Search Results for author: Shenghai Rong

Found 3 papers, 2 papers with code

Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach

1 code implementation ICCV 2023 Qinying Liu, Zilei Wang, Shenghai Rong, Junjie Li, Yixin Zhang

It comprises two core components: a snippet clustering component that groups the snippets into multiple latent clusters and a cluster classification component that further classifies the cluster as foreground or background.

Classification Clustering +4

Improve Temporal Action Proposals using Hierarchical Context

no code implementations Pattern Recognition 2023 Qinying Liu, Zilei Wang, Shenghai Rong

In this paper, we propose a novel hierarchical context network (HCN) to further explore the snippet-level and proposal-level contexts, which are used to improve the representations of snippets and proposals, respectively.

Action Detection Temporal Action Proposal Generation

Boundary-Enhanced Co-Training for Weakly Supervised Semantic Segmentation

1 code implementation CVPR 2023 Shenghai Rong, Bohai Tu, Zilei Wang, Junjie Li

The existing weakly supervised semantic segmentation (WSSS) methods pay much attention to generating accurate and complete class activation maps (CAMs) as pseudo-labels, while ignoring the importance of training the segmentation networks.

Segmentation Weakly supervised Semantic Segmentation +1

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