Global Motion Understanding in Large-Scale Video Object Segmentation

no code implementations • 11 May 2024 • Volodymyr Fedynyak, Yaroslav Romanus, Oles Dobosevych, Igor Babin, Roman Riazantsev

Namely, we focus on integrating scene global motion knowledge to improve large-scale semi-supervised Video Object Segmentation.

Instance Segmentation Optical Flow Estimation +5

DeVOS: Flow-Guided Deformable Transformer for Video Object Segmentation

no code implementations • 11 May 2024 • Volodymyr Fedynyak, Yaroslav Romanus, Bohdan Hlovatskyi, Bohdan Sydor, Oles Dobosevych, Igor Babin, Roman Riazantsev

For short-term local propagation, we propose a novel attention mechanism ADVA (Adaptive Deformable Video Attention), allowing the adaption of similarity search region to query-specific semantic features, which ensures robust tracking of complex shape and scale changes.

Optical Flow Estimation Semantic Segmentation +2