Metraipolis › archive › dc_db31c5d90e99
Image Classifiers are Efficient Self-Supervised Video Representation Learners — arXiv:2609.40347
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.40347
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:47:56.031Z
- SHA-256 of the archived text
770a8d5d2e0f11c8fbd826712aaf1e67630a0ec4fb69cf87b0cab39bb4f0e5bc- Stable URL of this page
https://metraipolis.com/documento/dc_db31c5d90e99
How to cite
Image Classifiers are Efficient Self-Supervised Video Representation Learners — arXiv:2609.40347 — arXiv (en), https://arxiv.org/abs/2609.40347 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db31c5d90e99 (Metraipolis archive dc_db31c5d90e99, sha256 770a8d5d2e0f11c8fbd826712aaf1e67630a0ec4fb69cf87b0cab39bb4f0e5bc)
BibTeX
@misc{dcdb31c5d90e99,
title = {Image Classifiers are Efficient Self-Supervised Video Representation Learners — arXiv:2609.40347},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.40347},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db31c5d90e99; sha256 770a8d5d2e0f11c8fbd826712aaf1e67630a0ec4fb69cf87b0cab39bb4f0e5bc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.40347. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We introduce VideoMSN, a Masked Siamese Network framework for efficient self-supervised spatio-temporal representation learning in videos. Instead of relying on heavy 3D architectures or reconstruction-based autoencoders for learning with unlabeled data, we repurpose standard image Vision Transformers by representing videos as super images which are grids composed of frames sampled from videos. From each super image, we construct two views: one with spatial patch masking and the other with temporal frame masking, ensuring no information leakage across frames. A shared Vision Transformer (ViT) encoder aligns their embeddings using a masked Siamese loss, capturing both motion and appearance cues without reconstruction. Our decoder-free formulation leverages an image foundation model towards efficient video representation learning. Starting from pretrained DINO-v3 and DeiT-v3 image encoders, VideoMSN achieves state-of-the-art performance on Kinetics-400, UCF101, and HMDB51 while requiring up to $32\times$ fewer and $160\times$ fewer video pretraining epochs compared to prior video self-supervised learning methods. Our proposed approach also shows strong performance in low-shot classification, confirming the transferability of the learned representations in a label-scarce scenario. Project Page: this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.40347 — 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 2026-10-07T13:18:10.703Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).