Metraipolis › archive › dc_568e693da4ca
Spatio-Temporal Multi-Order Interaction for Video Recognition — arXiv:2611.05633
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.05633
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:17:27.158Z
- SHA-256 of the archived text
61b63391d1c9497ef0c397c772dbc7628884cc083ede2f6ab481625a13d6d864- Stable URL of this page
https://metraipolis.com/documento/dc_568e693da4ca
How to cite
Spatio-Temporal Multi-Order Interaction for Video Recognition — arXiv:2611.05633 — arXiv (en), https://arxiv.org/abs/2611.05633 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_568e693da4ca (Metraipolis archive dc_568e693da4ca, sha256 61b63391d1c9497ef0c397c772dbc7628884cc083ede2f6ab481625a13d6d864)
BibTeX
@misc{dc568e693da4ca,
title = {Spatio-Temporal Multi-Order Interaction for Video Recognition — arXiv:2611.05633},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.05633},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_568e693da4ca; sha256 61b63391d1c9497ef0c397c772dbc7628884cc083ede2f6ab481625a13d6d864},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05633. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Many temporal approaches for video recognition rely on explicit cross-channel aggregation projections, which have quadratic complexity in the number of channels, introducing significant computational overhead. In addition, the spatio-temporal representation used for video recognition is biased either toward local order interactions (for CNNs) or toward global order interactions (for transformers). Starting from the multi-order spatial representation of MogaNet, our method introduces two complementary contributions to tackle these problems. First, for the temporal modelling, we introduce parallel multi-order processing with depthwise-only convolutions and implicit gating-based aggregation, which is linear in the number of channels, inducing a considerable computational reduction. Second, we propose a dual interaction between spatial and temporal dimensions, which allows a better spatio-temporal representation without increasing the computational cost. By combining these two contributions, our proposed VideoMogaNet achieves performance on par with or better than state-of-the-art action recognition approaches across multiple video benchmarks (UCF101, HMDB51, Kinetics-400, Diving48), while considerably reducing the cost of the temporal branch. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.05633 — 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 2026-11-05T18:12:49.030Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).