CodeCap-Bench: Can Code Serve as a Good Video Caption?
CodeCap-Bench explores executable code as a precise, unambiguous video captioning method, outperforming natural language in preserving spatial and temporal details.
ls ./papers | grep "#video captioning"
Trending AI research papers from Hugging Face, summarized in plain language: what each paper does, why it matters and where to read more.
2 papers · #video captioning
CodeCap-Bench explores executable code as a precise, unambiguous video captioning method, outperforming natural language in preserving spatial and temporal details.
Hy-Nomas is an 8B-parameter video world model enabling free-form multi-turn interaction with text instructions and continuous camera control, advancing interactive world generation.