minseong
minseong
## TAU **Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning** * intro: CVPR (2023) * paper: https://openaccess.thecvf.com/content/CVPR2023/papers/Tan_Temporal_Attention_Unit_Towards_Efficient_Spatiotemporal_Predictive_Learning_CVPR_2023_paper.pdf
Temp
Precipitation nowcasting using transformer-based generative models and transfer learning for improved disaster preparedness https://www.sciencedirect.com/science/article/pii/S1569843224003169
https://github.com/Atten4Vis/ConditionalDETR/blob/8ea7c3f3fff49cd287855d4f13cc12a6066bc8e9/models/transformer.py#L145 Since `reference_points` does not change in the for loop, it is more efficient that pre-calculate the `obj_center`.