Can you provide the original video caption generating the instruction qa?

[valencebond]

thanks for your great work, i just want to train a dense caption model with LLM, is there a way I can get the original dense video caption?

[ninatu]

I would be also interested in original dense video captions

[mmaaz60]

Hi @valencebond @ninatu

I appreciate your interest in our work. We recently released our work called VideoGPT+ and an improved semi-automatic video annotation pipeline. All the scripts to run the pipeline are also released.

Please check it out at GitHub, HuggingFace.

Further VCG+-112K dataset is also released with separate json files for semi-automatic and human annotated videos. Check it out at HuggingFace.

[ninatu]

Hi @mmaaz60, Super! Thanks so much for an update!