InternVideo icon indicating copy to clipboard operation
InternVideo copied to clipboard

a question about a statement in the paper

Open puren opened this issue 1 year ago • 1 comments

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 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

puren avatar Oct 30 '24 11:10 puren

Apologies for the incorrect citation, and thank you for bringing it to our attention. We will promptly correct the error in the paper on arXiv.

shepnerd avatar Oct 30 '24 14:10 shepnerd