about the code of the reference work "Pang et al."

[YukiFan]

thanks for your excellent work and open-sourced code in the paper, you say "For the multimodal baseline [43], we remove the mutual loss and multimodal fusion modules and leverage the vanilla attention-based variant (‡) for comparison. ", but I can't find the released code of the work baseline [43]----pang et al "Violence Detection in Videos Based on Fusing Visual and Audio Information. " could you please share the link you found? Thank you very much

[JustinYuu]

Hi, Thanks for your interest in our work! To the best of our knowledge, the baseline method [43] does not release publicly available codes, thus we re-implement this method based on model details reported in the raw paper. Considering the potential copyright risk, we do not release the re-implemented codes, but we suggest you consider trying to re-implement on your own since we found that the re-implementation of the baseline method [43] is not too complicated if removing the mutual loss and multimodal fusion modules.

[YukiFan]

Thank you; my understanding was erroneous. I assumed you discovered open-source code, and I will attempt to re-implement it. Again, thanks.