Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion

Ho Kei Cheng, Yu-Wing Tai, Chi-Keung Tang. Published in CVPR, 2021.

[Code & Data] [arXiv] [PDF]

Proposes a more user-friendly and efficient paradigm of iVOS in which interactions and propagations are decoupled, with the user’s intention captured by a novel difference-aware fusion module.