). The proposed MRAM is designed to strengthen the effective information while suppressing redundant information. It has multiple inputs and outputs and can learn the relationships between keypoints while retaining detailed information. The proposed MSFRNet outperforms HRNet, achieving a 1.4[Formula: see text]AP improvement on the COCO dataset with only a marginal computational increase of 0.35 GFLOPs. Additionally, it demonstrates superior performance with a 0.9[Formula: see text]AP, 0.7[Formula: see text]AP, and 1.8[Formula: see text]AP improvement on the MPII, CrowdPose and OCHuman datasets, respectively. Furthermore, compared with the latest attention mechanism PSA, the MSFRNet exhibits lower computational cost while maintaining the same pose-estimation accuracy.","PeriodicalId":54949,"journal":{"name":"International Journal of Pattern Recognition and Artificial Intelligence","volume":" 28","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135191970","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: 0

Cancer prediction using Feature fusion and Taylor-TSA based GAN with gene expression data 基于基因表达数据的特征融合和基于Taylor-TSA的GAN的癌症预测

4区计算机科学

International Journal of Pattern Recognition and Artificial Intelligence Pub Date : 2023-11-07 DOI: 10.1142/s0218001423570082

J. Jeyabharathi, S. Velliangiri, S. Iwin Thanakumar Joseph, C. Sorna Chandra Devadass

引用次数: 0

Query Preference Analysis on Cascade Inference Human-Object Interaction Detection Transformer 级联推理人-物交互检测变压器查询偏好分析

4区计算机科学

International Journal of Pattern Recognition and Artificial Intelligence Pub Date : 2023-10-28 DOI: 10.1142/s0218001423560219

Weizhe Jia, Shiwei Ma

{"title":"Query Preference Analysis on Cascade Inference Human-Object Interaction Detection Transformer","authors":"Weizhe Jia, Shiwei Ma","doi":"10.1142/s0218001423560219","DOIUrl":"https://doi.org/10.1142/s0218001423560219","url":null,"abstract":"Detection transformers (DETR) have provided a novel solution to human–object interaction detection in a set-prediction manner, thanks to expressive learnable queries. However, few studies covered how queries implicitly affect model behaviors, which might contain clues for model improvement. Therefore, we propose two dataset-based analysis tools: score state space and query preference map. They provide data on the distribution of model predictions, which can reveal overall-level and query-level model properties. Starting with our baseline model, we find the model naturally regresses object boxes to overlap human boxes in the edge case of no-object verbs (stand, etc.), even without a related loss. We encourage this by patching the supervision with virtual objects, resulting in more stable query preference. Moreover, we show that two-stage decoders designed for cascade inference do not decouple tasks as intended. We infer this is caused by the empty instances used as negative samples, which suggests a redesign in the matching scheme. Further, we reveal how adding an oracle-query-based teacher model affects query roles with a tiny gain, indicating room for refinement. Our findings demonstrate how a simple focus on query behaviors can provide insights for improving models.","PeriodicalId":54949,"journal":{"name":"International Journal of Pattern Recognition and Artificial Intelligence","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136157170","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: 0

Artificial Intelligent Manual-computer Dialogue Support platform in Hospital 医院人工智能人机对话支持平台

4区计算机科学

International Journal of Pattern Recognition and Artificial Intelligence Pub Date : 2023-10-27 DOI: 10.1142/s021800142359019x

Xin Xia, Yunlong Ma, Ye Luo, Jianwei Lu

引用次数: 0

A New Lightweight Script Independent Scene Text Style Transfer Network 一个新的轻量级脚本独立场景文本风格传输网络

4区计算机科学

International Journal of Pattern Recognition and Artificial Intelligence Pub Date : 2023-10-06 DOI: 10.1142/s0218001423530038

Palaiahnakote Shivakumara, Ayush Roy, Lokesh Nandanwar, Umapada Pal, Yue Lu, Cheng-Lin Liu

引用次数: 0

An Efficient Approach of Assessing Quality of Blurred Image 一种评估模糊图像质量的有效方法

4区计算机科学

International Journal of Pattern Recognition and Artificial Intelligence Pub Date : 2023-10-06 DOI: 10.1142/s0218001423540186

Md Amir Baig, Athar A. Moinuddin, Ekram Khan, Mohammed Ghanbari

引用次数: 0

Medical Image Segmentation and Classification using Modified DoubleU-Net and PolyNet Deep Neural Networks 基于改进DoubleU-Net和PolyNet深度神经网络的医学图像分割与分类

4区计算机科学

International Journal of Pattern Recognition and Artificial Intelligence Pub Date : 2023-10-06 DOI: 10.1142/s0218001423570136

S. Sasikumar, R. Pugalenthi, G.M. Sasikala, M.P. Rajakumar

引用次数: 0

Few-shot Person Re-identification Based on Meta Learning with a Compression and Stimulation Module 基于压缩和刺激元学习的少镜头人物再识别

4区计算机科学

International Journal of Pattern Recognition and Artificial Intelligence Pub Date : 2023-10-06 DOI: 10.1142/s0218001423560207

Jinying Cao, Hua Han, Li Huang

引用次数: 0

A robust kernel least mean square algorithm and its quantization 一种鲁棒核最小均方算法及其量化

4区计算机科学

International Journal of Pattern Recognition and Artificial Intelligence Pub Date : 2023-10-06 DOI: 10.1142/s0218001423590206

Huo Yuan-lian, Liu Jie, Qi Yong-feng, Hu Zhi-ling, Yang Kuo-jian

引用次数: 0