{"schema":"hottub-news/story/v1","story":"st_s6diajp3pu6mzy6is4oa","title":"Video, Ergo Genero: Unifying Video Tasks via Spatiotemporal Analogy","title_en":null,"outlets":1,"brief":null,"page":"https://hottub.news/stories/video-ergo-genero-unifying-video-tasks-via-spatiotemporal-analogy-s6diajp3pu","count":1,"items":[{"id":"n_s6diajp3pu6mzy6is4oa","seq":592963,"kind":"article","title":"Video, Ergo Genero: Unifying Video Tasks via Spatiotemporal Analogy","url":"https://arxiv.org/abs/2609.33935","summary":"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…","published":"2026-09-29T04:00:00Z","seen":"2026-09-29T06:10:00Z","lang":"en","source":{"id":"kite-arxiv-org-1637f0","name":"arxiv.org","domain":"rss.arxiv.org"},"via":"kite-arxiv-org-1637f0","topics":["photonics","cs.cv","cs.ai"],"authors":["Chia-Hsiang Kao, Belinda Zeng, Bharath Hariharan, Menglin Jia"],"entities":[{"id":"Q98069877","name":"video","type":"other"}],"story":"st_s6diajp3pu6mzy6is4oa","category":"science-technology","category_p":0.699999988079071,"sentiment":"neutral","tone":0.14000000059604645,"political":0.019999999552965164}]}