Ever watched a video where elements smoothly move, change size, or transform, and wondered how it's done? Welcome to the world of keyframe animations! If you're new to video editing and animation, ...

Addressing the pain point that "text only provides high-level semantics, while keyframes provide precise spatial-temporal constraints but are difficult to coordinate with text," this paper proposes a ...

description [CVPR 2025][Video Understanding][Long Video Understanding] This paper proposes DrVideo, which reformulates **long video understanding as a long document understanding** task: it first ...

Abstract: Multimodal large language models (MLLMs) have enabled open-world visual understanding by injecting visual input as extra tokens into large language models (LLMs) as contexts. However, when ...