Skip to main content

and
  1. No Access

    Chapter and Conference Paper

    Video Instance Segmentation via Multi-Scale Spatio-Temporal Split Attention Transformer

    State-of-the-art transformer-based video instance segmentation (VIS) approaches typically utilize either single-scale spatio-temporal features or per-frame multi-scale features during the attention computation...

    Omkar Thawakar, Sanath Narayan, Jiale Cao, Hisham Cholakkal in Computer Vision – ECCV 2022 (2022)