Search Results for author: Adrià Caelles

Found 1 papers, 1 papers with code

DeVIS: Making Deformable Transformers Work for Video Instance Segmentation

1 code implementation • 22 Jul 2022 • Adrià Caelles, Tim Meinhardt, Guillem Brasó, Laura Leal-Taixé

To reason about all VIS subtasks jointly over multiple frames, we present temporal multi-scale deformable attention with instance-aware object queries.

Ranked #15 on Video Instance Segmentation on YouTube-VIS 2021

Instance Segmentation object-detection +4

Paper
Code

Cannot find the paper you are looking for? You can Submit a new open access paper.