Metraipolis › archive › dc_2ddeed0fb313

W2Rep: Learning Visual Representations by Watching the World Change — arXiv:2609.35464

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.35464
License (as archived): CC0-1.0
Archived: 2026-10-07T23:54:48.583Z
SHA-256 of the archived text: 2b716fb3154485b106c65023290c7f813b24d5a99522b1db18a21de2d8f89e6f
Stable URL of this page: https://metraipolis.com/documento/dc_2ddeed0fb313

How to cite

W2Rep: Learning Visual Representations by Watching the World Change — arXiv:2609.35464 — arXiv (en), https://arxiv.org/abs/2609.35464 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2ddeed0fb313 (Metraipolis archive dc_2ddeed0fb313, sha256 2b716fb3154485b106c65023290c7f813b24d5a99522b1db18a21de2d8f89e6f)

BibTeX

@misc{dc2ddeed0fb313,
  title = {W2Rep: Learning Visual Representations by Watching the World Change — arXiv:2609.35464},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35464},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2ddeed0fb313; sha256 2b716fb3154485b106c65023290c7f813b24d5a99522b1db18a21de2d8f89e6f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35464. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Images capture the world at one moment, whereas video reveals how it changes. Image self-supervision learns spatial structure from a single moment, while video methods commonly learn temporal relationships inside a representation computed jointly from several frames. We ask whether watching a scene change can instead improve features available from one image without sacrificing the ability to represent video. We introduce W2Rep, a masked feature-prediction framework in which an independently encoded source image participates in prediction at the same or another moment. The predictor is conditioned on visible video context, the queried location, and the signed time interval between source and target. This gives the cross-frame objective two complementary roles: the image path learns features that remain useful across time, while the video path must gather evidence that is missing from the source image. Across model scales and downstream tasks, W2Rep improves frozen and fine-tuned recognition under our comparison protocol, while joint video encoding provides further gains over frame-wise aggregation. Controlled experiments show that these gains depend on directly updating the source-image features and on using both video context and temporal displacement. Overall, change across a video can supervise a visual encoder whose representations remain useful at either image or video granularity. Code is available at~\href{ this https URL }{ this https URL }.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.35464 — 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 2026-10-07T23:29:27.577Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).