消息
×
loading..
Video object segmentation quality assessment without groundtruth
2025
会议录名称PROCEEDINGS OF SPIE - THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING
ISSN0277-786X
卷号13521
发表状态已发表
DOI10.1117/12.3057923
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
EISSN1996-756X
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
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Hu, Hang]的文章
[Xu, Jinzhong]的文章
[Zhang, Yunfei]的文章
百度学术
百度学术中相似的文章
[Hu, Hang]的文章
[Xu, Jinzhong]的文章
[Zhang, Yunfei]的文章
必应学术
必应学术中相似的文章
[Hu, Hang]的文章
[Xu, Jinzhong]的文章
[Zhang, Yunfei]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。