Skip to main content

Cross-domain Action Recognition

Primary supervisor

Qiuhong Ke

Existing action recognition models are designed by following the typical single-dataset  training-testing paradigm   which cannot generalise well and inevitably suffer from severe accuracy drop issue, where these recognition models are deployed to another dataset with different distributions.

Student cohort

Single Semester
Double Semester

Aim/outline

This project aims to evaluate the domain gap between action recognition datasets and investigate various methods to reduce the domain gaps.

Required knowledge

computer vision 

deep learning