Action recognition using attention-based spatio-temporal VLAD networks and adaptive video sequences optimization
Abstract In the field of human action recognition, it is a long-standing challenge to characterize the video-level spatio-temporal features effectively. This is attributable in part to the inability of CNN to model long-range temporal information, especially for actions that consist of multiple stag...
| Autori principali: | , , |
|---|---|
| Natura: | Articolo |
| Lingua: | English |
| Pubblicazione: |
Nature Portfolio
2024-10-01
|
| Serie: | Scientific Reports |
| Accesso online: | https://doi.org/10.1038/s41598-024-75640-6 |