2 papers
cs.CV2021
WeClick: Weakly-Supervised Video Semantic Segmentation with Click Annotations
Peidong Liu, Zibin He, Xiyu Yan +4
Compared with tedious per-pixel mask annotating, it is much easier to annotate data by clicks, which costs only several seconds for an image. However, applying clicks to learn vide…
cs.CV2019
Deep Flow Collaborative Network for Online Visual Tracking
Peidong Liu, Xiyu Yan, Yong Jiang +1
The deep learning-based visual tracking algorithms such as MDNet achieve high performance leveraging to the feature extraction ability of a deep neural network. However, the tracki…