Object Level Grouping for Video Shots

作者：Josef Sivic, Frederik Schaffalitzky, Andrew Zisserman

摘要

We describe a method for automatically obtaining object representations suitable for retrieval from generic video shots. The object representation consists of an association of frame regions. These regions provide exemplars of the object’s possible visual appearances.

论文关键词：3D object retrieval in videos, tracking affine covariant regions, independent motion segmentation, robust affine factorization

论文评审过程：

论文官网地址：https://doi.org/10.1007/s11263-005-4264-y