Meituan Technology Team

Jun 3, 2021 · Artificial Intelligence

VisTR: End-to-End Video Instance Segmentation with Transformers

VisTR redefines video instance segmentation as an end‑to‑end sequence‑to‑sequence task, using a CNN backbone, Transformer encoder‑decoder with instance queries, and Hungarian matching to jointly predict masks, classes, and tracks across frames, achieving state‑of‑the‑art accuracy (40.1 AP) and 57.7 FPS on YouTube‑VIS.