PRAI 2025

2025 the 8th International Conference on Pattern Recognition and Artificial Intelligence August 15-17, 2025 \| Guizhou, China
	Proceedings Online IEEE Xplore: PRAI 2025 Proeedings will be Indexed by Ei Compendex & Scopus (论文集会后被EI, SCOPUS检索) PRAI 2025 was listed in IEEE Official Conference Calendar
On August 16, 2025, PRAI 2025 kicked off at Guizhou University, co-hosted by Guizhou University and IEEE, and organized by its School of Big Data and Information Engineering. Supported by institutions like University of Electronic Science and Technology of China, nearly 100 experts and students worldwide gathered in Guiyang. The opening ceremony, hosted by Professor Zhang Li, was attended by guests including Vice President of Guizhou University Xu Wang. Professor Huang Yongfeng from Nanjing University presided over keynote speeches. Scholars from Tsinghua University, Shanghai Jiao Tong University, Saudi Arabia’s Prince Sultan University and Italy’s Politecnico di Milano delivered talks on topics like radio astronomy data analysis and AI for industrial prediction. Lasting three days, the conference also included special reports and poster sessions, covering intelligent data analysis, medical image processing, etc. On August 15, attendees visited the National Big Data (Guizhou) Comprehensive Pilot Zone Exhibition Center. PRAI 2025 aims to boost academic-industrial integration in AI and pattern recognition. 2025年IEEE第八届模式识别与人工智能国际会议（PRAI 2025）于2025年8月16日在贵州大学隆重开幕。此次大会由贵州大学与IEEE联合主办，贵州大学大数据与信息工程学院承办，会议获得电子科技大学、西安微电子技术研究所、贵州师范大学、西南石油大学、西华师范大学、四川轻化工大学、中南林业科技大学等单位的大力支持。来自国内外知名高校和科研院所近百位专家学者及研究生齐聚贵阳，共同探讨该领域的最新研究进展与应用前景。 . PRAI 2024 Special Sessions 特别主题专场: Special Session 1: Information Visualization using Computational Intelligent Systems Special Session 2: Artificial Intelligence for Aerospace Applications Special Session 3: Intelligent Data Analysis and Cyber Security Special Session 4: Multimodal Affective Computing and Applications v Best Paper Award InStitch: An Incremental Approach to Stitching Low-overlap Images Author(s): Ning Li, Haifeng Zhao, Mingwei Cao Design of an Energy-Efficient Hybrid-Precision Neural Network Accelerator with a Unified Memory-Compute Architecture Author(s): Feng Jiao, Siying Bi, Shu Wang, Zhong Ma, Jin Huang, Siwei Xiang, Chen Yang Galaxy Image Reconstruction from Sparse Sampling using a Stripformer-based Deep Learning Network Author(s): Zujuan Xu, Li Zhang, Yuxin Xia, Xinglong Wang Outstanding Paper Nomination Award Cliva-Med: A Lightweight Vision-Language Model for Medical Visual Question Answering Authors: Juni Stefanus Santoso, Xiaohan Ma, Kehui Song, Rize Jin, Xuguang Qiu and Hongbo Zhao MUST: Fast Cardiac MR-to-US Image Conversion via Style Transfer Authors: Yusong Wang, Hongmei Zhang and Bo Peng GrapeCPNet: A Data-Driven Deep Learning Approach for Automated 3D Phenotyping and Predictive Analytics in Grape Cultivation Author: Sumit Mamtani Temporal Knowledge Graph Reasoning with Dynamic Context-Aware Attention and Evolutionary Learning Authors: Qingkui Chen, Siling Feng, Mengxing Huang and Yingjie Feng Primary Beam Effect Elimination for Mid-frequency SKA Imaging using a Uformer Network Authors: Yuxin Xia, Li Zhang, Xinglong Wang, Zujuan Xu 3D Reconstruction of Photovoltaic Scenes Based on Aerial Images Authors: Zilong Wang and Mingwei Cao Universal End-to-End Automated Evaluation Framework for Retrieval-Augmented Generation System Authors: Shen Li, Haochen Zhang, Yuejiao Wang, Meijuan Zhou, Zhong Ma and Feng Liang
