Add a new work *FDVS* which is published on IEEE TCSVT

[bolixinyu]

Dear ttengwang,

I am submitting a pull request to contribute to the Awesome_Long_Form_Video_Understanding with a new work titled "Towards Long Video Understanding via Fine-detailed Video Story Generation". This article transforms long videos into hierarchical textual representations that contain multi-granularity information of the video. With these representations, FDVS is applicable to various tasks without any fine-tuning., which I believe would be a valuable addition to the repository.

Changes Made:

Added "Towards Long Video Understanding via Fine-detailed Video Story Generation" to the Long-Term Video Large Language Models.