Video Object Segmentation using Point-based Memory Network
作者：
Highlights：
• Our point-based refinement module only considers the uncertain points rather than all the points when performing matching on the finer scales.
• Our adaptive matching module which flexibly assigns each memory feature point with an appropriate matching scheme.
• The proposed module can better adapt to video contexts and achieve better complementary between different matching schemes.
• Our PMNet achieves the state-of-the-art performance on several benchmark datasets while retaining competitive efficiency.
摘要
•Our point-based refinement module only considers the uncertain points rather than all the points when performing matching on the finer scales.•Our adaptive matching module which flexibly assigns each memory feature point with an appropriate matching scheme.•The proposed module can better adapt to video contexts and achieve better complementary between different matching schemes.•Our PMNet achieves the state-of-the-art performance on several benchmark datasets while retaining competitive efficiency.
论文关键词：Video object segmentation,Point-based feature matching,Adaptive matching module
论文评审过程：Received 14 April 2022, Revised 8 August 2022, Accepted 25 September 2022, Available online 27 September 2022, Version of Record 6 October 2022.
论文官网地址：https://doi.org/10.1016/j.patcog.2022.109073
