
CK
Chia-Hsiang Kao, Belinda Zeng, Bharath Hariharan, Menglin Jia
· 1 min read
ResearcharXiv cs.CV
Video, Ergo Genero: Unifying Video Tasks via Spatiotemporal Analogy
arXiv:2609.33935v1 Announce Type: new
Abstract: Adapting video models to new tasks typically requires dedicated data curation and fine-tuning. While visual analogy provides a training-free alternative by specifying tasks in-context, it remains restricted to the image domain. To explore whether analogy-based methods can unify diverse video tasks and generalize to out-of-distribution scenarios, we introduce ViGeo, a framework that extends visual in-context learning to the video domain via spatiotemporal canvas completion. Evaluated on a diverse task taxonomy with a strict train-test split, ViGeo generalizes to unseen video manipulations and zero-shot modalities (e.g., event cameras). Finally, we identify task internalization, where a query format associated with a pretrained task overrides the demonstration, and show that this shortcut can be removed with a small amount of task-unrelated data, highlighting the need to decorrelate prompt format from task identity.
Original source
This story was published by arXiv cs.CV and written by Chia-Hsiang Kao, Belinda Zeng, Bharath Hariharan, Menglin Jia. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


