YOWOv3: A Lightweight Spatio-Temporal Joint Network for Video Action Detection
Spatio-temporal action detection networks, which need to simultaneously extract and fuse
spatial and temporal features, often result in existing models becoming bloated and difficult …
spatial and temporal features, often result in existing models becoming bloated and difficult …
Bi-Directional Motion Attention with Contrastive Learning for few-shot Action Recognition
H Guo, W Yu, Y Yan, H Wang - ICASSP 2024-2024 IEEE …, 2024 - ieeexplore.ieee.org
In recent years, many few-shot action recognition methods have achieved competitive
performance by adopting metric-based techniques. However, they suffer from two …
performance by adopting metric-based techniques. However, they suffer from two …