The Excellent Presentation Winners Analysis of User-Privacy, Third-Party Data Sharing and Consent Mechanism on Online Pharmacy Websites in Ontario Atikor Ibodeng, Zuhaibuddin Bhutto, Yan Yan, Sampsa Rauti, Ville Leppänen, Adegboola Adelabu, and Wenjun Lin Yan Yan, University of Guelph, Canada VQA-driven Reranking Strategies for Improved Video Retrieval Kazuya Ueki Kazuya Ueki, Meisei University, Japan Augmented Hybrid Cost Volume Network for Stereo Matching Chenglin Dai Chenglin Dai, Guangzhou Huali College, China Deep Learning-Based Multiparametric Fusion of Diffusion MRI for Improved Prediction of Diabetic Kidney Disease Jian Liu, Daoyu Yang, Rongpin Wang and Xianchun Zeng Jian Liu, Guizhou University, China Collaborative Anomaly Detection Using Agent-Based Modeling in Smart Manufacturing Shuai Yuan, Haoxu Nong, Yunbo Rao Shuai Yuan, University of Electronic Science and Technology of China, China Decoding FRB energetics and frequency features hidden by observational incompleteness Chen-Ran Hu, Yong-Feng Huang, Jin-Jun Geng, Chen Deng, Ze-Cheng Zou, Xiao-Fei Dong, Yi-Dan Wang, Pei Wang, Fan Xu, Lang Cui, Song-Bo Zhang, Xue-Feng Wu Chen-Ran Hu, Nanjing University, China Cliva-Med: A Lightweight Vision-Language Model for Medical Visual Question Answering Juni Stefanus Santoso, Xiaohan Ma, Kehui Song, Rize Jin, Xuguang Qiu, Hongbo Zhao Rize Jin, Tiangong University, China Design and Application of an Evaluation System for Large Language Models Ying Shen, Zhiyuan Cao and Mingang Chen Zhiyuan Cao, Shanghai Development Center of Computer Software Technology, China Galaxy Image Reconstruction from Sparse Sampling using a Stripformer-based Deep Learning Network Zujuan Xu, Li Zhang,Yuxin Xia, Xinglong Wang Zujuan Xu, Guizhou University, China MIDI and Text Conditioned Diffusion Model for Style-Controlled Music Generation Dan GUO, Sha YU Dan Guo, Guizhou University, China CT Image Automatic Recognition Method Based on Two-Dimensional Segmentation and Three- Dimensional Visualization Baixiang Zeng, Zhiyu Gao, Haibin Lan, Linhai Xu, Wei Guan, Xiaolong Chen, Lindan Zheng, Qianni Wang, Shuangwei Yu, Changsheng Zhang, Jian Fu Baixiang Zeng, Beihang University, China An Improved Bat Algorithm with Multi-strategy for Multi-robot Path Planning Fangyan Nie, Pingfeng Zhang, Ranran Ao, Demin Zhang and Zhenlin Lu Fangyan Nie, Guizhou University of Commerce, China A Novel Hybrid Prediction Model of Stock Closing Price Based on CEEMDAN-SE-VMD and ARIMA-CNN-BiLSTM-Attention PeiyaoWang ,Chengdu Jincheng College, China FusionTrack: An Adaptive Hybrid Tracking Framework Overcoming Rapid Object Motion, Frequent Occlusions, Dynamic Scene Transitions, and Appearance-Scale Variations Akhil Penta, Vaibhav Adwani, Ankush Chopra Akhil Penta, Tredence Analytics, Bangalore, India. Dynamic Document Clustering through Topic-Level Continuity and Cluster Propagation Jingjing Xue, Ruina Bai and Ruizhang Huang JingjingXue, Guizhou University, China DFECformer: An iTransformer-Based Model with Variable Differential and Frequency Enhanced Channel Attention for Multivariate Time Series Prediction Desong Chen, Xi Yu, Mengji Yang, Xiaodong Yu and Shichun He Desong Chen, Chengdu University, China