| |||||||
ShanghaiTech University Knowledge Management System
Video object segmentation quality assessment without groundtruth | |
2025 | |
会议录名称 | PROCEEDINGS OF SPIE - THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING |
ISSN | 0277-786X |
卷号 | 13521 |
发表状态 | 已发表 |
DOI | 10.1117/12.3057923 |
摘要 | Despite recent advances in Video Object Segmentation (VOS), state-of-the-art models still face challenges with occlusion, fast motion, and long-term tracking. These difficulties often result in a noticeable degradation of segmentation accuracy as the video progresses, leading to poor performance over extended periods. To tackle these persistent issues, we propose an innovative approach that enhances video segmentation by introducing predictive segmentation heads. Building upon the Cutie model, our method enables the model to predict Intersection over Union (IoU) results without ground truth, thereby enhancing video segmentation performance in challenging scenarios. © 2025 SPIE. |
关键词 | Motion tracking Video analysis Cutie Deep learning Intersection over union Quality assessment Sam2 Segmentation quality State of the art Transformer Video objects segmentations Video segmentation |
会议名称 | 2024 International Conference on Computer Vision and Image Processing, CVIP 2024 |
会议地点 | Hangzhou, China |
会议日期 | November 15, 2024 - November 17, 2024 |
收录类别 | EI |
语种 | 英语 |
出版者 | SPIE |
EI入藏号 | 20250517790319 |
EI主题词 | Image segmentation |
EISSN | 1996-756X |
EI分类号 | 1106.3.1 Image Processing |
原始文献类型 | Conference article (CA) |
文献类型 | 会议论文 |
条目标识符 | https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/490329 |
专题 | 信息科学与技术学院 信息科学与技术学院_硕士生 |
通讯作者 | Xu, Jinzhong |
作者单位 | 1.Key Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing; 100094, China; 2.University of Chinese Academy of Sciences, Beijing; 100049, China; 3.School of Information Science and Technology, ShanghaiTech University, Shanghai; 201210, China |
推荐引用方式 GB/T 7714 | Hu, Hang,Xu, Jinzhong,Zhang, Yunfei,et al. Video object segmentation quality assessment without groundtruth[C]:SPIE,2025. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 |
修改评论
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。