VideoEditor-MoE is introduced, the first open-source mixture-of-experts framework for video editing that identifies decoupled weight decay as a strategy for stabilizing expert scaling and expands attention capacity through routed key--value experts while preserving global interactions among video tokens.
Xiao Cao, Fu-Chen Long, Yan-Song Qu et al.· 0 citations
While generative AI has significantly advanced video editing, existing methods primarily focus on single-shot or short video clips. Editing long videos with multiple instructions remains a formidable challenge. Naive chunking strategies, e.g., fixed-duration segmentation, often lead to entity fragmentation, severe edit...
Chen-Yang Wu, Fuchen Long, Bin-Yuan Huang et al.· 0 citations
The quality and diversity of instruction-based video editing datasets are steadily improving, yet existing datasets mainly focus on single editing operations and fall short in supporting compositional instruction-guided video editing. In particular, multiple editing intents must be jointly understood and faithfully exe...
Fuchen Long, Cong Wang, Zitao Gao et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.