WLiT: Windows and Linear Transformer for Video Action Recognition
The emergence of Transformer has led to the rapid development of video understanding, but it also brings the problem of high computational complexity. Previously, there were methods to divide the feature maps into windows along the spatiotemporal dimensions and then calculate the attention. There ar...
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Artigo |
| Lingua: | Inglês |
| Pubblicazione: |
MDPI AG
2023-02-01
|
| Serie: | Sensors |
| Soggetti: | |
| Accesso online: | https://www.mdpi.com/1424-8220/23/3/1616 |
| Tags: |
Nessun Tag, puoi essere il primo ad aggiungerne!!
|