English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Generating a video given the first several static frames is challenging as itanticipates reasonable future frames with temporal coherence. Besides videoprediction, the ability to rewind from the last frame or infilling between thehead and tail is also crucial, but they have rarely been explored for videocompletion. Since there could be different outcomes from the hints of just afew frames, a system that can follow natural language to perform videocompletion may significantly improve controllability. Inspired by this, weintroduce a novel task, text-guided video completion (TVC), which requests themodel to generate a video from partial frames guided by an instruction. We thenpropose Multimodal Masked Video Generation (MMVG) to address this TVC task.During training, MMVG discretizes the video frames into visual tokens and masksmost of them to perform video completion from any time point. At inferencetime, a single MMVG model can address all 3 cases of TVC, including videoprediction, rewind, and infilling, by applying corresponding maskingconditions. We evaluate MMVG in various video scenarios, including egocentric,animation, and gaming. Extensive experimental results indicate that MMVG iseffective in generating high-quality visual appearances with text guidance forTVC.

Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation