Metraipolis › archive › dc_2b426d2e7223
Kairos: A Dataset for Fine-Grained Video-Language Modeling over Space, Time, and Dynamics — arXiv:2609.08755
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.08755
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:12:22.293Z
- SHA-256 of the archived text
8d1b10a785bf645f2cbe8cc0d6ffbd362c52b86ba6a188bd84299a583aec8784- Stable URL of this page
https://metraipolis.com/documento/dc_2b426d2e7223
How to cite
Kairos: A Dataset for Fine-Grained Video-Language Modeling over Space, Time, and Dynamics — arXiv:2609.08755 — arXiv (en), https://arxiv.org/abs/2609.08755 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2b426d2e7223 (Metraipolis archive dc_2b426d2e7223, sha256 8d1b10a785bf645f2cbe8cc0d6ffbd362c52b86ba6a188bd84299a583aec8784)
BibTeX
@misc{dc2b426d2e7223,
title = {Kairos: A Dataset for Fine-Grained Video-Language Modeling over Space, Time, and Dynamics — arXiv:2609.08755},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.08755},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2b426d2e7223; sha256 8d1b10a785bf645f2cbe8cc0d6ffbd362c52b86ba6a188bd84299a583aec8784},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08755. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Many emerging video language modeling tasks require systems to move beyond clip-level abstraction and model visual content as it unfolds over extended time horizons. However, most existing video datasets rely on coarse or sparsely aligned supervision, which compresses temporal variation and limits the ability of models to learn reusable representations of continuous visual dynamics. We introduce Kairos, a video dataset for video-language modeling with time-resolved annotations. Kairos consists of long-duration videos, ranging from ten minutes to half an hour, annotated with fine-grained temporal alignment. The annotations capture ongoing actions, entity appearances and attributes, interactions, and evolving contextual cues along the video timeline. This time-resolved structure supports fine-grained evaluation, long-range modeling and reasoning, instruction data construction, representation learning, and video generation. Kairos provides a general-purpose foundation for modeling visual experiences over time. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.08755 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T14:49:57.341Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).