计算机科学
人工智能
计算机视觉
跟踪(教育)
匹配(统计)
目标检测
弹道
视频跟踪
代表(政治)
文本检测
运动(物理)
接头(建筑物)
模式识别(心理学)
特征提取
融合
传感器融合
运动检测
钥匙(锁)
融合机制
面子(社会学概念)
眼动
运动补偿
运动估计
匹配移动
变更检测
作者
Mingxuan Pan,Kun Xu,Yaru Chen
标识
DOI:10.1109/cvip67348.2025.11291282
摘要
In video scene text detection and tracking,challenges such as motion blur, occlusion, and target deformation often lead to unstable detection results and tracking drift. To address these issues, we propose a joint optimization framework that integrates text detection and tracking with temporal modeling to enhance robustness. Specifically, (1) a temporal information fusion method is designed to ensure consistent text representation across frames; (2) a cross-task learning strategy reuses semantic features from detection for trajectory matching while dynamically refining detection thresholds with tracking feedback. Experimental results on the ICDAR2015 Video Text Dataset indicate the effectiveness of our approach: it improves MOTA by 2.8 % and IDF1 by 1.7 % compared with GoMatching, achieving superior performance with a favorable balance between accuracy and robustness.
科研通智能强力驱动
Strongly Powered by AbleSci AI