HIGHLIGHTS
- who: Cheng Jiang et al. from the National University of Defense Technology, Changsha, China have published the research: PointSwin: Modeling Self-Attention with Shifted Window on Point Cloud, in the Journal: (JOURNAL)
- what: The authors propose a new model, PointSwin, which effectively improves the prediction accuracy of point cloud classification tasks. The models in the form of Point-Wise Transformer aim to discover natural spatial relationships of point clouds. The authors compare the model with eight classical methods. The focus of the work is to explore the feasibility of the Self-Attention with Shifted-Window . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.