Search Results for author: Lin Sui

Found 3 papers, 2 papers with code

A Simple and Efficient Pipeline to Build an End-to-End Spatial-Temporal Action Detector

1 code implementation7 Jun 2022 Lin Sui, Chen-Lin Zhang, Lixin Gu, Feng Han

Some existing methods build one-stage pipelines, But a large performance drop exists with the vanilla one-stage pipeline and extra classification modules are needed to achieve comparable performance.

Action Classification Action Detection +1

Salvage of Supervision in Weakly Supervised Object Detection

no code implementations CVPR 2022 Lin Sui, Chen-Lin Zhang, Jianxin Wu

However, the lack of bounding-box supervision makes its accuracy much lower than fully supervised object detection (FSOD), and currently modern FSOD techniques cannot be applied to WSOD.

Object object-detection +2

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