In the paper, you say "ActionFormer [Anne Hendricks et al., 2017] is used as the detection head" and then give Hendricks et al.'s paper as reference. But Hendricks et al.'s paper doesn't mention any model called ActionFormer. There is one paper called [ActionFormer](https://arxiv.org/pdf/[2202.07925](https://arxiv.org/pdf/2202.07925) by Zhang et al. Did you mean that paper and an error occurred during writing? I am asking to understand the details of the detection head of the architecture for temporal action localization.
Hello,
In the paper, you say "ActionFormer [Anne Hendricks et al., 2017] is used as the detection head" and then give Hendricks et al.'s paper as reference. But Hendricks et al.'s paper doesn't mention any model called ActionFormer. There is one paper called [ActionFormer](https://arxiv.org/pdf/[2202.07925](https://arxiv.org/pdf/2202.07925) by Zhang et al. Did you mean that paper and an error occurred during writing? I am asking to understand the details of the detection head of the architecture for temporal action localization.
Bests, Püren