Search Results for author: Kaiyuan Wan

Found 1 papers, 1 papers with code

Visual Saliency Transformer

1 code implementation • ICCV 2021 • Nian Liu, Ni Zhang, Kaiyuan Wan, Ling Shao, Junwei Han

We also develop a token-based multi-task decoder to simultaneously perform saliency and boundary detection by introducing task-related tokens and a novel patch-task-attention mechanism.

Ranked #1 on RGB-D Salient Object Detection on NJUD

Boundary Detection object-detection +4

116

Paper
Code

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