郑州大学学报（工学版）2025，Vol.46Issue(5)：51-59,9.DOI:10.13705/j.issn.1671-6833.2025.02.011
基于动态记忆与运动信息的目标中心视频预测算法
Object-centric Video Prediction Algorithm Based on Dynamic Memory and Motion Information
摘要
Abstract
In response to the challenges of maintaining structural and temporal consistency between video frames in video prediction tasks,an object-centric video prediction algorithm based on dynamic memory and motion informa-tion was proposed.Firstly,by introducing an object-centric model,the objects in the scene were decoupled to en-sure the consistency and stability of long-term dynamic modeling of video objects,to effectively maintain the struc-tural consistency of video objects.Secondly,an object dynamic memory module was designed to capture the long-term dependencies of videos and model object dynamics,to overcome the shortcomings of existing video prediction methods in predicting dynamic interactions between objects and enhancing the temporal consistency of video ob-jects.Thirdly,the feature similarity matrix of adjacent frames was used to capture the motion information between frames and model the spatiotemporal relationships of the video sequence,further strengthened the temporal consis-tency of video objects.Finally,a cross-attention mechanism was utilized to integrate the temporal and structural in-formation of video objects,further improved the video prediction performance.Experiments on video prediction were conducted on the Obj3D and CLEVRER datasets with complex object interactions.The results showed that compared to the state-of-the-art object-centric video prediction algorithms,the proposed algorithm increased per-formance on the PSNR and SSIM metrics by 4.5%and 1.4%,respectively,and also achieved a 20%reduction in the LPIPS metric.关键词
视频预测/目标中心学习/场景解析/无监督学习/时空预测Key words
video prediction/object-centric learning/scene parsing/unsupervised learning/spatiotemporal predic-tion分类
信息技术与安全科学引用本文复制引用
韩晨晨,卢宪凯,王志成,熊筱舟..基于动态记忆与运动信息的目标中心视频预测算法[J].郑州大学学报（工学版）,2025,46(5):51-59,9.基金项目
山东省自然科学优秀青年基金资助项目(ZR2024YQ006) （ZR2024YQ006）
山东省高等学校青创团队计划(2023KJ027) （2023KJ027）
