video

Definition

A sequence of image frames over time. Recognition on video gains motion and temporal context; generation on video takes on the much harder requirement that frames stay consistent — objects persist, lighting does not flicker, motion stays plausible. Because raw video is enormous, practical systems compress along the time axis or work in a learned latent space rather than on pixels.

Explainers using this term

• Paper Walkthrough — Beyond Retrieval: LatentStream Turns Retrieved Video Into Latent MemoryBeyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding
• Paper Walkthrough — The Missing Temporal Link: Putting Script Timing on the Video–Audio Axis with Temporal Context RoutingThe Missing Temporal Link: Temporal Context Routing for Script-Driven Audio-Video Generation
• SolarWM: Training on 5 Seconds, Walking for an Hour — and Opening the Whole StackSolarWM: Open Data and Scalable Training for Long-Horizon Video World Models