HIGHLIGHTS
- who: Ruoxi Sun and collaborators from the Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai, China School of Information Science and Technology, ShanghaiTech University, Shanghai, China have published the research: WLiT: Windows and Linear Transformer for Video Action Recognition, in the Journal: Sensors 2023, 23, 1616. of 28/01/2023
- what: While this approach has a powerful global context modeling capability, its computational complexity grows quadratically with token length, limiting its ability to scale to high-resolution scenarios. The authors propose a complementary framework of Windows and Linear Transformer (WLiT), which ensures the ability . . .
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.