作者其他论文
文献详情
SPFTN: A Self-Paced Fine-Tuning Network for Segmenting Objects in Weakly Labelled Videos
文献类型:会议
作者:Zhang, Dingwen[1]  Yang, Le[2]  Meng, Deyu[3]  Xu, Dong[4]  Han, Junwei[5]  
机构:[1]Northwestern Polytechincal Univ, Xian, Shaanxi, Peoples R China.;
[2]Northwestern Polytechincal Univ, Xian, Shaanxi, Peoples R China.;
[3]Xi An Jiao Tong Univ, Xian, Shaanxi, Peoples R China.;
[4]Univ Sydney, Sydney, NSW, Australia.;
[5]Northwestern Polytechincal Univ, Xian, Shaanxi, Peoples R China.;
年:2017
通讯作者:Han, JW (reprint author), Northwestern Polytechincal Univ, Xian, Shaanxi, Peoples R China.
会议名称:30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
会议论文集:30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTER
页码范围:5340-5348
会议地点:Honolulu, HI
会议开始日期:2017-07-21
收录情况:EI(20181304962235)  CPCI-S(WOS:000418371405046)  
人气指数:40
浏览次数:40
被引频次:1
语言:外文
摘要:
Object segmentation in weakly labelled videos is an interesting yet challenging task, which aims at learning to perform category-specific video object segmentation by only using video-level tags. Existing works in this research area might still have some limitations, e.g., lack of effective DNN-based learning frameworks, under-exploring the context information, and requiring to leverage the unstable negative video collection, which prevent them from obtaining more promising performance. To this ...More
0
评论(0 条评论)
登录