Image co-segmentation based on pyramid features cross-correlation network

作     者：Jia CHEN Yasong CHEN Weihao LI Zhi LIU Sannyuya LIU Zongkai YANG 

作者机构：Faculty of Artificial Intelligence in Education Central China Normal University Data61 Commonwealth Scientific and Industrial Research Organisation (CSIRO) National Engineering Laboratory for Educational Big Data Central China Normal University 

出 版 物：《Science China(Information Sciences)》 (中国科学:信息科学(英文版))

年 卷 期：2023年第66卷第1期

页      面：316-317页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：supported by National Natural Science Foundation of China (Grant Nos. 61605054, 62077017) Hubei Provincial Natural Science Foundation (Grant No. 2021CFB659) Fundamental Research Funds for the Central Universities (Grant Nos. CCNU22QN011, CCNU20TS032) Science and Technology Innovation 2030 “New Generation Artificial Intelligence” Major Program (Grant No. 2020AAA0108804) 

主　　题：Semantics 

摘      要：Dear editor,Co-segmentation aims to segment objects with the same semantic information that simultaneously appears in two or multiple images. Vicente et al. [1] proposed the definition of object co-segmentation, i.e., “The task of jointly segmenting‘something similar’ in a group or a pair of images is commonly referred to as co-segmentation.